Datasets:

Abirate
/

min_write_ups

Dataset card Viewer Files Files and versions Community

Split (1)

train · 2.87k rows

Title of Competition stringclasses 168 values	Title of Writeup stringlengths 9 139	User stringclasses 1 value	Writeup stringlengths 419 61.5k
NeurIPS 2023 - Machine Unlearning	9th Place Solution (Forget set-free Approach, 3rd on Public LB)	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: NeurIPS 2023 - Machine Unlearning <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><h1>Forget set-free Approach (9th on Private LB, 3rd on Public LB)</h1> <p>First of all, thank you for organizing this meaningful challenge. It provided a great opportunity to deeply engage with the concept of machine unlearning and to exchange ideas with esteemed researchers.</p> <h2>Context</h2> <p>Business context: <a href="https://www.kaggle.com/competitions/neurips-2023-machine-unlearning/overview" target="_blank">https://www.kaggle.com/competitions/neurips-2023-machine-unlearning/overview</a><br> Data context: <a href="https://www.kaggle.com/competitions/neurips-2023-machine-unlearning/data" target="_blank">https://www.kaggle.com/competitions/neurips-2023-machine-unlearning/data</a></p> <h2>Overview</h2> <p>Our solution consists of <em>forgetting phase</em> and <em>remembering phase</em>. In forgetting phase, model parameters are stochastically selected and re-initialized. In remembering phase, knowledge preserving loss is calculated between the original model and the target unlearning model to remind the target model about retain set. Furthermore, the forgetting phase and remembering phase are repeated for some cycles to enhance unlearning performance.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4500975%2F606b7592ad5f5e6b32c17f85818b3c6b%2Foverall.PNG?generation=1701416396700810&alt=media" alt=""></p> <p>Table 1 demonstrates the unlearning performance of our final solutions, compared with other published unlearning methods [1-4]. Note that the public scores are recorded.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4500975%2Ffcd863e1c450a399533f3925210fa46a%2Ftable1.PNG?generation=1702128358580812&alt=media" alt=""></p> <h2>Details</h2> <h3>Experimental Settings</h3> <p>NeurIPS 2023 Machine Unlearning Challenge has specific code requirements. For example, the submissions should run 512 completely independent unlearning algorithms without any pre-compiled code or caching work between each run. Furthermore, these 512 runs should be completed within 8 hours. To obligate these requirements, few cycles of stochastic re-initialization and knowledge preserving process are executed. In detail, the first algorithm has 3 cycles with [1, 2, 2] epochs for each cycle. During the total 5 epochs, cosine learning rate scheduler (init_lr=0.001, T_max=2) is employed. The second algorithm has 4 cycles with [2, 1, 1, 1] epochs for each cycle and learning rate is set to [0.0005, 0.001, 0.001, 0.001, 0.001] for each epoch. Both algorithms randomly select 6 layers from the selection pool, while allowing replacement. The gaussian noise is sampled from the distribution of zero mean with 0.01 sigma. Note that only retain set is utilized for the experiments.</p> <h3>Logit Distribution</h3> <p>If the unlearning is successful, the unlearned model should produce similar logit distributions compared with the retrained model. Therefore, in addition to the quantitative metric, we observed the distribution of logits when feeding forget set and retain set to the models. Logit values of forget set and retain set are collected and visualized as a overlapped histograms in Figure 2 and Figure 3. As demonstrated in Figure 2 and Figure 3, Our unlearned models produces closer distributions with the distributions of retrained model, when compared with the naively fine-tuned model. Because the challenge dataset is hidden, MUFAC dataset [5] is utilized to visualize these distributions.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4500975%2F82c3f0aa1b1df3f1354253ea0d30913d%2Flogits.PNG?generation=1702129823962503&alt=media" alt=""></p> <h3>Explored Methods</h3> <p>Aforementioned unlearning methods come from several interim experiments. In this section, some interim findings are introduced to follow our decision process. </p> <h4>Re-initialization</h4> <p>When stochastic re-initialization is employed in addition to the fine-tuning, the score surpasses that of pure fine-tuning. Furthermore, interestingly, parameter selection using diagonal elements of fisher information matrix decreases the score. These results are demonstrated in Table 2.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4500975%2Fa7bafc650a81274f36644b8160bcbb30%2Ftable2.PNG?generation=1702128837516533&alt=media" alt=""></p> <h4>Data Augmentation</h4> <p>Table 3 describes the effect of data augmentation. Gaussian noise, generated from a gaussian distribution with a mean of 0.0 and standard deviation of 0.1, is added to the retain set images.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4500975%2Fde255579512f779d39d06265c5527828%2Ftable3.PNG?generation=1702128859512521&alt=media" alt=""></p> <h4>Loss Functions</h4> <p>Table 4 describes the effect of different loss functions. Between the loss functions, MSE loss outperforms other loss functions, such as cross-entropy loss and L1 loss. </p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4500975%2F3317c74874cd638d5c5435f839253ef4%2Ftable4.PNG?generation=1702128943728505&alt=media" alt=""></p> <h4>N Cycles</h4> <p>It is unable to improve unlearning performance by simply increasing parameter selection ratio for re-initialization. However, we find that repeating cycles of forgetting phase and remembering phase significantly improves the performance. Table 5 demonstrates these improvements.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4500975%2Ff61d629e383ceda7a89654731f5575f2%2Ftable5.PNG?generation=1702128920501681&alt=media" alt=""></p> <h4>Layer-wise vs. Element-wise</h4> <p>In our experiments, layer-wise parameter selection highly surpasses element-wise parameter selection method, as shown in Table 6.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4500975%2Fe64dcf0616033366e9065ccccc26ee5f%2Ftable6.PNG?generation=1702128969844128&alt=media" alt=""></p> <h4>Selection Pool</h4> <p>Furthermore, it is effective to prevent some layers from the re-initialization. In our experiments, fully-connected layers and projection-shortcut layers should be excluded from parameter selection and re-initialization. Table 7 demonstrates these results.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4500975%2F378326d5b46ec9dd7237ef4ddcd80e16%2Ftable7.PNG?generation=1702128988087226&alt=media" alt=""></p> <h2>Conclusion</h2> <p>Our solution exclusively utilizes the retain set, omitting forget set and validation set. This can be effective when the forget set is already delected or its usage is prohibited.<br> However, as our solution involves random selection of layers, the unlearning performance may vary depending on the specific layers chosen.</p> <h2>Sources</h2> <p>[1] Laura Graves, Vineel Nagisetty, and Vijay Ganesh. Amnesiac machine learning. In Proceedings of the AAAI Conference on Artificial Intelligence, May 2021.<br> [2] Anvith Thudi, Gabriel Deza, Varun Chandrasekaran, and Nicolas Papernot. Unrolling sgd: Understanding factors influencing machine unlearning. In 2022 IEEE 7th European Symposium on Security and Privacy (EuroS&P), pages 303–319. IEEE, June 2022. ISBN 9781665416146, 9781665416153. doi: 10.1109/EuroSP53844.2022.00027.<br> [3] Eleni Triantafillou, Fabian Pedregosa, Jamie Hayes, Peter Kairouz, Isabelle Guyon, Meghdad Kurmanji, Gintare Karolina Dziugaite, Peter Triantafillou, Kairan Zhao, Lisheng Sun Hosoya, Julio C. S. Jacques Junior, Vincent Dumoulin, Ioannis Mitliagkas, Sergio Escalera, Jun Wan, Sohier Dane, Maggie Demkin, and Walter Reade. Neurips 2023 - machine unlearning, 2023.URL <a href="https://kaggle.com/competitions/neurips-2023-machine-unlearning" target="_blank">https://kaggle.com/competitions/neurips-2023-machine-unlearning</a>.<br> [4] Alexander Warnecke, Lukas Pirch, Christian Wressnegger, and Konrad Rieck. Machine unlearning of features and labels, August 2021.<br> [5] Dasol Choi and Dongbin Na. Towards machine unlearning benchmarks: Forgetting the personal identities in facial recognition systems, November 2023.</p> <h2>Supplementary Material</h2> <p>The detailed explanation of our methods can be found in pdf below: <a href="https://www.dropbox.com/scl/fi/izmzhmj3ktqk3ze6rhjv6/Kaggle_Unlearning_Challenge_Solution.pdf?rlkey=9pqw47izw4nuuthanw3czu1gi&dl=0" target="_blank">https://www.dropbox.com/scl/fi/izmzhmj3ktqk3ze6rhjv6/Kaggle_Unlearning_Challenge_Solution.pdf?rlkey=9pqw47izw4nuuthanw3czu1gi&dl=0</a></p> <p>Our solution code can be found in: <a href="https://www.kaggle.com/code/jaesinahn/forget-set-free-approach-9th-on-private-lb" target="_blank">https://www.kaggle.com/code/jaesinahn/forget-set-free-approach-9th-on-private-lb</a></p>
Bengali.AI Speech Recognition	44th Place Solution 🎉🎉🎉	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Bengali.AI Speech Recognition <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>Before into the topic, I would like to congratulate all team members: <a href="https://www.kaggle.com/nanaxing" target="_blank">@nanaxing</a>, <a href="https://www.kaggle.com/focuswilliam" target="_blank">@focuswilliam</a>, <a href="https://www.kaggle.com/zhangjinru" target="_blank">@zhangjinru</a>, <a href="https://www.kaggle.com/marcocheung0124" target="_blank">@marcocheung0124</a>. The first three of them are undergraduates and they are all new to Kaggle. CongratulationsBefore the topic, I would like to congratulate all team members: <a href="https://www.kaggle.com/nanaxing" target="_blank">@nanaxing</a>, <a href="https://www.kaggle.com/focuswilliam" target="_blank">@focuswilliam</a>, <a href="https://www.kaggle.com/zhangjinru" target="_blank">@zhangjinru</a>, <a href="https://www.kaggle.com/marcocheung0124" target="_blank">@marcocheung0124</a>. The first three of them are undergraduates and they are all new to Kaggle. Congratulation again on their first medal and the success of our first audio competition🥈🥈🥈!</p> <p>Then I acknowledge <a href="https://www.kaggle.com/takanashihumbert" target="_blank">@takanashihumbert</a> for his published training notebook <a href="url" target="_blank">https://www.kaggle.com/code/takanashihumbert/bengali-sr-wav2vec-v1-bengali-training/notebook</a>. Another acknowledgment is for <a href="https://www.kaggle.com/mbmmurad" target="_blank">@mbmmurad</a> for his work to introduce the audios of the dataset <a href="url" target="_blank">https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0</a> in <a href="url" target="_blank">https://www.kaggle.com/code/mbmmurad/dataset-overlaps-with-commonvoice-11-bn/notebook</a>.</p> <p><strong>Dataset</strong>: We directly used the data provided by the organizer and did not use any external data.</p> <p><strong>Training Environment</strong>: One Colab Pro+ account is utilized. Due to limitations of equipment and computing power, we are unable to train more models(like the punctuation model) and complete data sets. </p> <p><strong>Data Augmentation</strong>: Some augmentations like HighLowPass, Noise, and PitchShift are used to increase robustness.</p> <p><strong>Model Training</strong>: Pretrained model is from <a href="url" target="_blank">https://www.kaggle.com/datasets/takanashihumbert/bengali-ex002</a>. We put in one-tenth of the data for training each time (feature encoder and feature extractor take turns to freeze). For freezing the feature extractor, the lr is 2e-5 for warmup. For the feature encoder, it is 6e-6. In our experiments, bs=1. After training three-fifths of the data, the public score is 0.42 and private score is 0.503.</p> <p><strong>Decoding Parameters</strong>: We adjust the decoding parameters and displayed them in the notebook <a href="url" target="_blank">https://www.kaggle.com/code/yuliknormanowen/bengali-sr-wav2vec-v1-bengali-inference-for-v4?scriptVersionId=146374376</a>. </p> <p>Thank you all so much for reading this. If you have any suggestions, we are happy to accept them. We would be very grateful if you could upvote this topic🥺🥺🥺🙏🙏</p>
CommonLit - Evaluate Student Summaries	214th Place Solution	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: CommonLit - Evaluate Student Summaries <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>I am a student majoring in computer science and technology. Due to my love for mathematical modeling, I have been exposed to machine learning algorithms and kaggle. However, for a long time, due to the limits of my ability, I can only choose to participate in contests of notebook type.<br> This was the first NLP task I have participated in.Although I achieved a very regrettable ranking , I have learned a lot through the journey.<br> <strong>Model</strong><br> I choose Debertav3+LGBM & LGBM+autocorrect+Debertav3 in public notebook as a basic model。A few days after this, I tried to focus on developing the preprocessing part & the LGBM part of the code. And Optuna for finding the best parameter for LGBM.<br> <strong>Submissions overview</strong></p> <table> <thead> <tr> <th>model</th> <th>private score</th> <th>public score</th> </tr> </thead> <tbody> <tr> <td>CommonLit-ESS lgbm+autocorrect+DeBERTa V3 (Tuned) - Version 5</td> <td>0.484</td> <td>0.447</td> </tr> <tr> <td>Explained Tuned Debertav3+LGBM - Version 3</td> <td>0.485</td> <td>0.445</td> </tr> <tr> <td>Tuned Debertav3+LGBM+autocorrect - Version 2</td> <td>0.487</td> <td>0.450</td> </tr> </tbody> </table> <p>Unfortunately, I didn't get better results based on the original model.Finally, my score stabilized at 190th place in the public list.After sharking ,I ended up falling out of the prize zone.<br> <strong>Summary</strong><br> Through this competition, I understand my shortcomings, my machine learning is still at a entry level.<br> As a side note, I have always thought that the model with the same score is ranked by the order of submission time. After this competition, I found that even notebooks with the same code will have slightly different scores when submitted，my notebook has a score of 0.48475 on the first submission and 0.48497 on the second submission, which is an uncertain factor.</p>
Open Problems – Single-Cell Perturbations	#13: U900 team - PYBOOST is what you need	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>We would like to express great thanks to Kaggle and the organizers for creating that exciting (and quite difficult) challenge which is devoted to cutting-edge questions in bioinformatics. Research community will surely benefit from that. And great thanks to all participants and those who shared their ideas, notebooks, datasets, insights…</p> <p>Here is the report on U900 team approach. We follow the guidelines of the report provided by the organizers. The detailed Kaggle-style write-up of the solution is placed in the section 3.2 "Model design. Details" - Kagglers may prefer to jump to that subsection directly. </p> <h1>Context</h1> <p>Competition Overview: <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview</a><br> Open Problems: <a href="https://openproblems.bio/" target="_blank">https://openproblems.bio/</a></p> <h1>Table of contents</h1> <p>We follow <a href="www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview/judges-prizes-scoring-rubrics" target="_blank">organizer's guideline</a>:</p> <ol> <li>Integration of Biological Knowledge</li> <li>Exploration of the problem</li> <li>Model design</li> <li>Robustness</li> <li>Documentation & code style</li> <li>Reproducibility</li> </ol> <h1>Highlights</h1> <ul> <li>Main innovative tool - new gradient boosting algorithm designed for MULTI-target tasks - PYBOOST - developed by team member A. Vakhrushev. Effectiveness to predict thousands targets at once - distinguishes it from XGBoost, etc. E.g. aftermath: <a href="https://www.kaggle.com/code/alexandervc/op2-explore-4th-place-magic" target="_blank">solo PYBOOST</a> model can achieve private score 0.718 - better than top1 - 0.728. </li> <li>Openness and knowledge sharing. Team shared dozens notebooks, posts, datasets during the challenge - obtained: hundreds forks, thousands views, among 10 upvoted code notebooks 4 from the team (in particular <a href="https://www.kaggle.com/code/alexandervc/op2-eda-baseline-s" target="_blank">top1</a>). <a href="https://www.kaggle.com/code/alexandervc/pyboost-secret-grandmaster-s-tool" target="_blank">PYBOOST approach</a> has been openly shared, medal winning solutions incorporate it and as well as all top scored publicly open solo-models. We also organized and shared on Youtube webinars around the challenge (<a href="https://youtu.be/dRG3qTaALp0?si=wruKSL2wu-DZb6D2" target="_blank">1</a>,<a href="https://youtu.be/6ySKxnjHX8Y?si=llQxil9FCY-NB5Mc" target="_blank">2</a>,<a href="https://youtu.be/lcc5vY-Pycs?si=94hhV9IOwcbLbZHP" target="_blank">3</a>,) (as well as the one in 2022: <a href="https://youtu.be/aqUOz3nFYm4?si=XLWxMsoef8l6OpVU" target="_blank">1</a>,<a href="https://youtu.be/dS0p3e-Je90?si=REmpRqLgY3pIOdhO" target="_blank">2</a>… ) - with thousand+ views. </li> <li>Not only PYBOOST: several neural networks, in depth analysis of cross-validation schemes, methods to carefully control the diversity for models ensemble, non-standard approach to ensemble - forms the solution.</li> <li>Stability: 1) our public and private leaderboard rankings are approximately the same 2) <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/458939" target="_blank">aftermath:</a> correlation between public and private scoring - 0.98. Thus our models are stable and generalize well on unseen data - thanks to careful cross-validation for solo models as well as diversity control of the entire ensemble.</li> <li>In-depth biological knowledge exploration: we performed and publicly shared standard single-cell pipelines analysis with <a href="https://www.kaggle.com/code/alexandervc/op2-rna-seq-data-scanpy-adata-cell-cycle" target="_blank">Scanpy</a> and <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-adata-analysis-with-seurat" target="_blank">Seurat</a>, <a href="https://www.kaggle.com/code/alexandervc/op2-rna-seq-data-scanpy-adata-cell-cycle" target="_blank">cell cycle analysis</a>, <a href="https://www.kaggle.com/code/alexandervc/op2-eda-baseline-s" target="_blank">top upvoted EDA notebook</a>, <a href="https://www.kaggle.com/datasets/antoninadolgorukova/op2-supplementary-calcs-for-ml" target="_blank">created</a>, <a href="https://www.kaggle.com/code/alexandervc/op2-category-encoders-chembert-fingerpints-moldes?scriptVersionId=150999986&cellId=1" target="_blank">benchmarked</a> and analyzed <a href="https://www.kaggle.com/code/alexandervc/eda-morgan-fingerprint-features" target="_blank">1</a>,<a href="(https://www.kaggle.com/code/alexandervc/eda-molecular-descriptors-features" target="_blank">2</a> many features like ChemBert, molecular descriptors, Morgan fingerprints, etc…</li> </ul> <h1>1. Integration of Biological Knowledge</h1> <h2>1.1 Did you use the chemical structures in your model? Did you use other data sources? Which ones, why?</h2> <h4>Use of SMILES.</h4> <p>One of our key Neural Networks (see section “Family of Neural Networks based on NLP-like SMILES embedding”) use encoding for compounds based on their SMILES representation. It starts with Text Vectorization followed by Embedding layer and thus learns the embedding from the current data. We extended the training set with <a href="https://github.com/Ebjerrum/SMILES-enumeration" target="_blank">SMILES augmentation library</a>, unfortunately - no score uplift.</p> <h4>Use and benchmark Morgan Fingerprints and Molecular Descriptors, ChemBert embeddings.</h4> <p>We encoded compounds by these techniques (<a href="https://www.kaggle.com/code/antoninadolgorukova/op2-feature-engineering/notebook" target="_blank">Notebook</a>, <a href="https://www.kaggle.com/datasets/antoninadolgorukova/op2-supplementary-calcs-for-ml" target="_blank">Kaggle dataset</a>, <a href="https://www.kaggle.com/code/alexandervc/eda-morgan-fingerprint-features" target="_blank">EDA1</a>, <a href="https://www.kaggle.com/code/alexandervc/eda-molecular-descriptors-features" target="_blank">EDA2</a> ). Systematically compared these features with other encodings: ChemBert embeddings, pure machine learning encodings: one-hot, Helmert contrast encoding, Backward Difference. The tables in the <a href="https://www.kaggle.com/code/alexandervc/op2-category-encoders-chembert-fingerpints-moldes?scriptVersionId=150999986&cellId=1" target="_blank">notebook</a> show a bit surprising outcome that the most simple one-hot encoding is the most effective among those. At least among those encodings - which are not incorporating targets, target encoding techniques are more effective - <a href="https://www.kaggle.com/code/alexandervc/op2-target-encoders" target="_blank">benchmarked separately</a>.(All these notebooks and datasets were openly shared during the challenge). Final ensemble did not include these models. </p> <h4>DrugBank</h4> <p>We also analyzed and shared on Kaggle the DrugBank database ( <a href="https://www.kaggle.com/datasets/antoninadolgorukova/op2-supplementary-calcs-for-ml/data?select=drug_bank" target="_blank">Kaggle dataset</a> ) with the idea - split compounds by similarity groups and use group indicators as additional features for our models. However due to technical reasons (not all challenge compounds found in DrugBank) and lack of time - that was not implemented. Aftermath: <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/460567" target="_blank">team#43 reported</a> uplift for Pyboost from the similar idea.</p> <p>Our other models relied on pure ML technique for encoding compounds and cell types - target encoding. </p> <h2>1.2 What representation of the single-cell data did you use? Did you reduce genes into modules? Did you learn a gene regulatory network?</h2> <p>Mainly we worked directly with the pseudo-bulk differential expressions train dataset provided by the organizers ('de_train.parquet'). Various target encoding techniques (see “model design” section) were employed. </p> <h3>Genes reduction by clustering - helps some models</h3> <p>Two of our models included the reduction genes into groups. The genes were clustered by K-means into 3 groups based on input train dataset. Features were constructed by target encoding techniques for each group and neural networks were predicting each group independently. Concatenation was done at the final step. These models are among our top scored solo models (0.569, 0.570) as well as they allowed us to increase diversity in that family of our models. See e.g. <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-simple-mlp-part-of-13th-place-solution?scriptVersionId=154341265&cellId=56" target="_blank">correlations clustermap</a> for that family of models - the two mentioned above are: N3,4 ("3kmeans" in id). </p> <h3>Use of raw scRNA-seq counts data</h3> <p>Another two our models employed raw single-cell RNA sequencing data. That have been done using aggregation by cell-types and compound the raw counts expressions data, and further PCA and target encoding (see <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-adata-analysis-with-seurat#6.1.-Make-features" target="_blank">section 6.1. Make-features</a> ). Thus we created new features which have been used for training the neural networks. These features have been concatenated with the original one - we did not gain the performance, but we gained some diversity and so blend with the original one - brings uplift. The performance of the original model and the one with raw count features is described in the <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-simple-mlp-part-of-13th-place-solution?scriptVersionId=154412513&cellId=49" target="_blank">table</a> - pre-last raw (MLPv15 TE scaled_counts_features) - public score 0.583 - similar to other models. All the models from that table were averaged gaining score 0.573 and that entered as a component to the final ensemble (described in the <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-simple-mlp-part-of-13th-place-solution?scriptVersionId=154412513&cellId=52" target="_blank">next table</a>). </p> <h2>1.3 How did you integrate the ATAC data? Which representation did you use?</h2> <p>Integration of single cell ATAC data, or any other single cell (e.g. CITE-seq) data can be done by exactly the same scheme as described and utilized above for raw single cell RNA sequencing count data - aggregation, dimensional reduction (PCA), target encoding. We did not have enough time to explore these models. </p> <h2>1.4 If adding a particular biological prior didn’t work, how did you judge this and why do you think this failed?</h2> <p>Prior bio-knowledge will always contain a kind of "batch effect" - different type of cells, donors, conditions, technology so on… Batch effect problem is no so solvable or even well-defined because what can be unwanted batch is one situation, is desired biological effect in the other. During the Open Problems 2022 we studied a lot how to use various biological prior knowledge - we and colleagues organized a kind <a href="https://www.kaggle.com/competitions/open-problems-multimodal/discussion/348293" target="_blank">crowd-source activity</a> and participants openly shared with community solutions and datasets based on <a href="https://www.kaggle.com/code/annanparfenenkova/ridge-with-reactome-features" target="_blank">Reactome pathway database</a>, <a href="https://www.kaggle.com/code/visualcomments/sim-ppi-corr-output" target="_blank">Protein-protein interaction networks</a>, and so on and so forth. The idea was constructing features based on aggregation by the biologically motivated groups of genes , pre-selecting those which related to targets based on prior knowledge. Followed by modified forward selection addition of these features <a href="https://www.kaggle.com/code/visualcomments/mmscel-crossvalidation-schemes-features-select#Exploration-of-additional-features" target="_blank">if the cross-validation scores increases</a>. However the outcomes were less prominent than pure ML approaches by the other teams. It resembles the situation with NLP where key successes of LLM are big models and large datasets - while prior knowledge (linguistic) approaches are not so effective. As we can see from Open Problems 2021, 2022 and the current challenges there are always teams on top who rely solely on ML methods. In some sense ML-models extract information from the train data more effectively than our prior knowledge databases. </p> <h1>2 Exploration of the problem</h1> <h2>2.1 Are there some cell types it’s easier to predict across? What about sets of genes?</h2> <h3>Myeloid cells are more difficult to predict than B cells for the current challenge. (Not surprising biologically).</h3> <p>However that is most probably specific to the current dataset.<br> That is quite natural from prior knowledge: B-cells and all cell types from the train - are lymphoid cells, while myeloid is different branch of the blood cells e.g. see <a href="https://en.wikipedia.org/wiki/Haematopoiesis" target="_blank">hematopoiesis</a>. So B-cells are more similar to train cells than myeloid cells and so it is natural that prediction for B-cells goes better. </p> <p>Similar we can see from the data (without prior knowledge): multiple evidence (<a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/458842" target="_blank">e.g. clustermap, umap, etc</a>) leads to the following picture - NK-cells are the most close to test set, and the most close to B-cells rather than to Myeloid cells, T-regs are the next close, while T-cells CD4+ and <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/458842" target="_blank">especially CD8+ least close</a>. So since NK-cells a) are in the train b) closer to B-cells - hence we see translation goes better for B-cells. If train set would contain other cell type which is close to Myeloid cells - than it would be opposite. By “most close” we mean with respect to the current data, not the prior biological knowledge. </p> <p>The analysis comparing predictability of B-cells and Myeloid cells is the following:<br> There are 17 samples of each type in the train set - so one can compare local metrics for these samples and see that B-cells are better predicted <br> For test samples we do not have ground truth - but we can compare disagreement between different models predictions - we see that models quite more often disagree on Myeloid cells rather than on B-cells. See e.g. <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-analysis-of-different-models-predictions#-Correlations-between-all-models-included-in-the-final-ensemble" target="_blank">https://www.kaggle.com/code/antoninadolgorukova/op2-analysis-of-different-models-predictions#-Correlations-between-all-models-included-in-the-final-ensemble</a> </p> <h3>Genes</h3> <p>The first order of magnitude effect controlling genes predictability is, of course, how big are their values (more precisely how big are the values of their differential expression, since we are working with it) - bigger values - everything is bigger - prediction errors, variations etc… <br> The interesting question is what are the other effects. <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-analysis-of-different-models-predictions?scriptVersionId=154657444&cellId=148" target="_blank">Figures here</a> show the analysis.<br> We see that, for each model, especially, Pyboost, there is a subset of genes with big SD and quite low variance, meaning that a model is quite confident in their prediction despite the high variability of DE. Also, each model gives highly variable predictions to a subset of genes with quite low SDs. </p> <p>More details on the analysis added in the <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/461663" target="_blank">post</a> and <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-analysis-of-different-models-predictions" target="_blank">notebook</a>. Some highlights:</p> <ul> <li>All models are less confident in their predictions for myeloid cells compared to B cells (medians of prediction variability across genes and samples are higher).</li> <li>However, the highest bias (differences between predicted and true values) and variability of gene expression change predictions are associated with individual drugs rather than cell types.</li> <li>These drugs are mostly outliers - with the lowest number of cells (≤10 cells), or drugs that affected the cells in such a way that they were misclassified (discovered by <a href="https://www.kaggle.com/ambrosm" target="_blank">@ambrosm</a> in his <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/458661" target="_blank">Excellent EDA</a> ).</li> <li>GO enrichment analysis suggests that the hard-to-predict genes are often related to immune cell activities, cytotoxicity, and cell death. Though it might be some artefact. </li> </ul> <h3>2.2 Do you have any evidence to suggest how you might develop an ideal training set for cell type translation beyond random sampling of compounds in cell types?</h3> <p>As we understand the question - it is about planning new experiments to cover much higher number of the cell type, comparing to only 6 in the current challenge. With the goal to reduce expansive experiments costs in favor of a cheap computational computational approach. For that question - the experience of the current challenge suggests the following: </p> <p>Ideally we should take into account similarity distance between the cell types. Having the similarity - the strategy is the standard one - uniformly subsample train set with respect to similarity distance. In other words (simplified a bit): perform clustering of cell types with respect to similarity distance and choose say 1 representative from each cluster - that would be “ideal” training set. That ensures that every cell type would have a “neighbor cell type” belonging to the train set which is similar enough to it and so “translation” would go smoothly. </p> <p>So the key question - what similarity relation for cell-types to consider.</p> <p>We suggest: first run a preliminary experiment with SMALL number of drugs but LARGE number of cell-types - which allows to define similarity for cell types as similarity of their response to drugs. And take that similarity relation as a basis. </p> <p>Rationale and details behind that suggestion are the following. The <a href="https://www.kaggle.com/code/alexandervc/op2-eda-baseline-s?scriptVersionId=147818286&cellId=21" target="_blank">clustermap of cell-types</a> clearly suggests the relations described above: NK-cells close to B-cells and Myeloid, T-cells CD8+ are the most distinct, and the key points are the following:</p> <ul> <li>That similarity is consistent with models results. So: it is defined without any modeling, but models “respects” it: e.g. <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/458842" target="_blank">exclude T-cells CD8+</a> often improves modeling quality - and that corresponds to the fact CD8+ cells are the most different from the others on the clustermap; <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/460251" target="_blank">NK-cells is the best validation fold</a> for some models like Pyboost, etc. - and that corresponds to the fact that NK-cells most close to B-cells and Myeloid cells on the clustermap</li> <li>It is not evident from the prior biological knowledge. </li> </ul> <p>So it would be much more cost effective to define the similarity between cell types based on some prior biological knowledge (e.g. just the distance in some umap space for some atlas scale single cell dataset). But experience of the current challenge makes us doubt that such similarity would perform well on drug response tasks. </p> <p>If experiments are planned “one by one”, but not “all at once”, it is worth considering “active learning” strategy - analyzing results after each step, and choosing for the next step of experiment those cell types which are in the worst predicted clusters. </p> <h1>3 Model design.</h1> <p>We split that section into two parts the first one is devoted to answers to organizer's questions. The second part is detailed write-up of the solution - Kaggler's may prefer to jump directly to the subsection 3.2</p> <h2>3.1 Answers to organizer's questions</h2> <h3>3.1.1 Is there certain technical innovation in your model that you believe represents a step-change in the field?</h3> <h4>PYBOOST - a new innovative gradient boosting tool</h4> <p>Which is developed for MULTI-target tasks by team member A. Vakhrushev - we believe an important step-change in a field. It is well-known that for tabular data with SINGLE target gradient boosting (XGBoost, LightGBM, CatBoost) are the top performers - showing better result than e.g. Random Forest, SVR, etc. and even Neural Networks (neural works are best performing on images, audio, text - some kind of continuous, not tabular data). However these packages are not so effective when one needs to predict many targets simultaneously. PYBOOST resolves that issue providing an effective strategy to predict even thousands of targets at once by a gradient boosting approach. </p> <p>The innovative features of the PYBOOST consists of two parts: strictly-Pyboost - which is software library and the SketchBoost - which is algorithmic innovation which improves algorithmic part of gradient boosting on multi-target tasks. (But for brevity by PYBOOST we typically mean both parts). The software part - strictly-Pyboost - is software library which allows the efficient realization of the complicated boosting algorithms directly in Python utilizing GPU, that means we can write easy to deal Python code, but it will be almost as efficient as low level optimized C-code - because of utilizing the GPU. The second part is algorithmic innovation - "Sketchboost" - provides new strategy to speed up tree structure search in multioutput setup by approximating ("sketching") the scoring function used to find optimal splits. Approximation is made by reducing dimensions of the gradient and hessian matrices while keep other boosting steps without change, thus enables crucial speed-up for the main bottleneck in boosting algorithm.</p> <p>For more details we refer to the <a href="https://openreview.net/forum?id=WSxarC8t-T" target="_blank">paper</a>, and the <a href="https://youtu.be/5xRxuDh_cGk" target="_blank">webinar</a>. </p> <p>We openly shared the PYBOOST approach with the community during the challenge <a href="https://www.kaggle.com/code/alexandervc/pyboost-secret-grandmaster-s-tool" target="_blank">Notebook</a>, <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/454700" target="_blank">Post</a>. It gained hundred forks, becoming component of gold-zone solutions as well as other medal winning. Moreover aftermath shows that <a href="https://www.kaggle.com/code/alexandervc/op2-explore-4th-place-magic" target="_blank">solo-Pyboost solution</a> combined with ideas by the other teams provides better results than current top1. Recent top2 solution for the CAFA5 challenge - prediction Gene Ontology terms is also <a href="https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/434064" target="_blank">based on Pyboost</a>. Thus PYBOOST is quite effective for such kind of MULTI-target biological tasks. </p> <h3>3.1.2 Can you show that top performing methods can be well approximated by a simpler model?</h3> <p>It depends on the meaning of the “simpler”, let us try two variants for that meaning: </p> <h4>Answer 1. Production ready solution expected not to lose much compared to huge Kaggle-style ensemble</h4> <p>1) One side of the question seems to be: What is the estimated performance loss between Kaggle-style huge ensembles (not production ready) and production-ready reasonable solutions ?<br> In short - we think the performance loss would NOT be essential - some very rough and pessimistic estimation can be - let us say the top gives 0.558, then production ready (with ~2 solo models) - 0.566, with 3 solo models - 0.563, with 4 solo models 0.559. <br> We also think that appropriate modification of the PYBOOST solution deserves to be considered as the production ready solution, it is high performing, easy to use, maintain and modify. It is typically quite diverse from NN solutions and blend with any NN would uplift the scores. </p> <p>But … <br> But it seems we are not ready to give more precise analysis, because - strange and unusual things happened - just after the competition closure and based on published solutions and write-ups - new combined solutions breaking current top1 appeared (we followed that route - and demonstrated that <a href="https://www.kaggle.com/code/alexandervc/op2-explore-4th-place-magic" target="_blank">solo PYBOOST model beats the top1</a> ). So in some sense we do not know what are the real “top performing solutions” - almost surely combining approaches we can go quite further. Nevertheless we hope that it would not change the basic answer - the difference between the huge ensembles and production ready solutions is not expected to be essential. </p> <p>What seems to be essential - the setup with metric (MRRMSE) and preprocessing (LIMMA log-p-values) is not the perfect way. And so we recommend to update that first - before making any further conclusions for production choices. To give some details - it seems that setup MRRMSE + log-p-values is very sensitive to outliers, and that is the reason why see: solutions “Nothing but just multiplied a factor of 1.2” , leaderboard super-successful probing during the challenge and so on. </p> <h4>Answer 2</h4> <p>If we understand the question in a slightly different manner: is it possible to approximate top solutions by some conceptually “trivial” ones ? <br> Then the answer is: NO. It is clear from write-ups that teams incorporate models like Neural Networks, Pyboost, and have non-trivial findings - so we would not call that “trivial”. Also at the early stage of the competition we have tried more than 50 simple models+feature encodings: Ridge, SVR, KernelRidge, Catboost, etc… - but all of them showed results worse than 0.600 - so to break that barrier one should already do something a bit non-trivial. (The predictions and the analysis were openly shared during the challenge <a href="https://www.kaggle.com/datasets/alexandervc/open-problems-single-cell-perturbations-submitsetc" target="_blank">Kaggle dataset</a> link.)</p> <h3>3.1.3 Is your model explainable? How well can you identify what is causing your model to respond to certain inputs?</h3> <p>PYBOOST has feature importance estimation as any other boosting or Random Forest algorithm. For the Neural Networks we can apply the special techniques like activation maps technique to gain certain interpretation.</p> <h2>3.2 Model design. Details</h2> <p>We constructed diverse models to gain the stability and better performance. Each has been carefully cross-validated. While ensembling we controlled diversity and preferred to rely on the most stable schemes. The main innovative part of the solution - is PYBOOST - a new gradient boosting algorithm developed by team member (Kaggle grandmaser) Anton Vakhrushev. </p> <h3>3.2.0 Solution principal components:</h3> <p>1 Family of Pyboost/Catboost models<br> 2 Family of MLP-like Neural Networks employing target encoding<br> 3 Family of Neural Networks based on NLP-like SMILES embedding<br> 4 Analysis of several cross-validation schemes and CV-LB correspondence <br> 5 Multi-stage blend scheme with diversity control and weights equal to 0.5 at each stage</p> <p>Below we report on each item one by one. </p> <h3>3.2.1 Family of Pyboost/Catboost models</h3> <p>Here we describe construction of PYBOOST and CatBoost models - both by the same scheme. PYBOOST performs better, but CatBoost is diverse enough and provide uplift in blend. The code: Pyboost: <a href="https://www.kaggle.com/code/alexandervc/pyboost-secret-grandmaster-s-tool" target="_blank">the basic baseline notebook</a>, other versions of the PYBOOST are in the <a href="https://www.kaggle.com/alexandervc/pyboost-u900" target="_blank">notebook</a>. Catboost <a href="https://www.kaggle.com/code/alexandervc/fork-of-op2-oof-new-folds-v3-catboost" target="_blank">Notebook</a> , <a href="https://www.kaggle.com/code/alexandervc/fork-of-op2-oof-new-folds-v3-catboost?scriptVersionId=152513917" target="_blank">version 64, scores 0.584, 0.776</a></p> <h4>Highlights:</h4> <ol> <li>PYBOOST “out of box” gives quite good results (better than “out of box” our other models), but couple of tricks improves it:</li> <li>Target Encoding by Quantile 80 - that was found by systematic consideration of all target encoders and all their params</li> <li>Retraining on several “ALMOST ENTIRE” train subsets - the logic is simple: we have very few samples - so: retrain on entire train set - helps the model, but we slightly improved it: generate several “almost entire” train subsets, train on all of them, average the results. Thus we gain from both - larger train sets and diversity. </li> <li>CatBoost provides diverse enough solutions from Pyboost, even with less performance it is useful in blend. </li> </ol> <h4>Modeling organization:</h4> <p>The core Pyboost and Catboost models are organized as follows (TSVD + TargetEncoder scheme):</p> <ul> <li>TSVD reduction of targets to say 70 dimensions (components)</li> <li>Target encoding of cell type and compound by these components </li> <li>Train model to predict these components (NOT the original targets). <br> (For PYBOOST - one model predicts all components at once,<br> For CatBoost - train 70 models - one for each component - it is time consuming, but feasible)</li> <li>Predict TSVD components for the test set. And finally use TSVD-inverse-transform - to obtain original (genes) targets from the predicted components. </li> </ul> <h4>The key findings :</h4> <h5>Quantile 80 target encoder</h5> <p>brings significant boost in performance e.g. 0.602->0.586 for Pyboost and CatBoost. Default value - Quantile 50 is significantly worse. That have been found by systematic consideration of all possible category encoders and all their params. The notebook (openly shared) <a href="https://www.kaggle.com/code/alexandervc/op2-gentle-param-tuner" target="_blank">“Gentle tuner”</a> provides a framework to tune params of the models and encoders together (employing several CV-schemes simultaneously). First we found that effect for CatBoost (<a href="https://www.kaggle.com/code/alexandervc/op2-gentle-param-tuner?scriptVersionId=150416991&cellId=36" target="_blank">notebook v61 linked figures</a>) and then employed for PYBOOST.</p> <h5>The subsets for training - critically affect the scores.</h5> <p>Idea - “train on multiple ALMOST ENTIRE train subsets”. <br> Motivation: due to the small number of samples many of our models benefit if we retrain them on the ENTIRE train set (before the submission). But that is not the best way, which is - employ ALMOST ENTIRE train subsets, but SEVERAL of them :<br> I.e. retrain models on 5-10 subsets of the train (each sized 80-99% of the entire train set) and average the predictions of all these models to get the submission.<br> Thus models benefit from both - more information and diversity. <br> The trick uplifts Pyboost from 0.584 to 0.577</p> <p>Some details. Let us emphasize one moment - “CV tuning and submit preparation are DIVORCED” in contrast to the usual Kaggle approach. I.e. The whole process is two staged - first one is standard - we search for optimal params of the model using the cross-validation. At the second stage - submission preparation - we forget about CV folds and generate new training subsets (these “almost entire train” subsets). We train the model with SAME params (found by CV) on these subsets and average the predictions. It is important that we do not use early stopping - number of trees/epochs was optimized by CV at the first stage and fixed on the second stage. That allows to retrain on (almost) entire train set - impossible with early stopping. So cross-validation and submission preparation are divorced in contrast to the usual Kaggle approach. The strategy works most probably due to the small sample number. It is employed for boostings and one of our Neural Networks (Target Encoding based). </p> <h5>Exclude T-cells CD8+</h5> <p>One small improvement 0.586->0.584 (but stably seen for other variants of the PYBOOST also) - exclude T-cells CD8+ from the training set.</p> <h4>Notes:</h4> <p>Pyboost outperforms CatBoost about 0.010 for that task in equal setups, but their predictions are diverse enough to get uplift in blend. </p> <p>The standard tuning experiments:<br> Tuning the standard params for boostings - number of trees, max depth, learning rate, etc… as well as number of TSVD components - bring uplift from around 0.604 to 0.602 - so not that much crucial as ones above. We tried a bit PCA/ICA instead but TSVD but got downlifts. </p> <h4>Comments.</h4> <p>Comment on TSVD-scheme. Employment of TSVD (or PCA, or ICA) reduction of targets is a more or less standard approach to treat mult-target tasks e.g. widely used in Open Problems 2022. Its obvious benefit is simplification - direct prediction of 18211 targets is not feasible for many models (except NN). Less obvious benefit ( a bit surprisingly): it often improves the performance, despite seemingly loss of information reducing 18211 targets to say 70. The reason is: what is lost - mostly noise, not the useful information and so reduction to say 70 components - kind of denoises the data and helps the model. We also experimented with PCA/ICA, but TSVD seems better for boostings, while for NN we used PCA. (See our first notebooks for some experiments. And of course, that is not universal - depends on the data). </p> <p>Remark (other models): the TSVD-scheme above can be applied for any model - we experimented a lot with Ridge,SVR, Kernel Ridge, LightGBM, Random Forest, ExtraTrees - but only Pyboost and Catboost showed good results for us. Somehow surprisingly, LightGMB was not effective, despite CatBoost was - typically it is not like that. See <a href="https://www.kaggle.com/code/alexandervc/op2-gentle-param-tuner" target="_blank">“Gentle tuner”</a> public notebook. </p> <p>Comment (Target Encoders - pay attention to LeaveOneOutEncoder): <a href="https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.TargetEncoder.html" target="_blank">Target encoding</a> is a standard way to treat categorical features. The idea is to substitute the category by mean (median, quantile, etc) of target with respect to that category. There are many modifications of target encoding and they have several parameters: Quantile Encoder (respectively), LeaveOneOutEncoder, CatBoost Encoder, James-Stein Encoder. We made systematic benchmarking of the encoders for that task for many models. As said above Quantile80 Encoder uplifts boostings a lot. We should also note that LeaveOneEncoder deserves special attention - for linear and close to linear (SVR, some Kernel Ridges) it stably outperforms other encoders (<a href="https://www.kaggle.com/code/alexandervc/op2-target-encoders" target="_blank">tables</a>). For Boostings it is either the second one (after Quantile80) and even the first one (depending on training set configuration e.g. <a href="https://www.kaggle.com/code/madrismiller/copy-of-pyboost-secret-grandmaster-s-to-1d68b4?scriptVersionId=150557250" target="_blank">top public Pyboost 0.574</a> utlized LeaveOneOut and tricky preparation of the train set). </p> <p>PS</p> <p>Not enough time: </p> <p>PYBOOST predicting directly 18211 targets , i.e. not predicting TSVD-components followed by tsvd.inverse_transform - but just directly. <br> We did not have enough time to tune params, out-of-box we got 0.594 <a href="https://www.kaggle.com/code/alexandervc/fork-of-op2-oof-new-folds-v5-pyboost-no-tsvd" target="_blank">notebook</a> - not enough score comparing to our other models, so not included in the final ensemble. On the other hand we checked it is quite diverse from the tsvd-based PYBOOST, so we think it is promising to combine these two approaches. </p> <p>We planned to try feature engineering by target encoding not only from TSVD , but from biologically motivated groups of genes, or from most important features (<a href="https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366455" target="_blank">as grandmaster Silogram did in 2022</a>) but did not have enough time for that.</p> <h3>3.2.2 Family of MLP-like Neural Networks employing target encoding</h3> <p>We developed a Neural Network model which features are: Target Encoding of PCA components. And then we developed a huge number of variations for that basic model. Key ensemble gained 0.566 and included 8 model variations. <br> The main notebook with models: <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-simple-mlp-part-of-13th-place-solution" target="_blank">Notebook MLP with Target Encoding</a> </p> <h4>Highlights:</h4> <ol> <li>Easy to diversify the basic model and benefit from the ensemble of the variations - changing augmentation, noise levels, varying features, training subsets, activations etc. - one obtains models with similar performance, but diverse enough to boost the ensemble (blend)</li> <li>Raw single cell RNA-seq data employed in the same scheme, same can be done for ATAC-seq </li> <li>Model is very stable and easy to implement - various changes do not degrade the performance </li> <li>Genes clustering into groups is easily employed and boost the performance</li> <li>Magic (simple) train duplicating trick improved score significantly: 0.600+ -> 0.580+</li> <li>Training on "almost entire" train subsets boosted 0.580+-> 0.570+; blend boosted to 0.566</li> </ol> <h4>Modeling organization and details:</h4> <ul> <li>Feature creation: Target Encoding of cell-type and compounds by PCA-components, 100 components considered for both </li> <li>Architecture: Multi-layer perceptron with 2 layers (200,256,18211) ; activation: “relu”</li> <li>Prediction scheme: 18211 targets directly (PCA is used for feature creation, but we do not predict PCA components here - in contrast to Pyboost scheme)</li> <li>CV scheme: 5-fold cross-validation scheme - folds containing only leaderboard drugs are used, split randomly in 5 groups. </li> <li>Training/Tuning: loss: MAE; optimizer: AdamW; batch size: 256; max learning rate: 0.01, decayed with weight: wd = 0.5 - one-cycle learning rate strategy <a href="https://skeydan.github.io/Deep-Learning-and-Scientific-Computing-with-R-torch/training_efficiency.html" target="_blank">lr_one_cycle</a>; epoch number have been tuned and fixed to 20. (Fixed epoch number allows to retrain model on the (almost) entire train set, while early stopping methods forbid that way).</li> <li>Training/Submit: Retrain model on “almost entire” train subsets (i.e. entire train with exclusion 2-3-10 subsamples)</li> <li>Magic (simple) train duplicating trick improved score significantly: 0.600+ -> 0.580+</li> </ul> <h4>The strategy to create variations of the basic model employed the following techniques:</h4> <ul> <li>Changing the training set methods: exclusions of the samples which originate from extremely low numbers (1 or 2) of single cells processed in pseudo-bulk procedure. </li> <li>Genes clustering into groups (e.g. 3 groups by K-means); processing each group separately and concatenating the predictions</li> <li>Augmentation techniques: varying number train duplicates; different noise levels for cell type and compounds; linear combinations of features + targets to create new samples; </li> </ul> <p>Params used during the challenge: <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-simple-mlp-part-of-13th-place-solution?scriptVersionId=153981848" target="_blank">notebook version 52</a>. The precise description of all 10 variations of the basic model entered in the final submission is <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-simple-mlp-part-of-13th-place-solution?scriptVersionId=154412513&cellId=50" target="_blank">here</a>. The diversity analysis of the these variations is <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-analysis-of-different-models-predictions?scriptVersionId=154657444&cellId=153" target="_blank">here</a> - one can see - some models are quite diverse from the others - correlation score 0.9. </p> <p>We employed the same idea training on "almost entire" train subsets as described for PYBOOST above. It boosted scores approximately: 0.580+-> 0.570+. </p> <h3>3.2.3 Family of Neural Networks based on NLP-like SMILES embedding</h3> <p>We developed several NN models employing direct encoding of SMILES by embedding layer (technique coming from NLP). The key single model achieved 0.574, another quite diverse model entering the final ensemble - 0.587 and the last hours combination achieved 0.571 score - incorporating pseudo-labeling technique (not included in the selected blend submit). These solutions originate from the <a href="https://www.kaggle.com/code/kishanvavdara/nlp-regression" target="_blank">public one</a> by Kishan Vavdara though substantially reworked from architectural and training points of view uplifting the score from 0.607 (original) to 0.574 and further.</p> <h4>Highlights:</h4> <ol> <li>Lion - new powerful optimizer - outperformed Adam </li> <li>Magic (simple) train duplicating trick improved score 0.582 -> 0.574</li> <li>SMILES encoding by the embedding layer</li> </ol> <h4>Modeling organization (key 0.574 model):</h4> <p>The <a href="https://www.kaggle.com/code/alexandervc/nlp-regression-custom-kfold-update1" target="_blank">main notebook</a>, the submission with 0.574 (0.766 pricate) score is <a href="https://www.kaggle.com/code/alexandervc/nlp-regression-custom-kfold-update1?scriptVersionId=151529557" target="_blank">version 11</a>.</p> <ul> <li>Feature Encoding: SMILES - by Embedding layer, Cell Types - One-hot; both concatenated</li> <li>Architecture: 5-Layer (1558,512,256, 128, 256, 18211) Perceptron with carefully chosen Batchnorm and Dropout layers positions, activation: “elu”</li> <li>Preprocessing: Standard Scaler for targets, Add Gaussian Noise for features</li> <li>Training: Lion optimizer; loss: competition loss - MRRMSE (custom); 5 almost random folds; best (by validation score) epoch (out of 300) is restored for each fold - that appears to be quite important</li> <li>Prediction scheme: 18211 targets directly, (TSVD - not used at all) </li> <li>The trick with duplicating the train for each fold yields 0.582->0.574 uplift. Similar to our other NN models. </li> <li>Tuning: params were optimized by CV</li> </ul> <p>The model is defined in notebook section <a href="https://www.kaggle.com/code/alexandervc/nlp-regression-custom-kfold-update1#The-model" target="_blank">"The model"</a>, the next cell contains a <a href="https://www.kaggle.com/code/alexandervc/nlp-regression-custom-kfold-update1?scriptVersionId=154712856&cellId=64" target="_blank">figure</a> with the graphical description.</p> <p>So the model organized as follows: SMILES are encoded via the embedding layer and Cell Type via one-hot; both encodings concatenated; that followed by 5-dense-layers perceptron (1558,512,256, 128, 256, 18211) carefully interchanged with batchnorm and dropout layers; activation is “elu”. <br> We checked the stability of the model as follows. Rerun it with several times with similar params compare CV scores and submit. We stably observed similar CV scores and moreover LB scores at the range 0.581-0.583 - before adding train duplication trick and 0.574 after. That is quite in contrast to the original model - which has larger score variance: 0.600 - 0.617 at least (see experiments <a href="https://www.kaggle.com/code/erotar/fork-of-nlp-regression-12a31a?scriptVersionId=150057568" target="_blank">here</a> ). </p> <h4>What did not worked well for that version of the NN:</h4> <ul> <li><a href="https://github.com/Ebjerrum/SMILES-enumeration" target="_blank">SMILES augmentation package</a> </li> <li>LSTM/CNN architectures, other optimizers, pseudolabeling, dropping out noisy samples. </li> <li>The trick to retrain model on the entire train also was not successful for that NN (in contrast to other models) because the epoch number determined by early stopping was different from fold to fold and fixing it to some particular number - degraded the CV-scores and so we did not want to risk employing the models not having good CV scores. Spent quite a lot efforts to resolve it, but unsuccessful. </li> </ul> <h4>That family of models also included other variants:</h4> <p>It yielded 0.587 score in initial version (included in final blend) <a href="https://www.kaggle.com/bejeweled/scp-blend-own" target="_blank">notebook1</a>, <a href="https://www.kaggle.com/bejeweled/scp-pseudo50-ct-strat-mrrmse-tf-smilesv" target="_blank">notebook2</a>. And last hours change yielded 0.571, but not giving significant boost to the entire blend construction (so not included in the chosen submits): </p> <p>Highlight:</p> <ul> <li>The 0.571 versions heavily employed pseudolabeling: <a href="https://www.kaggle.com/code/bejeweled/op2-u900-part-of-solution-pytorch-tf-nns" target="_blank">https://www.kaggle.com/code/bejeweled/op2-u900-part-of-solution-pytorch-tf-nns</a></li> </ul> <p>The other findings are the following: </p> <ul> <li>With the LSTM layer after smile embeddings.</li> <li>With sigmoidal range activation as the model output.</li> <li>With multiplication of outputs by coefs.</li> <li>With pseudolabels from these models blends.</li> </ul> <p>PS</p> <p>What did not work: we spent quite efforts on Neural Network based on one-hot encoding of the compounds, even achieving local CV-uplift, but LB score still appeared to be 0.619 <a href="https://www.kaggle.com/code/alexandervc/fork-of-op2-oof-new-folds-v4-nnohe" target="_blank">notebook</a>, changing architecture, augmenting train, changing one-hot to similar encodings: Helmert, Backward difference, etc - nothing worked. We got same LB score as in the early version - which is just average of many random seeds in the simple version of the net from the public: <a href="https://www.kaggle.com/code/alexandervc/op2-kishan-s-nn-streamlined-and-blended" target="_blank">notebook</a>. The <a href="https://www.kaggle.com/code/kishanvavdara/neural-network-regression" target="_blank">original net</a> seems to be quite unstable - public score varies with the seed 0.599 - 0.620, and not so good results on private. </p> <h3>3.2.4 Analysis of several cross-validation schemes and CV-LB correspondence</h3> <p>Here we describe our approaches to cross-validation, analysis of the CV-LB correspondence.<br> More details (tables, figures, etc) can be found in the separate <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/460251" target="_blank">post</a>. </p> <p>CV - LB correspondence is quite problematic in the current challenge. Its better understanding would be important for research community future works. Even aftermath writeups analysis seems to reveal that good solution for CV-LB correspondence is not found yet. During the challenge several logical CV-schemes were proposed - AmbrosM - <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/443395#2457831" target="_blank">discussion</a>, <a href="https://www.kaggle.com/code/ambrosm/scp-quickstart?scriptVersionId=144293041&cellId=8" target="_blank">notebook</a> or MT's scheme: <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/444494#2466644" target="_blank">discussion</a>, <a href="https://www.kaggle.com/code/masato114/scp-quickstart-another-cv-strategy/notebook" target="_blank">notebook</a>. MT proposes to put in validation SAME CELL-TYPES as on LB, while AmbrosM proposes SAME COMPOUNDS. However even early analysis showed far from perfect correspondence to LB for both schemes. Note: we developed and <a href="https://www.kaggle.com/code/alexandervc/op2-class-for-custom-cv-schemes" target="_blank">openly shared</a> the Python class which conveniently encapsulates these and other CV-schemes.</p> <p>Here are some our findings:</p> <h4>Highlights</h4> <ol> <li>Local (CV) row-wise correlation score is better related (0.5) to LB (mrrmse score) than other metrics </li> <li>Local (CV) mrrmse score is near zero correlated with the LB (mrrmse score) for all CV schemes considered</li> <li>NK cells local mrrmse is better correlated to LB ( 0.2+), while for T-cells CD8+ it is negative (-0.1+) </li> <li>NK-cells local mrrmse is well related with LB for Pyboost models, but not for other e.g. NN models</li> <li>Random folds are NOT worse than more logical and sophisticated CV-schemes; and seems preferable for NN models</li> <li>Public and private LB scores - highly correlated: 0.98, despite poor CV-LB correspondence</li> </ol> <p>So, there seems to be many surprises: despite the LB metric is mrrmse - the best locally related to it - is the OTHER metric - row-wise correlation; while local mrrmse performs near zero. Another surprise - CV-LB correspondence is poor - while public-private LB is very good - 0.98 correlation. And also it is surprising that random folds performs not worse than more logical schemes.</p> <h3>Further notes/suggestions:</h3> <ol> <li>Models of the same nature/features - the CV-LB correspondence somehow working (not so good but still) for all CV schemes. So strategy can be - tune each particular model by CV, verifying by LB - that what we used. </li> <li>The main problem to compare different models - even close models Pyboost and Catboost, with same public LB scores e.g. 0.584 may show quite different CV score like 0.92 vs 0.89, and even worse for boosting vs NN. So for final blend we decided to rely more on LB score, rather than on CV. </li> </ol> <p><strong>Setup. Potential bias.</strong> The analysis is based on more than 50 quite diverse models, still it can be biased by models choice. We see very clearly that local metrics better corresponding to LB are quite dependent on the model/features/etc.</p> <p>See further analysis in the separate <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/460251" target="_blank">post</a>. </p> <p>PS</p> <p>To complement: here is table (<a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/460251#2553943" target="_blank">from here</a>) showing correlation of CV and LB for different metrics for a set of SIMILAR models (NN based on target encoding) - we see it is quite high (better for public, less for private): </p> <table> <thead> <tr> <th>metric</th> <th>corr_vs_public</th> <th>corr_vs_private</th> </tr> </thead> <tbody> <tr> <td>MRRMSE</td> <td>0.69</td> <td>0.39</td> </tr> <tr> <td>corr_rows</td> <td>-0.79</td> <td>-0.53</td> </tr> <tr> <td>corr_cols</td> <td>-0.74</td> <td>-0.48</td> </tr> <tr> <td>R2</td> <td>-0.64</td> <td>-0.42</td> </tr> </tbody> </table> <p>Pay attention that for models of diverse nature - correlations are much lower, even for that family of models but with bigger modifications of feature construction - correlations become much lower (see <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-tricks-and-metrics?scriptVersionId=155213609&cellId=53" target="_blank">table</a>). (See <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/460251#2553943" target="_blank">post</a> for more details).</p> <h3>3.2.5 Multi-stage blend scheme with diversity control and weights equal to 0.5 at each stage</h3> <p>Here we describe our approach to ensemble (blend). The more detailed explanations and working code are in the <a href="https://www.kaggle.com/code/alexandervc/op2-u900-team-blend" target="_blank">notebook</a>.</p> <h4>Highlights:</h4> <ul> <li>Main problem - absence of good CV - LB correspondence - forbids the usual strategy to choose weights by CV</li> <li>Solution relies on: how to increase and control diversification; how to avoid overfit-proning choice of weights - a scheme of multi-step blend with the only weight = 0.5 on each step.</li> <li>Measure of diversity - average target-wise correlation of predictions</li> <li>Check by various experiments: models with correlation score 0.8-0.9 - consistently give substantial uplift in blend (about +0.01 - 0.006)</li> <li>Avoid overfit-proning question: how to choose weights of the models with DIFFERENT scores, by the following scheme:</li> <li>Core scheme: sequential blend of the models with EQUAL (almost) scores, giving them EQUAL blend weight (=0.5):</li> <li>step1: LB score 0.575 = 0.5 Pyboost(0.584) + 0.5 <a href="https://www.kaggle.com/code/alexandervc/fork-of-op2-oof-new-folds-v3-catboost?scriptVersionId=152513917" target="_blank">Catboost(0.584)</a> </li> <li>step2: LB score 0.566 = 0.5 step1 (0.575 ) + 0.5 <a href="https://www.kaggle.com/code/alexandervc/nlp-regression-custom-kfold-update1" target="_blank">NN-NLP (0.574)</a></li> <li>step3: LB score 0.559 = 0.5 step2 (0.566 ) + 0.5 <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-simple-mlp-part-of-13th-place-solution" target="_blank">MLP_TargetEncEnsemble (0.566)</a></li> <li>final polishing: 0.558 - blend more Pyboost (0.574,0.577) and NN (0.569,0.570,0.572,0.587) models:</li> </ul> <h4>Experiments with other blend ideas:</h4> <ul> <li>Different weights for B-cells and Myeloid cells (partially successful)</li> <li>Tried, but had not enough time to succeeded:<ul> <li>Estimate variance and correlations for each target (or each row) of predictions and choose blend weights according to modifications of the classical statistical formula - weights are proportional to variance - bigger variance - less confidence - lower weight in blend</li></ul></li> </ul> <h1>4. Robustness</h1> <h2>4.1 How robust is your model to variability in the data? Here are some ideas for how you might explore this, but we’re interested in unique ideas too.</h2> <p>The robustness of our models can be advocated e.g. as follows. Our public and private leaderboard ranking is approximately the same, moreover it corresponds to our ranking during last weeks of challenge (ignoring the effect of public-LB-probing notebooks appearing at the end). Aftermath: we <a href="https://www.kaggle.com/code/alexandervc/op2-public-vs-private-scores" target="_blank">computed the correlation</a> between public and private scores of our submits and it is 0.98. So models well generalize on the unseen data. <br> Additionally we performed the following tests for most of our models during the challenge - changed params a bit and made submissions - the variations was always around 0.001-0.002. </p> <p>All the models have been optimized by local cross-validation scores and only then submitted to LB, we accepted only those changes which improve both CV and LB. </p> <h3>4.2 Add small amounts of noise to the input data. What kinds of noise is your model invariant to? Bonus points if the noise is biologically motivated.</h3> <p>Gaussian noise has been included at the feature generation stage for our neural network models. We tested several values of noise magnitude and chose the optimal values of the noise level. </p> <h1>5. Documentation & code style</h1> <p>The code is documented in the notebooks.<br> The section 3.2 "Model Design - Details” here provides quite detailed description of the solution. </p> <h1>6. Reproducibility</h1> <p>Source code is here available in the notebooks:<br> Pyboost: <a href="https://www.kaggle.com/code/alexandervc/pyboost-secret-grandmaster-s-tool" target="_blank">the basic baseline notebook</a>, other version of the PYBOOST are in the <a href="https://www.kaggle.com/alexandervc/pyboost-u900" target="_blank">notebook</a>.</p> <p>Catboost <a href="https://www.kaggle.com/code/alexandervc/fork-of-op2-oof-new-folds-v3-catboost" target="_blank">Notebook</a> , <a href="https://www.kaggle.com/code/alexandervc/fork-of-op2-oof-new-folds-v3-catboost?scriptVersionId=152513917" target="_blank">version 64, scores 0.584, 0.776</a></p> <p>MLP-like Neural Networks employing target encoding <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-simple-mlp-part-of-13th-place-solution" target="_blank">Notebook</a>, params used during the challenge: <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-simple-mlp-part-of-13th-place-solution?scriptVersionId=153981848" target="_blank">notebook version 52</a>.</p> <p>Neural Networks based on NLP-like SMILES embedding - <a href="https://www.kaggle.com/code/alexandervc/nlp-regression-custom-kfold-update1" target="_blank">the main notebook</a>, the submission with 0.574 (0.766 private) score is <a href="https://www.kaggle.com/code/alexandervc/nlp-regression-custom-kfold-update1?scriptVersionId=151529557" target="_blank">version 11</a>.</p> <p>Blend: <a href="https://www.kaggle.com/code/alexandervc/op2-u900-team-blend" target="_blank">Notebook</a>, selected final submit is version 15 - <a href="https://www.kaggle.com/code/alexandervc/op2-u900-team-blend?scriptVersionId=153084243" target="_blank">direct link</a>.</p> <p>Most of our submissions can be found in the Kaggle datasets <a href="https://www.kaggle.com/datasets/alexandervc/open-problems-single-cell-perturbations-submitsetc" target="_blank">submits and out-of-fold predictions</a>, <a href="https://www.kaggle.com/datasets/alexandervc/open-problems-2-submits-etc" target="_blank">Open Problems 2 Submits, etc</a></p> <p>Information on all submits with public and private scores is in the <a href="https://www.kaggle.com/code/alexandervc/op2-public-vs-private-scores/output?select=df_stat_submissions.csv" target="_blank">file</a></p> <p>Our initial PYBOOST notebook has been openly shared and forked about 100 times, being a component of top public solo models as well as many medal winning solutions - probably the best indication of the reproducibility. </p> <h1>Concluding remarks</h1> <h2>MRRMSE and log-p-values - may not be the perfect choice</h2> <p>The metric mrrmse and preprocessing - log-p-values by Limma - seems to cause certain problems. It seems that combination - mrrmse and log-p-values is too much sensitive to outliers. During the competition - the leaderboard has been probed too easily. It is also quite unusual appearance of the better than top1 late submits just 1-2 days after the end and medal zone solutions like “Nothing but just multiplied a factor of 1.2”. All that indicates: a) we (as a community) not fully understand the problem b) the metric was not chosen perfectly. We are not fully convinced that the argument that p-values allow to catch difference in distributions, while log-fold change will capture only the difference in averages between distributions - that would be the case for p-values of the concordance criteria like KS or Chi2, but it seems p-values by Limma capture only the difference in averages. What should be the proper choice of the metric and processing ? - seems to an interesting and important question. </p> <h2>small number of samples - but sill stable - how to anticipate ?</h2> <p>It seems the small number of samples was really frightening and prevented participation of many experienced Kagglers at the challenge. Small number of samples typically leads to high instability and shake-up at the end, thus people not willing to invest their time with big chances to be randomly ranked at the end. However, surprisingly, that seems to have appeared to be a mistake. There were only moderate changes in ranking for the leaders, aftermath shows quite high correlation 0.98 between public and private leaderboard scoring. So in some sense, a small number of samples was compensated by a large number of targets and overall ensured certain stability. Could be anticipated from the beginning i.e. despite small number of samples overall predictability is quite stable ?</p> <p>Overall “Open problems” team and Kaggle team are doing great job bringing cutting-edge datasets to community consideration and thus allowing to contribute the cutting-edge scientific research. We are happy to be a part of that activity. </p>
Open Problems – Single-Cell Perturbations	The 440th solution of the 'Open Problems – Single-Cell Perturbations' competition	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>Business context:<br> <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview</a></p> <p>Data context: <br> <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/data" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/data</a></p> <p>Code link:<br> <a href="https://github.com/900Step/Open-challenge" target="_blank">https://github.com/900Step/Open-challenge</a></p> <p>Overview<br> This solution considers the impact of drugs on the gene expression of unknown cell types from three aspects: dimensional change, feature construction, and regression algorithms. Due to the high dimensionality of genes, PCA is used to reduce the dimensions of the response variable. Natural language processing, combined with SMILE chemical structures, is employed to encode the drugs. For the regression algorithm, we attempt to use a simple regression model (SVR) for prediction. A tensor model is utilized to conduct stratified analysis on plate-class data. The regression effect of experiments on linear combinations of some public datasets.</p> <p>Data Processing</p> <p>Due to the project providing both public and private test sets, we do not perform any additional train-test splitting during the modeling process.</p> <p>Response variable<br> Our objective is to predict highly-dimensional gene expression data using existing cell type and drug information. Initially, this requires altering the data dimensions and structure. Given over 18,000 genes as response variables and the limited sample size, it becomes challenging to draw reliable conclusions. Further-more, this scenario often leads to model overfitting and weak interpretability. Hence, analogous to the independent variables, it is imperative to apply dimensionality reduction to the response variables. We employ the Principal Component Analysis (PCA) method, preserving 10-20 dimensions to maintain a cumulative contribution rate of 95%, thus constructing new response variables.</p> <p>Feature construction<br> The column ”SMILE” (Simplified Molecular Input Line Entry System [2]) encompasses the chemical properties of drugs, for instance, Clotrimazole, with its chemical encoding as<br> ”Clc1ccccc1C(c1ccccc1)(c1ccccc1)n1ccnc1”. We utilize natural language processing techniques<br> to encode the chemical expressions of drugs using strings. For example, ”c1ccccc1” represents<br> a benzene ring, and ”Cl” signifies a chlorine atom. Certain punctuation marks also bear specific meanings, such as ”=” for a double bond and ”#” for a triple bond. Through encoding chemical structures, we extract chemical structural features pertinent to the drugs. The S and R configurations in chiral structures are denoted by ”@” and ”@@”, respectively.</p> <p>After these transformations, we convert the boolean values of ”control” to {0,1}, remove the original three columns of drug information from the dataset, and thus obtain a preliminarily processed dataset.</p> <p>Modeling</p> <p>SVR<br> Using the SVM-based regression algorithm from scikit-learn for prediction, it can be anticipated that due to the low dimensionality of the independent variables and the complex relationships of the response variables, there will be a significant prediction error. This method does not incorporate any specificity processing based on the model's background.</p> <p>Tensor<br> We adapted Algorithm 3 from the article "Tensor Completion with Noisy Side Information" for tensor-based analysis. This approach involved transforming the original dataset into a 3-dimensional tensor object with the dimensions (146, 18211, 6), corresponding to (drug, gene, cell type). To address missing values in the gene expression data, a "warm start" matrix is employed. This matrix is initially populated with zeroes or randomized values for the absent data points. This technique provides a preliminary structure, aiding in more effectively estimating and filling in the missing gene expression values. </p> <p>CPA method (didn’t been realized but we think it is a good method)<br> I explored the CPA (Component-Based Pathway Analysis) method, which aims to uncover latent variables that influence response prediction. This algorithm converts gene expression data, along with all other features, into the 'adata' data type. By using a more complex data structure, it enables the full utilization of the information. Our goal is to garner more gene-related information, such as gene length, expression characteristics, and whether certain genes exhibit synergistic or antagonistic effects with specific cells or drugs. Enriching the feature information of the existing data could significantly reduce the prediction error rate for differential expression in the forecasting process.</p> <p>In Kaggle, there are some public datasets related to specific competitions. Building upon the corresponding files, I attempted to apply a linear combination with weighting to them. The results of this approach were superior to those of each individual file used in the process.<br> /kaggle/input/open-problems-2-submits-collection<br> /kaggle/input/op2-603<br> /kaggle/input/op2-604<br> /kaggle/input/op2-607<br> /kaggle/input/op2-720</p>
Open Problems – Single-Cell Perturbations	7th Place Solution for the Open Problems – Single-Cell Perturbations	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>Thank the organizers for hosting this interesting competition and congrats to the Winners.<br> It was a big surprise for me to see my resolution finally achieve 7th place. </p> <h2>Context</h2> <p><a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview</a><br> <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/data" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/data</a></p> <h2>Overview of the approach</h2> <p>My approach has two major steps: i) learn embeddings for all cell types, small molecular, and genes, ii) use embedding as features to train a deep learning model to predict the target while accounting for overfitting. Throughout the competition, I only used a fully connected network with three layers. My best submission is also based on a single FC model.</p> <h3>Learning embeddings</h3> <p>In this step, the goal is to learn a specific embedding for each cell type, molecular, and gene. I was strongly inspired by <a href="https://genomebiology.biomedcentral.com/articles/10.1186/s13059-020-01977-6" target="_blank">this paper</a>, where the authors used deep tensor factorization to learn a dense, information-rich representation for cell type, experimental assay, and genomic position. </p> <p>Basically, I used the same approach but played around with the model architectures and parameters, such as the number of latent factors, and the number of dimensions of the network, as well as how to combine the features (e.g., concatenate vs. additive). </p> <p>In the end, my mode is the following:</p> <pre><code> (torch.nn.Module): (): ().__init__() self.cell_types = cell_types self.compounds = compounds self.genes = genes self.n_cell_types = (cell_types) self.n_compounds = (compounds) self.n_genes = (genes) self.n_cell_type_factors = n_cell_type_factors self.n_compounds_factors = n_compounds_factors self.n_gene_factors = n_gene_factors self.cell_type_embedding = torch.nn.Embedding(self.n_cell_types, self.n_cell_type_factors) self.compound_embedding = torch.nn.Embedding(self.n_compounds, self.n_compounds_factors) self.gene_embedding = torch.nn.Embedding(self.n_genes, self.n_gene_factors) self.n_hiddens = n_hiddens self.dropout = dropout self.n_factors = n_cell_type_factors + n_compounds_factors + n_gene_factors self.model = nn.Sequential(nn.Linear(self.n_factors, self.n_hiddens), nn.BatchNorm1d(self.n_hiddens), nn.ReLU(), nn.Dropout(self.dropout), nn.Linear(self.n_hiddens, self.n_hiddens), nn.BatchNorm1d(self.n_hiddens), nn.ReLU(), nn.Dropout(self.dropout), nn.Linear(self.n_hiddens, )) (): cell_type_vec = self.cell_type_embedding(cell_type_indices) compound_vec = self.compound_embedding(compound_indices) gene_vec = self.gene_embedding(gene_indices) x = torch.concat([cell_type_vec, compound_vec, gene_vec], dim=) x = self.model(x) x </code></pre> <p>To train this model, I used all the data from <code>de_train.parquet</code> and converted the table as follows:</p> <pre><code> df = pd.read_parquet() df = df.sort_values([, ]) df = df.drop([, , ], axis=) df = pd.melt(df, id_vars=[, ], var_name=, value_name=) </code></pre> <p>The training data looks like:<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F642483%2Ffcf2b04f2255dc9fe2f0382320346feb%2FScreenshot%202023-12-05%20at%2021.02.43.png?generation=1701828192377214&alt=media" alt=""></p> <p>Here, I trained the model with 100 epochs without validation, because I will only the embedding layer for Step 2.</p> <p>To check if the model learns meaningful embedding for cell types, molecules, and genes, I also visualized the embedding with UMAP. For example, below is the 2D UMAP of gene embeddings:<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F642483%2F59782ef056d394c5deb99376c0af2a05%2FScreenshot%202023-12-05%20at%2021.05.28.png?generation=1701828348397738&alt=media" alt=""></p> <p>By eyeballing, it looks like there are some structures for the genes.</p> <h3>Predicting target</h3> <p>Once I obtained the embeddings, I trained another model to predict the target, and this model was also used to generate the final submission. Again, I used a FC network as follows:</p> <pre><code> (torch.nn.Module): (): ().__init__() self.n_input = n_input self.n_hiddens = n_hiddens self.dropout = dropout self.model = nn.Sequential(nn.Linear(self.n_input, self.n_hiddens), nn.BatchNorm1d(self.n_hiddens), nn.ReLU(), nn.Dropout(self.dropout), nn.Linear(self.n_hiddens, self.n_hiddens), nn.BatchNorm1d(self.n_hiddens), nn.ReLU(), nn.Dropout(self.dropout), nn.Linear(self.n_hiddens, )) (): x = self.model(x) x </code></pre> <p>To prevent overfitting, I used each of the cell types as validation data, which means my model was based on 4-fold cross-validation. For the compounds, I followed the notebook here to select the private test compounds for validation:</p> <pre><code> key, cell_type cell_type_names.items(): (cell_type) df_train = df[(df[] != key) \| ~df[].isin(privte_ids)] df_valid = df[(df[] == key) & df[].isin(privte_ids)] df_train = df_train.sort_values([, ]) df_valid = df_valid.sort_values() df_train = convert_to_long_df(df_train) df_valid = convert_to_long_df(df_valid) df_train.to_csv() df_valid.to_csv() </code></pre> <p>For model training, I used the following strategies:</p> <pre><code> criterion = torch.nn.MSELoss() optimizer = AdamW(model.parameters(), lr=args.lr, weight_decay=) scheduler = ReduceLROnPlateau(optimizer, , min_lr=) </code></pre> <p>I trained one model by using each of the cell types as validation data, and for the final submission, I just averaged the predictions.</p> <h2>What didn't work for me</h2> <p>During the competition, I spent a lot of time including the features based on prior knowledge, such as single-cell data, molecular structure embedding, and gene embedding for other large models, such as geneFormer. However, they all didn't work out. So my final model was just based on the features learned from Step 1.</p> <h2>Source</h2> <p><a href="https://github.com/lzj1769/7th_place_solution_Single-Cell-Perturbations" target="_blank">https://github.com/lzj1769/7th_place_solution_Single-Cell-Perturbations</a><br> <a href="https://genomebiology.biomedcentral.com/articles/10.1186/s13059-020-01977-6" target="_blank">https://genomebiology.biomedcentral.com/articles/10.1186/s13059-020-01977-6</a><br> <a href="https://github.com/jmschrei/avocado" target="_blank">https://github.com/jmschrei/avocado</a></p>
Open Problems – Single-Cell Perturbations	17th Place Solution for the Open Problems – Single-Cell Perturbations (ADEFR)	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>We are thrilled to share our solution with the community. Thanks to Kaggle and the Organizers for the opportunity to participate in such an interesting challenge.</p> <h2>1 Context</h2> <ul> <li><a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview" target="_blank">Competition Overview</a></li> <li><a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/data" target="_blank">Competition Data</a></li> </ul> <h2>2 Overview</h2> <ul> <li>Our solution comprises an ensemble of <strong>four gradient boosting based regression models</strong>, all trained on a shared feature set. Each model is endowed with distinctive hyperparameters and tailored training settings.</li> <li>Regression models are trained individually for each of the 129 compounds in the public/private test set, with the exception of instances where multi-regression is performed using <a href="https://github.com/sb-ai-lab/Py-Boost/blob/master/tutorials/Tutorial_2_Advanced_multioutput.ipynb" target="_blank">SketchBoost</a>.</li> <li>Local training and evaluation follow a "one-vs-rest" style cross-validation approach across four cell types with known target variables: <code>['NK cells', 'T cells CD4+', 'T cells CD8+', 'T regulatory cells']</code>.</li> <li>Important features used:<ul> <li>Gene-wise PCA derived from the differential gene expression (DGE) table.</li> <li>Mean single-cell gene expression averaged over cell types and compounds, with particular emphasis on the control compound expression levels to enhance results.</li> <li>Gene-wise PCA derived from downsampled single-cell transcriptomics data.</li></ul></li> <li>We averaged feature values of nearest neighbor genes (neighbors were calculated based on the DGE data). This potentially reduced noise and improved downstream modeling.</li> <li>Moreover, we realized the impact of the number of cells used for DGE per <code>(cell type, compound)</code> on the mean target value per <code>(cell type, compound)</code>. Consequently, we incorporated the number of cells listed in the training data per <code>(cell type, compound)</code> to define importance weights for each training record using the formula: <code>w = 1-1/np.sqrt(1+num_cells['obs_id'][cell_type][compound])</code></li> <li>Our final submission is a blend of our solution (more details in the <code>4 Models</code> section) and a <a href="https://www.kaggle.com/code/olegpush/op2-eda-lb" target="_blank">public one</a> with 0.5-0.5 equal weights.</li> </ul> <h3>2.1 Things that did not work</h3> <ul> <li>Inclusion of multiome data based features</li> <li>Inclusion of external knowledge based on<ul> <li>SMILES (we were experimenting with <a href="https://www.rdkit.org/docs/GettingStartedInPython.html" target="_blank">RDKit</a>)</li> <li>the <a href="https://string-db.org/" target="_blank">STRING database</a></li> <li><a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7289078/" target="_blank">sci-Plex</a>, <a href="https://pubmed.ncbi.nlm.nih.gov/29195078/" target="_blank">LINCS data</a></li></ul></li> </ul> <h3>3 Feature engineering</h3> <h4>3.1 Input data</h4> <ul> <li>We extract features from the differential gene expression (DGE) data (<code>de_train.parquet</code>) and the single cell transcriptomics data (<code>adata_train.parquet</code>, <code>adata_obs_meta.csv</code>):</li> </ul> <pre><code> pandas pd tr = pd.read_parquet(data_path + , engine=) genes = (tr.columns[:]) feats = (tr[tr[]==][].unique()) trx = pd.read_pickle(data_path + ) tro = pd.read_csv(data_path + ) genesx = (trx.index) obs = pd.DataFrame({:trx.columns}).reset_index().set_index() obs = obs.join(tro.set_index()).sort_values() X = trx.transpose() X = X.join(obs[[,]]) ... </code></pre> <ul> <li>We exclude single-cell records based on the file <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/454107" target="_blank">provided by Kaggle</a> </li> </ul> <pre><code>excluded_ids = pd.read_csv(data_path + ) excluded_ids[] = excluded_ids = excluded_ids.pivot(index=, columns=, values=) excluded_ids = excluded_ids.fillna() excluded_ids = excluded_ids[trx.columns] = trx[[]] = .join(excluded_ids).fillna() = (-) = np.array(.astype()) trx_ = np.array(trx) trx_ = * trx_ trx_ = pd.DataFrame(trx_) trx_.columns = trx.columns trx_.index = trx.index trx = trx_ ... </code></pre> <ul> <li>Importantly, we downsample the single-cell data to get an <strong><em>equal number of cells per cell type and perturbation</em></strong> and we use this subsampled data for some of the downstream generated features</li> </ul> <pre><code>D = [] sample_num = X.groupby([,]).count().().() (sample_num, end = ) sm_name X[].unique(): (sm_name,end = ) ct X[].unique(): x = X[X[]==sm_name] x = x[x[]==ct] x = x[genesx] x = x.head(sample_num) D.append(x) D = pd.concat(D,axis=) </code></pre> <h4>3.2 Single-cell transcriptomics data based PCA</h4> <ul> <li>We generate gene representations by performing PCA on this subsampled dataset</li> </ul> <pre><code> sklearn.decomposition PCA n_components = pca = PCA(n_components=n_components) d = D[genes].transpose() features_pca_genes_sc = pca.fit_transform(d) ... </code></pre> <h4>3.3 Mean gene expression based on the single-cell transcriptomics data</h4> <ul> <li>Mean gene expresison is calculated per cell type and compound</li> </ul> <pre><code>X = trx.transpose() X = X.join(obs[[,,]]) X = X[X[]] X[] features_mean_expression = {} cell_type X[].unique(): (cell_type, end = ) features_mean_expression_ = X[X[]==cell_type] features_mean_expression_ = features_mean_expression_.groupby()[genesx].mean() ... </code></pre> <h4>3.4 DGE based PCA</h4> <pre><code>cell_types_train = [, , , ] D = tr[tr.apply( x: x[] cell_types_train, axis = )][genes] D = D.transpose() D = (D - D.mean())/D.std() n_components = pca = PCA(n_components=n_components) features_pca_genes = pca.fit_transform(D) </code></pre> <h4>3.5 Raw DGE values of the 17 compounds known for all six cell types</h4> <pre><code>features_dge = {} cell_type cell_types: (cell_type, end = ) d = tr[tr[]==cell_type] d = d.set_index() d = d[genes].transpose() features_ = pd.DataFrame() feat feats: feat d.columns: features_[feat] = d[feat] : features_[feat] = features_dge[cell_type] = features_ ... </code></pre> <h4>3.6 Nearest Neighbor based 'smoothing' over genes:</h4> <pre><code> sklearn.neighbors NearestNeighbors feats = (tr[tr[]==][].unique()) tr_genes = tr[tr.apply( x: x[] feats, axis = )][genes] tr_genes = tr_genes.transpose() tr_genes = (tr_genes - tr_genes.mean())/tr_genes.std() gene_nn = nbrs = NearestNeighbors(n_neighbors=gene_nn+).fit(tr_genes) nn_distances, nn_indices = nbrs.kneighbors(tr_genes) cell_type cell_types: (cell_type, end = ) d = features_dge[cell_type] d_ = np.array(d) d_nn = np.zeros(d.shape) ii ((d)): n_neighbors = nn_indices.shape[]- jj= neighbor nn_indices[ii,:]: jj+= d_nn[ii,:] += d_[neighbor,:] d_nn[ii,:] = d_nn[ii,:]/n_neighbors ... </code></pre> <h4>3.7 Smoothed DGE values:</h4> <p>We use Ridge regression to reduce the noise for DGE values</p> <pre><code> numpy np (): eps = eps * np.var(data, axis=) nmat = data + np.random.normal(size=data.shape) * eps[, ...] solvemat = np.linalg.inv(nmat.T.dot(nmat) + lambd * np.diag(np.ones(nmat.shape[]))).dot(nmat.T) coefs = solvemat.dot(data) coefs features_dge_smoothed = {} cell_type cell_types: (cell_type, end = ) d = features_dge[cell_type] d_ = np.array(d).transpose() coefs = get_smoothing_coefs(d_) d_smoothed = (d_.dot(coefs)).transpose() d_smoothed = pd.DataFrame(d_smoothed) d_smoothed.index = d.index cols = [] col feats: cols.append(+col) d_smoothed.columns = cols features_dge_smoothed[cell_type] = d_smoothed </code></pre> <h3>4 Models</h3> <h4>4.1 Blending different boosting models</h4> <p>In our modeling framework, we use various boosting libraries with different settings.</p> <ul> <li><strong>LGBM:</strong> We predict DGE values for each of the 129 target compounds with different <a href="https://lightgbm.readthedocs.io/en/latest/pythonapi/lightgbm.LGBMRegressor.html" target="_blank">LightGBM regressors</a>. This model achieved a public LB score of 0.571. </li> <li><strong>LGBM_LIN:</strong> We added the prediction of a simple Linear Regression as extra features to the previous setting. Public LB score is 0.573.</li> <li><strong>SketchBoost:</strong> We performed multi-regression for the 129 target compounds with a single <a href="[https://github.com/sb-ai-lab/Py-Boost/blob/master/tutorials/Tutorial_2_Advanced_multioutput.ipynb]" target="_blank">SketchBoost</a> model. We trained this model with the following parameters: <code>{"ntrees":4096, "lr"=0.01, "subsample"=0.5, "colsample"=0.5, "min_data_in_leaf"=5, "max_depth"=5}</code></li> <li><strong>DART:</strong> We also use LightGBM with DART trained for 130 iterations with the following parameters: <code>{"feature_fraction": 0.7, "bagging_fraction": 0.6, "data_sample_strategy":'goss', 'boosting_type': 'dart'}</code>. Furthermore, we average out the predictions of five DART models trained with different random seeds.</li> </ul> <p>In our solution, we blend these models with equal (0.25) weights and then combine our prediction with a <a href="https://www.kaggle.com/code/olegpush/op2-eda-lb" target="_blank">public one</a>, as described above in the Overview section.</p> <h4>4.2. Feature importance</h4> <p>Below, we show some of our feature importance measurements for the SketchBoost component.<br> Observe that almost half of all importance is attributed to DGE-based gene PCA features (3.4). Ridge regression smoothing (3.7) proved to be slightly more effective than KNN-based smoothing (3.6). The remaining importance goes to raw compound DGE features (3.5) and mean expression values (3.3). </p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F611446%2Ff6b0a8cb4592370dd6a3a59d726fb68b%2Fcategory_imp.png?generation=1702845405654725&alt=media" alt="Top 20 most important features for SketchBoost"></p> <p>Finally, we show the top 20 most important features for the SketchBoost component.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F611446%2F52ad6d64f8ab92a9cc0d1252b5c89399%2Ftop20.png?generation=1702845427700935&alt=media" alt="Top 20 most important features for SketchBoost"></p>
Open Problems – Single-Cell Perturbations	6th Place Solution for the Open Problems – Single-Cell Perturbations	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><h2>1. Integration of biological knowledge</h2> <p>I tried integrating different biological knowledge, but unfortunately, most didn't work very well.</p> <p>Firstly, I came up with the idea of using the GO term to reduce genes into modules. I adopted the KEGG 2016 genes set and filtered out gene sets with a P-value less than 0.05. However, genes from the same set exhibit considerably different differential expression (DE) values. As a result, I feel the hypothesis that genes from the same GO term would have similar DE values cannot stand. Then, I resorted to finding co-expressed genes based on the gene expression matrix. I found the DE values between co-expressed genes do have a high Pearson correlation. However, I checked the predicted DE values of co-expressed genes and found they yield strong Pearson correlations as well. In other words, adding the correlation constraints to the optimization process won't have much effect.</p> <p>Next is about the molecule representation. I tried using the features from the pre-trained molecule models including ChemBERT and MolCLR, as well as the TFIDF-transformed element count proposed in the public notebooks. In my experiments, using the pre-trained features led to slightly inferior results, while the TFIDF-transformed element count and simply learnable molecule features give similar performance. I wonder if it is because the pre-training models capture more coarse-grained differences between molecules, or because the molecules in the contest are quite different from those used for pre-training.</p> <p>Finally is the integration of ATAC data. I did not have a good idea of integrating ATAC data into the model. All that I had come up with is that genes corresponding to a small ATAC count would be less affected by molecules. Anyway, I am not sure about such a hypothesis, and in practice, I simply concatenated the ATAC feature and found it slightly improves the results.</p> <h2>2. Exploration of the problem</h2> <p>According to the problem definition, I think three targets could be predicted to achieve the task. The first target is directly the DE values. The variables in DE value prediction would be cell types and compounds. A model could be trained to predict the DE value given cell type-compound pairs. The second target is the bulk expression values, namely, the input to the Limma model. The variables in bulk prediction would be only the compounds (as I will elaborate on later). I feel such a paradigm is the most promising and robust solution. The most important reason is that the results could be precisely validated. To be specific, we could send the predicted and provided bulk expressions to the Limma model, and check how close the predicted DE values are to the provided ones. I feel such a validation scheme would be much less risks in overfitting. The third target is the single-cell gene expression. Though the training data is most sufficient in such a paradigm, it is the most challenging paradigm since we do not have the paired before-perturbation and after-perturbation gene expression values.</p> <h2>3. Model design</h2> <p>In this competition, I mainly explored the first two prediction paradigms, namely the DE values and bulk expression values.</p> <h3>3.1 DE value prediction</h3> <h4>3.1.1 Preprocess</h4> <p>No data preprocessing is applied. Common preprocessing strategies such as normalizing and scaling even harm the performance in my experience.</p> <h4>3.1.2 Model architecture</h4> <p>The plainest model learns the cell type and compound representation, as well as makes the predictions at the same time. The model could be written within a few lines, namely,</p> <pre><code> (nn.Module): (): (Net, self).__init__() self.type_num = type_num self.compound_num = compound_num self.gene_num = gene_num self.type_embedding = nn.Embedding(self.type_num, ) self.compound_embedding = nn.Embedding(self.compound_num, ) self.predictor = nn.Sequential( nn.Linear(, ), nn.BatchNorm1d(), nn.Dropout(), nn.ReLU(), nn.Linear(, ), nn.BatchNorm1d(), nn.Dropout(), nn.ReLU(), nn.Linear(, self.gene_num), ) (): type_embedding = self.type_embedding() compound_embedding = self.compound_embedding(compound) embedding = torch.cat([type_embedding, compound_embedding], dim=) self.predictor(embedding) </code></pre> <p>Optionally, we could replace the learnable cell type representation with RNA or ATAC counts averaged by cell type, and replace the compound representation with features from pre-trained models such as ChemBERT and MolCLR. Training such a vanilla model gives 0.586 MRRMSE on the public test split and 0.785 MRRMSE on the private test split.</p> <p>I also tried Transformer architecture like the Performer used in the scBERT paper. The idea is to treat each gene as a token and replace the positional embedding with cell type and compound representation. The token of each gene is learned together with the Transformer model. Due to the space limitation, I will not attach the model configuration code here, please refer to the GitHub repository attached below. Sadly, though the Transformer architecture generally gives better performance, in my practice, I just cannot successfully train the model (i.e., the training loss stays very high), and achieved 0.611 MRRMSE on the public test split and 0.767 MRRMSE on the private test split. It was not until the competition ended that I found the Transformer architecture achieved a much better score on the private test split, despite its poor performance on the public test split. Such an interesting result is worth exploring (or it is simply due to randomness and luck).</p> <h4>3.1.3 Learning objective</h4> <p>To directly predict the DE values, I tried the MSE loss, L1 loss, and MRRMSE loss. The MRRMSE loss gives the best performance in practice. I did not use fancy tuning on the optimizer but simply used a standard Adam optimizer without any learning rate scheduler.</p> <h3>3.2 Bulk expression prediction</h3> <h4>3.2.1 Preprocess</h4> <p>The bulk count data is first normalized following the classic scRNA-seq preprocessing pipeline, namely, i) scaled to have 1e4 counts per bulk, ii) applied the log1p transformation, and iii) scaled to have zero mean and unit variance.</p> <h4>3.2.2 Model architecture</h4> <p>After many tries on the DE value prediction paradigm, I felt a bit frustrated since the performance gain only comes from the fancy tuning of the model architecture. Hence, I turned to try the bulk expression prediction paradigm in the later stage of the competition. According to the experiment design, I noticed that there is a negative control spot in each row on the plate. In other words, the only difference between the negative spot and the remaining spots lies in the added compound (please correct me if that is wrong). Consequently, we could predict the perturbed bulk expression values based on the baseline counts and the compound. To this end, I built a conditional autoencoder as follows,</p> <pre><code> (nn.Module): (): (Net, self).__init__() self.compound_num = compound_num self.gene_num = gene_num sm_feature : self.sm_emb = nn.Embedding(self.gene_num, ) self.sm_enc = : self.sm_emb = sm_feature self.sm_enc = nn.Sequential( nn.Linear(self.sm_emb.shape[], ), nn.BatchNorm1d(), nn.ReLU(), nn.Linear(, ), ) self.type_atac = type_atac self.atac_enc = nn.Sequential( nn.Linear(self.type_atac.shape[], ), nn.BatchNorm1d(), nn.ReLU(), nn.Linear(, ), ) self.encoder = nn.Sequential( nn.Linear(self.gene_num, ), nn.BatchNorm1d(), nn.ReLU(), nn.Linear(, ), ) self.decoder = ConditionalNet( dim_feature=, dim_cond_embed=, dim_hidden=, dim_out=self.gene_num, n_blocks=, skip_layers=(), ) (): self.sm_enc : sm = self.sm_emb(sm_name) : sm = self.sm_enc(self.sm_emb[sm_name]) encode = self.encoder(x) atac = self.atac_enc(self.type_atac[]) x = sm cond = torch.cat([encode, atac], dim=) pred = self.decoder(x, cond) pred </code></pre> <p>Notably, here I unnaturally chose the negative count and cell type-averaged ATAC count as conditions, while letting the compound be the input. In practice, such a configuration leads to better results than reversely setting negative count as input and compound as the condition. Such a result could probably be attributed to the over-fitting of compound representation for the later configuration. Likewise, I also tried the Transformer architecture but it does not work very well.</p> <h4>3.2.3 Learning objective</h4> <p>The model was trained to predict the normalized bulk count value change after adding the compound. The predicted normalized value is then recovered to the raw count according to the previous scaling and normalization factors. I tried the MSE loss, L1 loss, Smooth L1 loss, and MRRMSE loss, and found the Smooth L1 loss leads to the best performance. The predicted bulk value was then concatenated with the known bulk value and fed into the Limma model to compute the DE values.</p> <h4>3.2.4 Post preprocessing</h4> <p>Though the bulk expression prediction paradigm seems technically sound, its performance is not that satisfying. In my experiments, the prediction DE values differ a lot on the known compounds. Here, I would like to point out that comparing the DE values computed by Limma on the predicted bulk expression and the provided DE values is a solid validation metric, which would be less affected by the over-fitting problem. Anyway, I found the computed DE values have a larger mean compared with the provided ones. I wonder if it is because the Limma is applied on different sets of compounds (i.e., partially on the provided DE values but fully on the private DE values). Thus, I scaled the DE values computed by Limma to have the same mean on the known compounds. Such a paradigm ends up in the best MRRMSE of 0.587 on the public test split and 0.809 on the private test split.</p> <h3>3.3 Ensembling</h3> <p>Ensembling the results of the above two different paradigms led to 0.563 MRRMSE on the public test split and 0.755 on the private test split. By further ensembling the EDA results of 0.567 public score, the performance further improved to have 0.552 MRRMSE on the public test split and 0.728 on the private test split. The performance gain by ensembling results of different paradigms is surprising. Yes, my best history submission is even better than the 1st place in the leaderboard. However, it does not correspond to the best public score so I did not choose it as the final submission.</p> <h2>4. Robustness</h2> <p>For the DE value prediction paradigm, I tried removing compounds with extreme values such as "MLN 2238", but did not observe performance improvements. Adding noise to the inputs is less effective than adding the Dropout layers into the network. For the bulk expression paradigm, I tried removing the most dissimilar cell type "T regulatory cells" when training the model. Interestingly, the results were almost not influenced. The stronger robustness of the bulk expression paradigm could probably be attributed to the larger training data sample number. As for directly predicting the DE values, hundreds of data samples are too little to predict thousands of genes.</p> <h2>5. Documentation, code style, and reproducibility</h2> <p>The code and documentation can be accessed from <a href="https://github.com/Yunfan-Li/PerturbPrediction" target="_blank">https://github.com/Yunfan-Li/PerturbPrediction</a>.</p>
Stanford Ribonanza RNA Folding	[1st place solution] Transformer model with Dynamic positional encoding + CNN for BPPM features	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Stanford Ribonanza RNA Folding <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>The Ribonanza RNA Folding competition has been an amazing opportunity and we are really glad to have participated in it. Kudos to the hosts for their substantial effort in keeping the high organizational level and giving the contestants plenty of valuable insight and support. We would also like to thank the community for the fruitful public discussions and coding initiatives. Congratulations to everyone involved! 🎉</p> <h1>Code</h1> <p>Open source code is available on <a href="https://github.com/autosome-ru/vigg_ribonanza/" target="_blank">github</a>.</p> <h1>TLDR</h1> <p>Our solution is based on transformer architecture. We predicted base pair probability matrix(BPPM) for each RNA sequence using EternaFold and added convolutional blocks to our architecture to process BPPM features. For some models we added Squeeze-and-Excitation layer in convolutional blocks Also we add these features with attention values before softmax operation in Self-Attention block. To allow better generalization for longer input we implemented Dynamic Positional Bias. Then we ensembled models with slight differences in architecture and training process.</p> <h1>Data Preprocessing</h1> <p>At first, for each sequence in train and test datasets we calculated a base pair probability matrix (BPPM) using EternaFold. During training and inference phases we passed to our model the RNA sequences encoded with a learnable embedding layer. Each nucleotide was considered a token and special <strong>< start ></strong> and <strong>< end ></strong> tokens were placed at both ends as well. To provide the model with the information about whether the sequence comes from a “clean” subset of training dataset (which SN_filter values show - 1 corresponds to “clean” sequences with high signal-to-noise ratio and 0 is otherwise) we encoded SN_filter values with a learnable embedding layer and added corresponding embeddings to sequence embeddings. The embedding dimension was chosen to be of size <strong>192</strong>. BPPMs were padded with zeros at their margins to account for adding <strong>< start ></strong> and <strong>< end ></strong> tokens. The figure below summarizes the data preprocessing part.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16725112%2F482c2d20fce57fa513021909a515e98b%2Fpreprocessing.png?generation=1701994647204619&alt=media" alt=""></p> <h1>Model</h1> <p>The model idea is partially inspired by <a href="https://www.kaggle.com/shujun717" target="_blank">@shujun717</a> solution to the Open Vaccine challenge, <a href="https://www.kaggle.com/competitions/stanford-covid-vaccine/discussion/189564" target="_blank">link</a></p> <p>The model takes a sequence of tokens and BPPM as input and outputs DMS_MaP and 2A3_MaP reactivities for each input nucleotide. Its architecture comprises 12 consecutive Transformer Encoder Layers and an output projection linear layer. Each Transformer block takes a sequence of tokens and BPPM features from the previous layer and outputs updated feature maps as shown below. The Transformer Encoder block adopts common transformer encoder architecture, except we modified the Self-Attention block to ensure interaction between BPPM features and sequence features.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16725112%2F0c70879344b972d64ba13945e163a126%2Fmodel_general_view.png?generation=1701994737102906&alt=media" alt=""></p> <h2>Self-Attention Block</h2> <p>In the Self-Attention (SA) block we implemented an attention mechanism with the following modifications: after attention values for each head are calculated, we add BPPM features updated by the ‘Convolutional block’, which outputs BPPM features with the number of channels corresponding to the number of heads in the SA block. We set the number of heads in SA and corresponding channels of BPPM features to be 6. Thus, the hidden dimension size of Q, K, V matrices is 32. The overall structure of the SA block is shown below.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16725112%2F5a7bf6e6f893938ced8bdd2e9a1fb08c%2Fselfattention.png?generation=1701994715778085&alt=media" alt=""></p> <h2>Dynamic Positional Bias</h2> <p>The sequence length is distributed differently in train and test datasets (test sequences are generally longer). To allow for the better generalization of longer inputs we implemented a positional encoding to be added to attention values. We found Dynamic Positional Bias to be of more use compared to other relative positional encoding methods we tried, such as xPos (rotary positional encoding) and ALiBi. Dynamic Positional Bias calculates for each head a relative positional bias map, which is learnable and depends on sequence length. Relative positional bias doesn’t allow to leverage distance from start and end of sequence, so tokens <strong>< start ></strong> and <strong>< end ></strong> were added to fix that.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16725112%2F8d8468983d7a7d057dcf74d7511b3ac8%2Fdynpos%20(1).png?generation=1701994757603986&alt=media" alt=""></p> <h2>Convolutional Block and SE block</h2> <p>The models in the final ensemble come in two versions that are slightly different in the structure of the Convolutional block. The basic Convolutional block consists of 2D convolutional layer, batchnorm layer, activation and learnable gamma parameters that scale the output feature channels, whereas the modified version of this block (SE-Convolutional block) also contains Squeeze-and-Excitation layer, hence the name. The SE layer applies input-dependent rescaling of values along the channels as shown below. Thus, the only difference between models in the ensemble is the presence of the SE layer.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16725112%2F4b8f15f5aa950ba64ecbd55df123cad4%2Fconv_se.png?generation=1701994778649467&alt=media" alt=""></p> <h1>Training Process</h1> <p>The training process has been adapted from the <a href="https://www.kaggle.com/code/iafoss/rna-starter-0-186-lb/notebook" target="_blank">notebook</a> by <a href="https://www.kaggle.com/IAFOSS" target="_blank">@IAFOSS</a><br> We used a one-cycle learning rate schedule (pct_start=0.05, lr_max=2.5e-3,) coupled with AdamW optimizer (wd=0.05), and batch size set to 128.<br> The number of epochs for model training was determined from the dataset size.<br> For final models (trained almost on the whole dataset) we used 270 epochs. <br> In each epoch, 1791 batches were processed (we kept this number due to historical reasons), elements of each batch were sampled from dataset with the weight = 0.5 * torch.clamp_min(torch.log(sn + 1.01),0.01)</p> <p>We have also found that training model with a simple SGD optimizer for ~15 epochs of 500 batches each additionally improves model performance (the number of epochs varies so we used a small validation set to determine the exact number of epochs)</p> <p>Additionally, one model was trained to predict 2A3 given DMS, RNA sequence and BPPM (dms-to-2a3 model).</p> <h1>Inference</h1> <p>At the inference phase for all inputs we set the SN filter value to be 1 as if they come from a “clean” dataset.</p> <h1>Ensembling</h1> <p>We ensembled 15 models with SE-Convolutional block, 10 models with plain Convolutional block, 2 with plain Convolutional block trained on split by sequence lengths (one of these two models accepts bracket features). We took the average of their predictions. Then we predicted 2a3 reactivities based on averaged dms reactivities using dms-to-2a3 model and added these predictions to averaged 2a3 reactivities in the following way: (27/28)<em>averaged_2a3 + (1/28)</em>predicted_2a3.</p> <h1>Other splits</h1> <p>The clear problem with a simple KFold split is the high sequence similarity across the training dataset and the fact that test sequences are very distinct from the training data. This might hamper the model development, because the increase in quality on the validation set could be due to overfitting rather than actual improvement.</p> <p>We have calculated a hamming distance matrix for all the sequences present in the training set and performed a modified DBSCAN clustering procedure with distance threshold set at 0.2. In the following picture we show the clusters mapped to their respective cluster identifier (a cluster ID was assigned as a number of the smallest sequence within that cluster in the train dataset).</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16725112%2F55dc21823386d878fb212d681cae593e%2Fcluster.jpg?generation=1701994798203967&alt=media" alt=""></p> <p>We tested several splits based on sequence identity (the easiest one is just to split data into folds without shuffling) and found out that while the model final validation performance degrades as we choose more and more stricter distance threshold, its relative value behave the same way as for a simple KFold split. So, we decided to use simple KFold split than training final models </p> <p>Also, we have conducted a test of the model performance on length-based split. For that, we trained a model on the short sequences (length < 206) and validated it on sequences of size = 206. The behavior of the validation metric was slightly noisier but still highly correlated with a metric for a simple KFold split.</p> <h1>Public data leakage</h1> <p>Approximately 13% of public test sequences are identical to the ones present in the train dataset (by sequence). To avoid selecting a model that is memorizing more of these sequences rather than learning RNA-related stuff, we zeroed out the predictions for these sequences in most of our submissions, while sometimes sending non-zeroed out submissions in order to compare our performance to other participants.</p> <h1>Features we also tried</h1> <h2>capR</h2> <p>We don’t have conclusive results for that feature. It seems like it is not beneficial for the model on average but sometimes it resulted in a better model and sometimes – in worse. We decided to not use this feature.</p> <h2>Brackets</h2> <p>We have tried to use brackets generated by EternaFold, ContraFold, ViennaRNA, etc., as well as programs for pseudoknots prediction (like IPknot). However, after adding EternaFold BPPMs to the model, adding other features yields no significant increase in model performance. For some models we used brackets just to augment model</p> <h2>Different BPPMs</h2> <p>All other BPPMs (ContraFold, ViennaRNA, RNAsoft, RNAstructure) result in a suboptimal model.<br> Averaging BPPMs doesn’t result in better performance.<br> BPPMs from RFold yield the same quality as ViennaRNA BPPMs.<br> The RNA-FM model produces both per-nucleotide embeddings and BPPM-like matrix. Still, those don’t help the model at all, and using them results only in a slight increase in model performance then compared to sequence only model</p> <h2>SQUARNA matrix</h2> <p>SQUARNA (<a href="https://github.com/febos/SQUARNA" target="_blank">github</a>) outputs a matrix different from BPPM, but can be used in the same manner. Unfortunately, this feature also didn’t yield any additional performance increase.</p> <h1>What we also tried</h1> <h2>Fully-Convolutional architecture</h2> <p>The initial reason we decided to take part in the competition was to test our model LegNet <a href="https://academic.oup.com/bioinformatics/article/39/8/btad457/7230784" target="_blank">link</a>, which shows SOTA results on DNA sequences and worked well on some RNA-related tasks (not yet published).<br> Unfortunately, any modifications of this architecture resulted in subpar performance when compared with properly tuned transformer models. This can be explained by the fact that predicting RNA secondary structure requires attending to long-range contacts. The transformer architecture suits better for such cases.</p> <h2>Subsetting data</h2> <p>Subsetting data (filtering by different thresholds on SN ratio) resulted in a performance boost for all models. However, this technique was superseded by weight sampling, which proved itself to be more effective.</p> <h2>Fine-tuning on public datasets</h2> <p>We tried to fine-tune our model on a public dataset, gathered by the organizers (<a href="https://www.kaggle.com/datasets/rhijudas/rmdb-rna-mapping-database-2023-data/data" target="_blank">link</a>) by training model to predict the results of the public experiments (excluding ones with a small number of samples) and for Ribonanza data simultaneously. Unfortunately, this also gave no boost to the model performance.</p> <h2>Using 3D data</h2> <p>We tried to use data about predicted 3D structure of 100k sequences from the train dataset but gave up on that once we had visually analyzed them:</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16725112%2F2d054d1679176e0664130f6c46ccb0ae%2Ftrashfold.jpg?generation=1701994817511350&alt=media" alt=""></p> <h2>Absolute positional embedding</h2> <p>Using absolute positional embedding leads to unsolvable issues when generalizing upon longer sequences.</p> <h2>Relative positional embedding</h2> <p>The simplest approach is to augment absolute positional encoding during the training phase to shift randomly from 0 to (Lmax - seqlen) position. This indeed solves the issue with extrapolation, but works worse than other methods.<br> Rotational positional embedding, unfortunately, doesn’t help the model to generalize on larger lengths.<br> ALiBi positional embedding solves the issue with extrapolation but even after keeping it only for a part of heads (as suggested in <a href="https://github.com/lucidrains/x-transformers" target="_blank">https://github.com/lucidrains/x-transformers</a>) still behaves worse than dynamic positional bias.</p> <h2>Augmentation</h2> <p>First, we tried to use reverse augmentation. This can be done in three ways:<br> reversing sequence before any modifications,<br> reversing sequence before padding, but after adding and tokens,<br> reversing sequence after padding.</p> <p>The first two ways yield no gain for all variants of models we tested. Yet, the third one (upon coupling with additional finetuning) gave us a good result for a model with xpos positional encoding. The resulting single-model performance was 0.13937 on the public leaderboard. Unfortunately, xpos shows rather poor performance on long sequences so we abstained from using this model in the final submission.</p> <p>We have also tried shift augmentation and different sequence padding approaches. This didn’t improve our model performance as well.</p> <h2>Sliding window</h2> <p>One of the possible ways to generalize for larger sequences is to predict reactivities using the sliding window. However, the idea is somewhat wrong in a biological sense, and it results in performance degradation when testing on train dataset sequences.</p> <h2>Pseudolabelling</h2> <p>Once we obtained ensembles of best-performing models we tried to use them to pseudolabel test dataset and use predictions with the highest confidence to train new models. While this indeed results in a better single-performing model, adding such a model to ensemble doesn’t improve ensemble performance.</p> <h2>Changing loss</h2> <p>Instead of filtering sequences with low SN we tried to mask positions with high reactivity error as it was done by <a href="https://www.kaggle.com/nullrecurrent" target="_blank">@nullrecurrent</a> in Open Vaccine challenge (<a href="https://www.kaggle.com/competitions/stanford-covid-vaccine/discussion/189620" target="_blank">link</a>)<br> This resulted in poor performance.<br> We tried to weight loss for each sequence by its SN – it didn’t result in any improvement</p> <h1>Tools</h1> <p><a href="https://github.com/DasLab/arnie/tree/master" target="_blank">arnie</a><br> <a href="https://github.com/eternagame/eternafold" target="_blank">EternaFold</a></p> <h1>Links</h1> <h2>Squeeze-and-excitation block</h2> <p>Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7132-7141).</p> <h2>Dynamic positional bias</h2> <p>Wang, W., Chen, W., Qiu, Q., Chen, L., Wu, B., Lin, B., … & Liu, W. (2023). Crossformer++: A versatile vision transformer hinging on cross-scale attention. arXiv preprint arXiv:2303.06908.</p>
Open Problems – Single-Cell Perturbations	#30: "Melting" the Data	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>Thank you to the organizers of the Open Problems – Single-Cell Perturbations competition for this incredible opportunity. </p> <p>My approach combines four model types: Tabular Models with embeddings and dense layers, fine-tuned Transformer Models, Random Forests, and XGBoosted Forests, all trained on a "melted" format of the training data. </p> <p>In the following sections, I provide a comprehensive breakdown of my approach and the specific models employed. Links to models and other resources are provided throughout the text and can also be found in Section 6.</p> <p></p> <h2>1. Integration of biological knowledge</h2> <p>My initial approach involved training Tabular Neural Networks and Transformers specifically on the categorical features available in the training data. These models excel in encoding complex relationships within their embedding layers. Concurrently, I planned to augment the training data with information sourced from biological databases and web searches, and I intended to incorporate calculated molecular descriptors derived from SMILES. This enriched dataset would then be used to train tree-based models.</p> <h3>Molecular Descriptors</h3> <p>I calculated 1600+ molecular descriptors using the <a href="https://jcheminf.biomedcentral.com/articles/10.1186/s13321-018-0258-y" target="_blank">mordred</a> python library and trained a random forest using all molecular descriptors in order to select the most important features (importance > 0.5 %) based on the feature importance results of the training run, which yielded a set of 23 molecular descriptors. All molecular descriptors as well as the list of most important descriptors can be found in the <a href="https://www.kaggle.com/datasets/frenio/op2-scp-additional-cell-gene-and-mol-features" target="_blank">OP2 Additional Features Dataset</a> in the files <code>mol_descriptors.parquet</code> and <code>important_mol_descriptors.csv</code>, respectively.</p> <pre><code> rdkit, rdkit.Chem mordred, mordred.descriptors calc = mordred.Calculator(mordred.descriptors, ignore_3D=) molecules = [rdkit.Chem.MolFromSmiles(smi) smi compounds[]] features = calc.pandas(molecules) </code></pre> <p>Here <code>compounds['SMILES']</code> contained a list of unique SMILES strings from the training data.</p> <h3>Gene Information</h3> <p>Gene information was obtained from the ENSEMBL database through the <a href="https://jrderuiter.github.io/pybiomart/index.html" target="_blank">pybiomart</a> python package. Note that gene info could only be obtained for 13,423 of the 18,211 genes in this way.</p> <pre><code> pybiomart Server server = Server(host=) dataset = server[][] results = dataset.query(attributes=[, , , , ], filters={: id_filter, : }) </code></pre> <p>From there I added additional features. For example, the number of each nucleobase (ACGT) obtained from the sequence data seemed particularly useful, according to feature importance results evaluated after training of Random Forests. A data frame containing added gene info can be found in the <a href="https://www.kaggle.com/datasets/frenio/op2-scp-additional-cell-gene-and-mol-features" target="_blank">OP2 Additional Features Dataset</a> as <code>geneinfo.parquet</code>.</p> <h3>Cell Features</h3> <p>Finding useful features that distinguish the 6 different cell types in the training data was a challenge for me. I ended up browsing Wikipedia, PubMed, and the <a href="https://www.immunology.org/public-information/bitesized-immunology/cells" target="_blank">website</a> of the British Society for Immunology for information that I could add as cell features. The resulting data frame can be found in the <a href="https://www.kaggle.com/datasets/frenio/op2-scp-additional-cell-gene-and-mol-features" target="_blank">OP2 Additional Features Dataset</a> as <code>cellinfo.csv</code>.</p> <h3>Result of Direct Integration of Biological Knowledge</h3> <p>The best result that I was able to obtain using a tree-based model after adding the features described above was a Random Forest that achieved scores of 0.628 and 0.836 on the public and private leaderboards, respectively. For comparison, my best Random Forest trained on embeddings learned by a Tabular Neural Network (TabMod NN) achieved scores of 0.588 and 0.780.</p> <h3>Embeddings</h3> <p>Due to the inadequacy of direct integration of molecular descriptors, gene, and cell information, I decided to train Random and XGBoosted Forests on embeddings learned by the TabMod Neural Network. The use of embeddings significantly improved my results and might reasonably be considered an indirect form of "integration of biological knowledge," because neural networks like TabMod NN are able to uncover and encode complex, often non-linear relationships inherent in biological systems into these embedding vectors. The embeddings obtained from TabMod NN can be found in the <a href="https://www.kaggle.com/datasets/frenio/op2-single-cell-perturbations-tabmodnn-embeddings" target="_blank">OP2 TabMod NN Embeddings Dataset</a>.</p> <p>Plots of the <code>cell_type</code>, <code>sm_name</code>, and <code>gene</code> embeddings after PCA using 2 components as well as the corresponding code can be found in the <a href="https://www.kaggle.com/code/frenio/30-op2scp-look-at-tabmod-nn-embeddings" target="_blank">Look at Embeddings Notebook</a>. The plot of the <code>gene</code> embeddings shows two large distinct clusters – one very dense, the other less dense. The red marks with labels show a random selection of gene names to be displayed.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F15827820%2Fa3a4ee89d9b9f0bc7d51f7c55e6faad6%2Fgene_embeds.png?generation=1702353451391406&alt=media" alt="Gene Embeddings"></p> <h2>2. Exploration of the problem</h2> <p>At first glance, the training data seemed like a collaborative filtering problem, where cell types are the users, drugs are the items, and gene expression confidence values are the targets. However, thinking about it that way leads to 18211 collaborative filtering problems – one for every gene – and I was intimidated by the idea of training 18211 models to come up with a single submission. Then I realized that collaborative filtering is just a special case of a tabular modeling problem with two features and one target, which led to the idea to "melt" the training data and the test data (convert from wide to long format):</p> <pre><code>train_df = df_de_train.melt(id_vars=[, ], value_vars=df_de_train.iloc[:,:].columns, var_name=, value_name=) </code></pre> <p>Melting of the training data results in a data frame with 11,181,554 rows (11,181,554/614 = 18,211), three features (<code>cell_type</code>, <code>sm_name</code> and <code>gene</code>), and one target (signed -log(p-value) called <code>value</code>). I used this data format for all my models, which then had to predict only one target for each <code>cell_type</code>/<code>sm_name</code>/<code>gene</code> combination. Inference using a model trained on data in that format yielded a list of 4,643,805 prediction values, which I just reshaped back into the submission format of 255 x 18,211 (see e.g. my <a href="https://www.kaggle.com/code/frenio/30-op2scp-random-forest-with-tabmod-embeds" target="_blank">Random Forest Notebook</a>).</p> <h2>3. Model design</h2> <p>For final submission, I used an ensemble of 4 different model types: Tabular Model Neural Networks, fine-tuned Transformer Models, Random Forests, and XGBoosted Forests. These are described in more detail below. The ensemble that achieved the placement in position 30 of the private leader board (with scores of 0.553 and 0.753 in the public and private leaderboards, respectively) had the following structure:</p> <p>5 TabMod NNs using 600 dimensions for gene embeddings and random seeds 42, 55, 120, 457, and 736 and 5 TabMod NNs using 1000 dimensions for gene embeddings and random seeds 42, 199, 550, 855, and 970:</p> <pre><code>df1 = df1_1* + df1_2* + df1_3* + df1_4* + df1_5* + df1_6* + df1_7* + df1_8* + df1_9* + df1_10* </code></pre> <p>5 Random Forests using random seeds 209, 569, 739, 885, and 926:</p> <pre><code>df2 = df2_1* + df2_2* + df2_3* + df2_4* + df2_5* </code></pre> <p>5 XGBoosted Forests using random seeds 117, 150, 234, 624, and 804:</p> <pre><code>df3 = df3_1* + df3_2* + df3_3* + df3_4* + df3_5* </code></pre> <p>5 fine-tuned Transformer Models, TinyBioBert and DeBERTa-v3-small (see details below):</p> <pre><code>df4 = df4_1* + df4_2* + df4_3* + df4_4* + df4_5* </code></pre> <p>The weights used for the final submission were:</p> <pre><code>submission = df1* + df2* + df3* + df4* </code></pre> <p>The following figure shows a correlation heat map of the predictions of the different model types (see the <a href="https://www.kaggle.com/code/frenio/30-op2scp-correlation-of-predictions" target="_blank">Prediction Correlation Notebook</a> for the source code):</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F15827820%2F261951234c01103ce2cb74c09c7dad41%2Fprediction_correlation.png?generation=1702353628253144&alt=media" alt="Prediction Correlation"></p> <p>In the subsequent sections I present detailed descriptions of each model type, along with links to the relevant Kaggle notebooks. These notebooks are designed to run on Kaggle. However, the fine-tuning of transformer models, utilizing the full training data, was conducted on SaturnCloud. To adapt these notebooks for Kaggle, the training data was substantially reduced. As a result, the transformer models showcased on Kaggle are for demonstrative purposes only and do not achieve scores indicative of their full potential in the competition.</p> <h3>TabMod NN</h3> <p>TabMod NN performance was best when the training data was denoised using PCA and 10 components prior to training (see the <a href="https://www.kaggle.com/code/frenio/30-op2scp-tabular-model-nn-with-pca10-denoising" target="_blank">TabMod NN Notebook</a> for details and code). The two kinds of tabular neural networks used for final submission were identical except for the dimensionality (600 and 1000) of gene embeddings used. The models were based on fast.ai’s <code>tabular_learner</code> with the following configuration:</p> <pre><code>learn = tabular_learner(dls, y_range=(y_min, y_max), emb_szs=emb_szs, layers=[, , ], n_out=, loss_func=F.mse_loss) </code></pre> <p>To achieve a gene embedding size of 1000 instead of the default 389, the <code>emb_szs</code> dictionary was customized.</p> <pre><code>emb_szs = {: , : , : } </code></pre> <p>The range of the final sigmoid layer was set to <code>y_min</code> to <code>y_max</code> which were obtained by determining the minimum and maximum target values in the training data after PCA denoising. The three dense layers of size 1000, 500, and 250 were optimized for appropriate expressivity. Finally, the mean squared loss function was chosen to best reflect the evaluation in the leaderboard. Experiments using mean absolute error, huber loss, and log-cosh did not lead to improvements of the model and instead reduced model performance.</p> <h3>Random Forest</h3> <p>Random Forests (see <a href="https://www.kaggle.com/code/frenio/30-op2scp-random-forest-with-tabmod-embeds" target="_blank">Random Forest Notebook</a>) were trained after adding embeddings for <code>cell_type</code>, <code>sm_name</code>, and <code>gene</code> to the training data. These embeddings were obtained from a TabMod NN similar to the one described in the previous section with gene embeddings of dimensionality 1000 but without the use of PCA denoising on the training data (see <a href="https://www.kaggle.com/code/frenio/30-op2scp-export-tabmod-nn-embeddings" target="_blank">Export Embeddings Notebook</a> for the code). Of those the <code>cell_type</code> embeddings of dimensionality 5 were left unchanged, whereas <code>sm_name</code> and <code>gene</code> embeddings (of dimensionality 26 and 1000, respectively) were reduced to 10 components each using PCA.</p> <p>All Random Forest models used in the final submission were identical except for the random seeds used. They were based on scikitlearn’s <code>RandomForestRegressor</code> using 100 trees on 66 % of samples in order to achieve a meaningful out-of-bag error and score. The square root of feature number was used as the maximum number of features per tree which has been <a href="https://scikit-learn.org/stable/auto_examples/ensemble/plot_ensemble_oob.html" target="_blank">shown</a> to be beneficial for the model’s ability to generalize. The minimum number of samples per leaf was set to 5 in order to achieve high expressivity. Such a Random Forest could be trained using the following example code:</p> <pre><code> sklearn.ensemble RandomForestRegressor m = RandomForestRegressor(n_jobs=-, n_estimators=, max_samples=, max_features=, min_samples_leaf=, oob_score=) m.fit(xs, y) </code></pre> <h3>XGBoosted Forest</h3> <p>The same embeddings used to train Random Forests were also used to train XGBoosted Forests using the same dimensionality reductions.</p> <p>The XGBoosted Forests used in the final submission were also identical to each other except for the random seed used. They were trained using the following code (see <a href="https://www.kaggle.com/code/frenio/30-op2scp-xgboosted-forest-with-tabmod-embeds" target="_blank">XGBoosted Forest Notebook</a> for details):</p> <pre><code> xgboost xgb m = xgb.XGBRegressor(device=, n_estimators=, learning_rate=, max_depth=, min_child_weight=, gamma=, subsample=, colsample_bytree=) m.fit(xs, y) </code></pre> <p>The model parameters were optimized using the cross validation scheme proposed by <a href="https://www.kaggle.com/code/ambrosm/scp-quickstart?scriptVersionId=144293041&cellId=8" target="_blank">AmbrosM</a>, where all but 10 % of the data of one of four cell types is used as a validation set. It should be noted that the performance of the model could potentially be enhanced by configuring the <code>max_depth</code> parameter to values exceeding 20. This approach was not extensively explored due to the higher computational costs associated with larger values.</p> <h3>Transformer Models</h3> <p>Two kinds of Transformer models from the <a href="https://huggingface.co/docs/transformers/index" target="_blank">Huggingface Transformers</a> data base were fine-tuned to output a number when given a standardized input sentence. The general model configuration is shown in the following code snippet:</p> <pre><code> transformers TrainingArguments, Trainer args = TrainingArguments(, save_steps=steps, learning_rate=, warmup_ratio=, lr_scheduler_type=, fp16=, evaluation_strategy=, per_device_train_batch_size=bs, per_device_eval_batch_size=bs*, num_train_epochs=epochs, weight_decay=, report_to=, seed=random_seed) model = AutoModelForSequenceClassification.from_pretrained(model_nm, num_labels=) </code></pre> <p>The argument <code>num_labels=1</code> configures the final linear layer of the model to have a single output neuron which is appropriate for a regression task, as it leads to prediction of a single continuous value.</p> <p>The first model was based on the <a href="https://huggingface.co/microsoft/deberta-v3-small" target="_blank">deberta-v3-small</a> model (<a href="https://openreview.net/forum?id=XPZIaotutsD" target="_blank">link to article</a>) with 44M parameters pre-trained on general text data. The "sparse" input used for the DeBERTa model was:</p> <pre><code>trdf[] = + trdf.cell_type + + trdf.sm_name + + trdf.gene </code></pre> <p>Fine-tuning the DeBERTa for 20-25 epochs on an A10 GPU using an 80/20 train-valid-split and a batch size of 256 took about 48-60 hours (see <a href="https://www.kaggle.com/code/frenio/30-op2scp-transformer-deberta-v3-small-demo" target="_blank">Transformer DeBERTa (Demo) Notebook</a> for a training demo that runs on Kaggle in ~2 hours).</p> <p>The second model was based on the <a href="https://huggingface.co/nlpie/tiny-biobert" target="_blank">tiny-biobert</a> model (<a href="https://doi.org/10.48550/arxiv.2209.03182" target="_blank">link to article</a>) with 15M parameters pre-trained on citations and abstracts of biomedical literature using the PubMed dataset. The "verbose" input used for the TinyBioBert model was:</p> <pre><code>trdf[] = + trdf.gene + + trdf.cell_type + + trdf.sm_name + </code></pre> <p>Fine-tuning the TinyBioBert model for 20-30 epochs on an A10 GPU using an 80/20 train-valid-split and a batch size of 256 took about 24-30 hours (see <a href="https://www.kaggle.com/code/frenio/30-op2scp-transformer-tinybiobert-demo" target="_blank">Transformer TinyBioBert (Demo) Notebook</a> for a training demo that runs on Kaggle in ~1:30 hours).</p> <p>Interestingly, the "sparse" input used for the DeBERTa model did not lead to very good performance in the TinyBioBert model, whereas the more "verbose" input used for the TinyBioBert model led to slower training and worse results in the DeBERTa model. This is reflected in the following submission scores (all trained for 5 epochs using the same random seed of 42):</p> <pre><code> public LB privateLB DeBERTa sparse: DeBERTa verbose: TinyBioBert sparse: TinyBioBert verbose: </code></pre> <p>The transformer part of the final ensemble consisted of four TinyBioBert models. These were trained for 30 epochs using seed 42, 30 epochs using seed 546, 20 epochs using seed 419, and 5x5 epochs using different random seeds. Each model was assigned a weight of 0.15 in the Transformer sub-ensemble. The single DeBERTa model used was trained for a total of 22 epochs using different random seeds, and was assigned a weight of 0.4.</p> <h2>4. Robustness</h2> <p>The robustness of each individual model type was evaluated using triplicate submissions with different random seeds by calculating the mean and standard deviation of the scores achieved on the public and private leaderboard (in the case of transformers, the models also varied slightly in the number of epochs trained). </p> <p>TabMod NN (600): 0.567 ± 0.003 public, 0.777 ± 0.007 private.<br> TabMod NN (1000): 0.562 ± 0.002 public, 0.778 ± 0.003 private</p> <p>Random Forest: 0.592 ± 0.004 public, 0.781 ± 0.002 private.</p> <p>XGBoosted Forest: 0.588 ± 0.002 public, 0.780 ± 0.001 private.</p> <p>Transformer (DeBERTa) 22-25 epochs: 0.606 ± 0.013 public, 0.784 ± 0.007 private.<br> Transformer (TinyBioBert) 25-30 epochs: 0.607 ± 0.003 public, 0.777 ± 0.004 private.</p> <p>These results show that the fine-tuned DeBERTa model is the least robust of the models. The fine-tuned TinyBioBert model consistently performed as well as the TabMod NNs on the private leaderboard, but consistently looked worse on the public leaderboard.</p> <h2>5. Documentation & code style</h2> <p>The code is documented in the notebooks linked throughout the notebook. Additionally, a list of links to all notebooks and datasets can be found in Section 6.</p> <h2>6. Reproducibility</h2> <p>The source code and further documentation for all models as well as additional datasets can be accessed through the following links:</p> <p>Model Notebooks:<br> <a href="https://www.kaggle.com/code/frenio/30-op2scp-tabular-model-nn-with-pca10-denoising" target="_blank">TabMod NN Notebook</a><br> <a href="https://www.kaggle.com/code/frenio/30-op2scp-random-forest-with-tabmod-embeds" target="_blank">Random Forest Notebook</a><br> <a href="https://www.kaggle.com/code/frenio/30-op2scp-xgboosted-forest-with-tabmod-embeds" target="_blank">XGBoosted Forest Notebook</a><br> <a href="https://www.kaggle.com/code/frenio/30-op2scp-transformer-deberta-v3-small-demo" target="_blank">Transformer DeBERTa (Demo) Notebook</a><br> <a href="https://www.kaggle.com/code/frenio/30-op2scp-transformer-tinybiobert-demo" target="_blank">Transformer TinyBioBert (Demo) Notebook</a></p> <p>Other Notebooks:<br> <a href="https://www.kaggle.com/code/frenio/30-op2scp-look-at-tabmod-nn-embeddings" target="_blank">Look at Embeddings Notebook</a><br> <a href="https://www.kaggle.com/code/frenio/30-op2scp-correlation-of-predictions" target="_blank">Prediction Correlation Notebook</a></p> <p>Datasets:<br> <a href="https://www.kaggle.com/datasets/frenio/op2-scp-additional-cell-gene-and-mol-features" target="_blank">OP2 Additional Features Dataset</a><br> <a href="https://www.kaggle.com/datasets/frenio/op2-single-cell-perturbations-tabmodnn-embeddings" target="_blank">OP2 TabMod NN Embeddings Dataset</a></p>
NeurIPS 2023 - Machine Unlearning	Unlearning solution (3th rank)	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: NeurIPS 2023 - Machine Unlearning <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><h1>1. Presentation and general context</h1> <p>Hello! I am Seifeddine Achour an engineering student specializing in mathematical modeling and data science at ENIT, enrolled simultaneously in a Master's program in image processing and living complexity of Paris cité. Also, I am the co-founder of Google's machine learning community MLAct.</p> <p>I conducted many AI researches, some of them were academic, others were professional, but most of them were brought by me based on spontaneous questions that came to my mind, on which I work to find them a solution just out of passion and interest. One of these questions was: What if I have a large model and I want to let it forget some data while keeping almost the same performance on the other data without retraining it from scratch, as it may take much time?<br> I mulled over that for some time until I stumbled upon this competition, which allowed me to focus more on it, and then authored a scientific paper on this topic.</p> <h1>2. Overview</h1> <p>The competition aims to find the model state that maximizes the memory on the wanted data and minimizes it on the unwanted data. In my article, I used a different approach which worked perfectly in the Starting Kit using the CIFAR10 dataset and Resnet18 model as shown in the following figure:</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F9882418%2F0d7473ba58c21828942b871a8bce85cd%2Funlearning.png?generation=1701713408479176&alt=media" alt=""></p> <p>However, in this competition, I encountered some compiling problems that were not understandable of course as I don't have access to the error interface.<br> Therefore, I used a different approach starting from our main problem which is The heavy computation time related to retraining from scratch, which is based on 2 main axes:</p> <ol> <li><p>Instead of running a forgetting algorithm which is time-consuming, initially, the algorithm confuses instantly the model’s vision by changing a bit the state of the convolutional weights while keeping in average the original information and then training it on the retainset.</p></li> <li><p>Due to the classes’ unbalance in this dataset specifically, I introduced a new criterion that gives more importance to the majority class “Class0” to minimize the outlier decisions.</p></li> </ol> <h1>3. Approach details</h1> <p>As mentioned in the previous section, the problem of retraining from scratch is The heavy computation time. The main reason behind this heaviness is related to the slow backpropagation of the model state using gradient descent on all parameters starting from an initial random state. That's why, to surpass this problem the approach consists of retaining on average the global information existing in the original trained model and just confusing a little bit its vision to reconstitute it later properly. This will be achieved by deviating a bit the convolutional parameters' from its actual state while keeping on average the old parameters, then reinforcing the model's knowledge on the desired data through epochs. </p> <p>Let’s understand the maths behind that, we consider, initially, w_1…w_n the weights of the convolutional layers as random variables that follow the Gaussian Law 𝓝(m_i ,𝜎^2) , where mi is the original weight and 𝜎=0.6. After that, we continue the training process on the retaining set for 4 epochs using the SGD algorithm, learning rate 0.0007, momentum 0.9, and the strong convexity component weight_decay=5e-4. Before starting the final training epoch we apply a light variation in the weights to avoid the non-differential minima in the loss landscape then we finalize the last epoch.</p> <p>The second crucial component to consider while unlearning the model is the class imbalance present in the dataset as mentioned in the organizers’ article and shown in the following figure:</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F9882418%2F0d94529afdec56a7b6646b59727bd22c%2FCapture%20dcran%202023-12-03%20151053.png?generation=1701713844326082&alt=media" alt=""><br> [1]</p> <p>To highlight this fact while training, I introduced a customized loss function which is based on the cross entropy principle but additionally, it gives weight = 1 to class 0 and 0.05 to the rest of classes. The loss is represented as follows :</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F9882418%2Fc01d714daff5f65871244be1502348ce%2FCapture%20dcran%202023-12-04%20191925.png?generation=1701714020731331&alt=media" alt=""></p> <h1>4. Results</h1> <p>The scoring system in this competition is based on the degree of similarity between the retrained model and the unlearned model. The highest score that my model obtained using the first 50% of the test set was 0.0968 and the average of all scores of this same algorithm was 0.092. Using the second 50% of the test set, it obtained 0.0885 as a final validation score. </p> <p>It is also important to note that the whole algorithm duration is around 6 hours from the confusing process to the training through 4 epochs.</p> <h1>5. Discussion</h1> <p>In this section, I would like to highlight three aspects:</p> <ol> <li><p>The increase in the number of epochs seems to be unuseful above a certain threshold. Although it may be challenging to confirm it without access to the output interface to make a proper analysis and interpretation of model performance, I assume it is due to an overfitting which happened because of the class unbalance.</p></li> <li><p>Despite the relative fastness of the algorithm that I implemented in the competition and its good score using only the retain set, the use of the forget set can be beneficial as it adds more information to help the model make the right decision. I confirmed that using the approach that I developed theoretically in my article on a regression problem, and used it to conduct experiments on classification problem using the starting kit of this competition.</p></li> <li><p>It sounds logical that the retrained model will have the best forgetting performance on the forget set while keeping the exact same accuracy on the retain set. Otherwise, according to the experiments that I have conducted, If we are satisfied with a lightly low retain accuracy we can get much better results in terms of forgetting performance which can be more beneficial in many applications as we can interpret from the following figure:</p></li> </ol> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F9882418%2F38d519141cfd3a3441c398c99976897c%2FCapture%20dcran%202023-12-03%20185038.png?generation=1701714211392961&alt=media" alt=""></p> <h1>6. References</h1> <p>[1] NeurIPS Machine Unlearning Competition organizers, (August 2023), “Evaluation for the NeurIPS Machine Unlearning Competition”</p> <p>Code link: https: //<a href="http://www.kaggle.com/code/seifachour12/unlearning-solution-4th-rank" target="_blank">www.kaggle.com/code/seifachour12/unlearning-solution-4th-rank</a></p>
Open Problems – Single-Cell Perturbations	16th Place Solution Writeup for the Open Problems – Single-Cell Perturbations (Los Rodriguez)	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>We finally had some time to writeup our strategy for the OP2 challenge. It was a super engaging competition, and we're really thankful to both the organizers and fellow competitors for making it such a blast! The whole experience taught us a ton, and we're happy to share what we did/discover along the way. Can't wait for the next challenge!</p> <h2>Context</h2> <p>In this competition, the main objective was to predict the effect of drug perturbations on peripheral blood mononuclear cells (PBMCs) from several patient samples. For convenience, we have created a Python package with the model here <a href="https://github.com/scapeML/scape" target="_blank">https://github.com/scapeML/scape</a>. </p> <ul> <li>Business context: <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview</a></li> <li>Data context: <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/data" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/data</a></li> </ul> <h2>Overview of the approach</h2> <p>Similar to most problems in biological research via omics data, we encountered a high-dimensional feature space (~18k genes) and a low-dimensional observation space (~614 cell/drug combinations) with a low signal-to-noise ratio, where most of the genes show random fluctuations after perturbation. The main data modality to be predicted consisted of signed and log-transformed P-values from differential expression (DE) analysis. In the DE analysis, pseudo-bulk expression profiles from drug-treated cells were compared against the profiles of cells treated with Dimethyl Sulfoxide (DMSO). In addition, challenge organizers also provided the raw data from the single-cell RNA-Seq experiment and from an accompanying ATAC-Seq experiment, conducted only in basal state.</p> <p>At the beginning of the challenge, we tested different models using the signed log-pvalues (“de_train” data) alone, such as simple linear models, ensembles of gradient boosting with drug and cell features, conditional variational autoencoders, etc. We soon realized that a simple Neural Network using only a small subset of genes to compute drug and cell features (median of the genes grouped by drug and cell) was enough to have a competitive model.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F311361%2F72933c3ebc89980311c9824a42bffde2%2Fnn-architecture.png?generation=1702418417955250&alt=media" alt=""></p> <p>The figure above shows the final architecture used for our submission. We used a Neural Network that takes as inputs drug and cell features and produces signed log-pvalues. Features were computed as the median of the signed log-pvalues grouped by drugs and cells, calculated from the de_train.parquet file. Additionally, we also estimated log fold-changes (LFCs) from pseudobulk expression, to produce a matrix of the same shape as the de_train data but containing LFCs instead. We also computed the median per cell/drug as features.</p> <p>Similar to a Conditional Variational Autoencoder (CVAE), we used cell features both in the encoding part and the decoding part of the NN. Initially, the model consisted of a CVAE that was trained using the cell features as the conditional features to learn an encoding/decoding function conditioned on the particular cell type. However, after testing different ways to train the CVAE (similar to a beta-VAE with different annealing strategies for the KL term), we finally considered a non probabilistic NN since we did not find any practical advantage in this case with respect to a simpler non-probabilistic NN. </p> <h3>Neural Net</h3> <p>We created a method to parametrize the architecture of the NN and the feature extraction from different data sources. This is the code needed to create the NN through the scAPE library specifically created for this challenge: <a href="https://github.com/scapeML/scape/blob/222b19f47a32afb8d157aecd5e46b23d90b73e9d/scape/_model.py#L678" target="_blank">https://github.com/scapeML/scape/blob/222b19f47a32afb8d157aecd5e46b23d90b73e9d/scape/_model.py#L678</a></p> <p>We used <code>n_genes=64</code> (top 64 genes sorted by variance across conditions).This generates a NN with 9637475 parameters (36.76 MB). The inputs are computed from de_train and from log-fold changes calculated from pseudobulk. Cell features are duplicated both in the encoder and decoder. We did some permutations to estimate the distribution of CV errors, permuting drug and cell features, also in the encoder and decoder part. Drug features have more impact on the final error (something to expect since there are 146 datapoints per cell type + B/Myeloid drugs). For the cell features, in general we observed that when used through the encoder and decoder, the NN places more importance in the cell features on the decoder rather than the encoder. This might suggest that cell features are more important for performing a conditional decoding of the drug features which is cell-type specific.</p> <h3>Model selection</h3> <p>Using the previous NN, we did a leave-one-drug-out for NK cells, which resulted in 146 models. We used the median of the predictions from the 146 models on the cell/drugs for the submission to generate what we call <em>base predictions</em>.</p> <p>The idea of using this strategy is motivated by the fact that NK cells are the most similar ones to B/Myeloid cells. The other advantage of adopting a leave-one-drug-out approach for NK-cells is that it allows us to estimate how well the model generalizes to unseen drugs, on a per-drug basis per cell type. We also observed that in general, the median was much better than the mean for aggregating the results of the 146 models, since it is more robust to outliers (some models did not generalize well on some drugs, and early stopping selected bad models in those situations).</p> <p>We also trained a second neural network with the same hyperparameters, but this time using only the top 256 most variable genes and focusing on the 60 most variable drugs. In this second set of predictions, instead of predicting the 18211 genes, the NN predicts only the top 256 genes used as inputs. We did this because we realized the NN was learning to decide if there was an effect on a given cell type from a small set of genes (essentially, determining where to place values close to 0 in the matrix). We reasoned that training again on only a subset of the data, where most of the changes were concentrated, would help increase performance for that subset of genes. We generated 60 models and computed the median of the predictions, which we referred to as <strong>enhanced predictions</strong>.</p> <p>We finally replaced the base predictions with the enhanced predictions (on the subset of genes/drugs). For the final submission, to be more conservative, we mixed the predictions in 0.80/0.20 proportions (0.80 given to the enhanced predictions). <strong>We tested this strategy with several different base predictions, and it always resulted in a boost of performance, which was also the case on the private leaderboard.</strong> A reproducible notebook for the submission is available at: <a href="https://github.com/scapeML/scape/blob/main/docs/notebooks/solution.ipynb" target="_blank">https://github.com/scapeML/scape/blob/main/docs/notebooks/solution.ipynb</a>.</p> <p>One limitation of this strategy is that most of the trained models are very similar, and the blending with the median is very conservative. We also tested different CV strategies, and we found that using blendings of models trained on a 4-CV setting with handpicked drugs on both B/Myeloid cells provided better results in the private leaderboard. However, we didn't trust this strategy that much since it was not very stable and it was hard to understand how well those models were performing in particular cell/drugs combinations.</p> <h3>Baselines</h3> <p>We think that having simple baselines is important to understand 1) if the model works, and 2) how good it is. </p> <p>We decide to use two simple baselines: predicting zeros (as the baseline used in the competition, which achieves a 0.666 error in the public LB), and the median of the genes grouped by drugs (computed on the training data). The second baseline is more informative.</p> <p>We combined those baselines with our leave-on-drug-out strategy to produce plots per drug, so we could have an upper bound estimation of the generalization for each drug. Here is an example for NK and Prednisolone:</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F311361%2Fba8aa85e97594aed0ab09f324528e0fa%2Fexample-nk-prednisolone.png?generation=1702418460653383&alt=media" alt=""></p> <h2>Specific questions</h2> <h3>1. Use of prior knowledge</h3> <p>We decided against using LINCS data in our model because it primarily focuses on cancer cell data, which tends to have a molecular state quite distinct from the PBMCs we were investigating. Despite our exploration of published work and datasets related to predicting drug-induced changes in single-cell states, none of them encompassed the vast array of drug perturbations examined in the challenge. Additionally, we chose not to integrate external data into our approach due to concerns about handling batch effects caused by differences in laboratory settings, protocols, and other related factors.</p> <p>We've also tried to use ATAC-seq with no success. We believe that this data would be useful in the case of not having any measurement for B/Myeloid. However, more informative than ATAC-seq are the actual perturbational profiles on the small subset of drugs on those cells.</p> <p>Here is a summary of different features we tested:</p> <ol> <li>Dummy binary variables for cell types and drugs.</li> <li>Basal omics features, including average expression in DMSO and average accessibility per the ATAC-Seq data.</li> <li>Summary statistics of the drug response after grouping by cell type and drug, including standard deviation, mean and median.</li> <li>A “raw” fold-change computed over the raw counts of the single-cell RNA-Seq data (this is, without the corrections applied by limma).</li> <li>Centroids of the principal component space of the drug response data, using cell-type and drug as grouping variables.</li> </ol> <p>And we obtained the best results using the median of the response after grouping by cell type and drug in combination with the raw fold changes, using only a subset with the most variable genes in the dataset.</p> <h3>2. Exploration of the problem</h3> <p>We found that the error distribution for the drugs was more or less even except for the first four drugs, which accounted for 15% of the total error. As expected, we also found out that the response of drugs that were harder to predict was very different from training cell-types in comparison to the test cell-type. For instance, the drug that accounted for the maximum proportion of the error (IN1451), produced a strong response in NK cells, but seemed to have little effect in T cells CD4+, T cells CD8+ and T regulatory cells.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F311361%2Fec079268e6ac589644cf28ae1921517f%2Ffig6.png?generation=1702418626577518&alt=media" alt=""></p> <p>Our approach was refined to better understand cell-type errors, aiming to identify the most challenging cell type for accurate prediction. We evaluated 15 drugs across all cell types, selecting 4 at random for testing. This test set was used for cell-type cross-validation, where the model was trained on data from all 15 drugs, excluding the 4 test drugs within a specific cell type. Our method facilitated evaluation of predictive performance for each cell type. Our findings, illustrated in the figure below, indicated that myeloid cells were more difficult to predict than others, corroborating RNA-Seq PCA analysis results.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F311361%2F86646a0d4e453e58e2856a74b029b11d%2Ffig7.png?generation=1702418748195660&alt=media" alt=""></p> <p>Regarding genes, we investigated if specific biological functions were harder to predict. An enrichment analysis of the top 5% genes with the highest average error in our local CV setup was conducted using MSigDB hallmarks and <a href="https://www.kaggle.com/code/pablormier/op2-biologically-aware-dimensionality-reduction" target="_blank">decoupleR</a>. This revealed that certain hallmarks, such as epithelial mesenchymal transition and TNF alpha signaling, had a significant number of genes with high error rates:</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F311361%2Fcc674087faeccb96578b85de39123a7a%2Ffig8.png?generation=1702418832195389&alt=media" alt=""></p> <h3>3. Model design</h3> <p>We wanted to check if simpler models could perform just as well. So, we cut down the input features in our models. Considering that our architecture was simple already, we aimed to find the fewest input features that could match the local CV performance of using the top 128 genes with the highest variance.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F311361%2Ff29dbc0d67029908ca8bcf86be308426%2Ffig9.png?generation=1702418909501736&alt=media" alt=""></p> <p>Interestingly, we found that models with 8 to 64 input features would achieve similar performance that the model that employed 128 features.</p> <p>Regarding explainability, even though the model is not easily interpretable, we put some extra care in understanding better how the NN behaved through the leave-on-drug-out + baselines, and by doing permutations on the input data after training a model, to asses the impact on the validation loss.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F311361%2F309451c68977bac8fa6e310a788103df%2Ffig10.png?generation=1702418986950956&alt=media" alt=""></p> <p>We observed that while both components had a direct impact on the performance of our model, the mean of the errors after drug features permutation was higher compared to the average error after cell features permutation. This is something to expect, as we have more data points of gene values per drug (146 data points per cell type except B/Myeloid), but we only have 6 data points grouping by cell type. We used this type of permutation tests to estimate the importance that different features had in the CV error.</p> <h3>4. Robustness</h3> <p>Our model included a Gaussian Noise layer from Keras to perturb the input data. We used this to test CV errors for different noise levels. The following figure shows that a gaussian noise of std=0.01 w. This is the value we selected for training the final models:</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F311361%2F21ba9f226003e9246391f7181ba834bb%2Ffig11.png?generation=1702419081567894&alt=media" alt=""></p> <h3>5. Documentation & code style</h3> <p>For convenience, we refactored the code and created a package called “scape” (<a href="https://github.com/scapeML/scape" target="_blank">https://github.com/scapeML/scape</a>) using <a href="https://pdm-project.org/" target="_blank">https://pdm-project.org/</a>, which contains the code that we finally used for the submission. The code is documented using numpydoc docstrings, and we included a series of notebooks using the scape package to learn how to use it and how to manually create the setup for generating our submission. We have put effort into developing a library that allows for the comfortable configuration and parameterization of neural networks, with an automatic mode for calculating diverse features from drugs and cell lines.</p> <h3>6. Reproducibility</h3> <p>In order to improve reproducibility, we show how the tool package can be installed and used directly from Google Colab <a href="https://colab.research.google.com/drive/1-o_lT-ttoKS-nbozj2RQusGoi-vm0-XL?usp=sharing" target="_blank">https://colab.research.google.com/drive/1-o_lT-ttoKS-nbozj2RQusGoi-vm0-XL?usp=sharing</a>. </p> <p>We also included an environment.yml file to exactly recreate the environment we used for testing using conda.</p> <h2>Sources</h2> <ul> <li><a href="https://github.com/scapeML/scape" target="_blank">https://github.com/scapeML/scape</a></li> <li><a href="https://academic.oup.com/bioinformaticsadvances/article/2/1/vbac016/6544613?login=false" target="_blank">https://academic.oup.com/bioinformaticsadvances/article/2/1/vbac016/6544613?login=false</a></li> <li><a href="https://www.kaggle.com/code/pablormier/op2-biologically-aware-dimensionality-reduction" target="_blank">https://www.kaggle.com/code/pablormier/op2-biologically-aware-dimensionality-reduction</a></li> </ul>
Child Mind Institute - Detect Sleep States	10th Place Solution	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Child Mind Institute - Detect Sleep States <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>First and foremost, I would like to express my gratitude to all participants and organizers.<br> It was a very tough competition as I did not have many good scores on public LB, but I was satisfied with the final results.</p> <h2>Features engineering</h2> <ul> <li>enmo<ul> <li>Utilized as is</li></ul></li> <li>anglez<ul> <li>Used <code>anglez.diff().abs()</code></li></ul></li> <li>Time Encoding<ul> <li>Normalized the hours into t=[0~1) and employed <code>sin(2pit)</code> and <code>cos(2pit)</code> as features</li> <li>Experimented with finer periodicities (e.g., <code>sin(4pit)</code>, <code>sin(8pit)</code>, <code>cos(4pit)</code>, <code>cos(8pit)</code>), but performance worsened</li> <li>Considered features like week and month, but they were rejected due to performance degradation.</li></ul></li> <li>Duplicate Data<ul> <li>Identified instances of identical sensor data occurring in the same series at the same time.</li> <li>Assigned a flag of 1 for times with duplicates and 0 for times without duplicates</li></ul></li> <li>Step<ul> <li>Flags set for within 1 hour and within 8 hours from the start of measurement</li> <li>Because, included data points where onset occurred within 1 hour or wakeup within 8 hours since there were none</li></ul></li> </ul> <h2>Model</h2> <p>Adopted a 1D-UNet GRU model as illustrated. Features, excluding enmo and anglez, are added just before the GRU. Trained using Binary Cross Entropy.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1630583%2F5e93b7c1e25dd2fbcc18d346c320ec93%2Fmodel.png?generation=1701906351601543&alt=media" alt=""></p> <h2>Target Design</h2> <p>Utilized a heatmap based on a Gaussian distribution. For stability in training and improved AP at a large tolerance, a Gaussian distribution with a large sigma was advantageous. Contrastly, a Gaussian distribution with a small sigma led to instability in training but improved AP at a small tolerance. As a compromise, a weighted sum of Gaussian distributions with large and small sigmas was used.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1630583%2Ff2d28c6cc637e3f55d3ca2383a845d25%2Ftarget.png?generation=1701906225296881&alt=media" alt=""></p> <pre><code>gauss_small_sigma_minute = gauss_large_sigma_size = gauss_mix_ratio = gauss_small_sigma_size = minute2step(gauss_small_sigma_minute) gauss_large_sigma_size = minute2step(gauss_large_sigma_minute) gauss_large = np.exp(-((x - gauss_center)*) / ( (gauss_large_sigma_size))) gauss_small = np.exp(-((x - gauss_center)) / ( * (gauss_small_sigma_size)*)) gauss = (gauss_large + gauss_mix_ratio gauss_small) gauss /= gauss.() </code></pre> <p>`</p> <h2>Training</h2> <ul> <li>Randomly sample 12 hours</li> <li>150 epoch, AdamW</li> <li>Apply SWA after 50 epoch</li> </ul> <h2>Inference</h2> <ul> <li>In contrast to training, infer a entire series at a time</li> </ul> <h2>Ensemble</h2> <p>The processing time for the entire test dataset, including data loading, pre-processing, and post-processing, was approximately 18 minutes.<br> Of that time, model inference took 45 seconds.</p> <p>Public LB is calculated by 25% of the test data, so some shake was expected.<br> Therefore, the decision was made to perform ensemble learning with large number of models. The final ensemble consists of 120 models, and the processing is completed within 120 minutes.</p> <h2>Post-processing</h2> <p>It is crucial to detect multiple candidates in one night.</p> <ul> <li>Smooth the output values with a width of 11</li> <li>Detect all local maxima with a threshold of 0.01 and add them as candidate points</li> <li>For all remaining timestamps, perform the following in descending order of output values<ul> <li>If the timestamp is more than 21 minutes away from any previously detected timestamp, add the product of 0.1 and the output value as a candidate point</li></ul></li> </ul>
Open Problems – Single-Cell Perturbations	34th Place Solution Writeup for Open Problems – Single-Cell Perturbations	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>First of all, I would like to express my gratitude to the organizers and kagglers of this competition. I learned a lot from the open notebooks and discussions.<br> Especially, I would like to express my big thanks to the following people.<br> <a href="https://www.kaggle.com/mehrankazeminia" target="_blank">@mehrankazeminia</a><br> <a href="https://www.kaggle.com/somayyehgholami" target="_blank">@somayyehgholami</a><br> <a href="https://www.kaggle.com/alexandervc" target="_blank">@alexandervc</a><br> <a href="https://www.kaggle.com/antoninadolgorukova" target="_blank">@antoninadolgorukova</a><br> <a href="https://www.kaggle.com/kishanvavdara" target="_blank">@kishanvavdara</a><br> <a href="https://www.kaggle.com/pablormier" target="_blank">@pablormier</a></p> <p><strong>34th Solution</strong></p> <p>We blended the results of three tasks to find one result. Being different approaches, blending these models was very effective.</p> <p>The three approaches<br> Task1 : test set as categorical variable<br> Task2 : test set as continuous variable ( genes as sampled)<br> Task3 : test set as continuous variable ( compounds as sample)</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2646279%2Fb2df8d249afa3fa8af194ba5d14f3438%2FOC2_34th.png?generation=1702317451136015&alt=media" alt="34th_solution"></p> <p>Basically, it is a simple solution that blends public notebook's score and sklearn's model. If you combine it with a better performing model (like PY-BOOST), the performance will be even better.</p> <ol> <li>integration of biological knowledge<br> In Task 3, we incorporated the decoupler. A small improvement in public scores was obtained. </li> </ol> <p>2.Exploration of the problem<br> In Task 2 and Task 3, CD8 data were excluded. <a href="https://www.kaggle.com/code/yoshifumimiya/op2-about-positive-control" target="_blank">op2-about-positive-control</a></p> <p>3.Model design<br> I used sklearn's MLP, lightgbm, and Ridge. </p> <p>4.Robustness<br> Robustness is considered to be high, because I sought a single result from three different perspectives. </p> <p>5.Documentation & code style<br> In preparation</p> <p>6.Reproducibility<br> In preparation</p>
NeurIPS 2023 - Machine Unlearning	3rd place solution	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: NeurIPS 2023 - Machine Unlearning <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>First of all, thanks to Kaggle and Google for such an exciting competition. It was a great experience.</p> <h3>Summary</h3> <p>In this work, we developed a gradient-based re-initialization method. We assumed that if the gradients of the weights in the model, specifically in the retain set and forget set, are similar, it becomes challenging to forget information from the forget set during the retraining of the retain set. To address this, we selectively reinitialized weights with similar gradients between the two sets, followed by retraining the model.</p> <h3>Method</h3> <p>The proposed gradient-based re-initialization method for unlearning consists of three main steps:</p> <ol> <li>Gradient collection: Gradient information is collected from the forget set and the retain set. The forget set’s gradient is collected using gradient ascent from cross-entropy loss with the forget set label, while the retain set’s gradient is collected using gradient descent cross-entropy loss with the retain set label. Due to the unequal sample sizes between the retain set and forget set, random sampling was used from the retain set to match the number of samples in the forget set for gradient collection. </li> <li>Weight initialization: Based on the gradient information collected in the first step, a percentage of the convolution filter weights are re-initialized. The weights with the smallest absolute values of gradient information are re-initialized. (Our best result initialized 30% of the weights) The weights are globally unstructured initialized, following the same He initialization (mode="fan_out", nonlinearity="relu") from torchvision Resnet codes.</li> <li>Retraining: The model is retrained with the retain set. The learning rate for the Uninitialized weights uses 1/10 of the base learning rates. This is accomplished by scaling the gradient of the Uninitilaized weight by 1/10. </li> </ol> <h3>learning rate scheduler</h3> <p>The learning rate scheduler is also an important factor. A linear decay learning rate scheduler with a few warmup epochs consistently produces better results than a linear decay learning rate scheduler or a linear increase learning rate scheduler.</p> <h3>Randomness</h3> <p>Randomness is also an important factor. Selecting weights using a subset of the retain set(resulting in a different initialization for each run) results in better performance than using the entire retain set. </p> <h3>Image</h3> <ul> <li>gradient collection<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F3106709%2F9db2c688349380dc6feee88a71eacee9%2F1.PNG?generation=1701663754125244&alt=media" alt=""></li> <li>Weight initialization<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F3106709%2F4bcb6052f572a1edd1f49c34efa5453d%2F2.PNG?generation=1701663777339997&alt=media" alt=""></li> </ul> <h3>Our <a href="https://www.kaggle.com/code/nuod8260/targeted-re-initialization-3rd-on-private-lb" target="_blank">code</a></h3> <p>Affiliation: School of Artificial Intelligence, College of Computer Science, Kookmin University</p> <p>Doun Lee<br> Email: <a href="mailto:Idoun8260@kookmin.ac.kr">Idoun8260@kookmin.ac.kr</a></p> <p>Name: Jinwoo Bae<br> Email: <a href="mailto:bgw4399@kookmin.ac.kr">bgw4399@kookmin.ac.kr</a></p> <p>Name: Jangho Kim (Professor)<br> Email: <a href="mailto:Jangho.kim@kookmin.ac.kr">Jangho.kim@kookmin.ac.kr</a></p>
Open Problems – Single-Cell Perturbations	SCP 21st Solution	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p><strong>Feature Engineering</strong></p> <p>Broadly two different sets of features were used for different models used in the final ensemble:</p> <p>Feature Set 1</p> <ol> <li>Cell type - one-hot encoded</li> <li>SMILES - converted to 2048 bit vectors using RDKit Morgan fingerprints</li> <li>Drug properties: for each SMILE, log P and log of Molar Refractivity, standard scaled</li> <li>Control - whether or not drug is a control (1) or not (0)</li> </ol> <p>Feature Set 2</p> <ol> <li>Same features as in Feature Set 1</li> <li>Average SVD embedding values for drug effects on all cell types AND average SVD embedding values for cell response to various drugs</li> <li>Exclusive of 2), or usage of average SVD embedding values for log fold-change for drug effects on all cell types AND average SVD emedding values for log fold-change for cell response to various drugs (either use 2 or 3)</li> </ol> <p>Note that the number of SVD singular values to keep was chosen according to the Gavish-Donohoe (GD) SVD hard threshold method: <a href="https://arxiv.org/abs/1305.5870" target="_blank">https://arxiv.org/abs/1305.5870</a></p> <p>Target</p> <ol> <li>GD SVD criterion used for singular value cutoff for low dimensional modes to keep</li> <li>SVD applied to target matrix and the singular value cutoff determined according to the Gavish-Donohoe threshold</li> <li>All models were trained against the SVD embedding of the original target, and model predictions were transformed back using the transpose of the V matrix</li> </ol> <p><strong>Model Architectures and Data Upsampling</strong></p> <p><strong>Model 1:</strong> </p> <p>Simple direct regression on SVD embedding targets</p> <ol> <li>8 layers Dense feed-forward neural netwok (5128 neurons per layer), output layer 114 neurons </li> <li>SELU activation each layer except for output layer (no activation, linear regression output)</li> <li>Output is in the SVD embedding space (114 columns)</li> <li>Loss: MAE or Pseudo-huber</li> <li>Epochs: 800</li> <li>Batch size: 16</li> <li>Cosine training schedule with warm restart every 200 epochs (alpha = 0.01, t_mul = 1.0, m_mul = 0.9)</li> <li>Stochastic weight averaging (SWA): SWA start from epoch 2</li> <li>Predictions for 18211 genes:<ol> <li>Let output be the predicted SVD embedding</li> <li>Take predicted SVD embedding and multiply by transpose of V matrix from SVD to get back to original 18211 representation</li> <li>Number of singular values to keep chosen according to Gavish-Donohoe threshold (see above)</li></ol></li> </ol> <p><strong>Model 2:</strong></p> <p>Same architecture as Model 1 however sample weights introduced to loss function.</p> <p>Sample weight scheme:</p> <ol> <li>From training set filter out drug-cell pairs where B cells / myeloid cells were exposed to same compounds</li> <li>From 1), exposure to same set of compounds but observed difference in target ( - log10(p_val) * sign(LFC)) should be attributable to cellular difference</li> <li>For each cell type not B cells / myeloid cells calculate a notion of "distance" from the filtered and observed targets for exposure under same drugs using a distance metric of choice, e.g. Frobenius norm of difference of target matrices</li> <li>For each cell type not B cells / myeloid cells average out this "distance" metric calculated in 3) and then subtract from 1 i.e. distance to B cell or myeloid cell would be 0 s.t. one minus this amount would give each cell type of prediction interest a score of 1, whilst cell types further away gets a lower score</li> <li>Divide each cell type by the minimum score of the 6 cell types as calculated in step 4), and use this number as a weight for each row in training based on cell type used in the experiment</li> <li>Model is trained on this weighted loss inclusive of each row's weight</li> </ol> <p><strong>Model 3:</strong></p> <p>Skip connections architecture:</p> <ol> <li>8 or 9 Dense layers</li> <li>Skip connections:<ol> <li>Input dimension: 2056</li> <li>Concatenate layer: Input concatenated with layer 2 pre-activation output (3072 neurons) leading to 5128 output dimension <br> (3072+2056) before feeding into SELU activation layer</li> <li>Additive skip connections: SELU output of concatenate layer (5128) + pre-activation output of layer 4 (5128), SELU<br> output of layer 4 + pre-activation output of layer 6 (5128), SELU output of layer 6 + pre-activation output of layer 8<br> (5128 / used where network has 9 hidden layers)</li></ol></li> <li>Other details similar to Model 1</li> </ol> <p><strong>Model 4:</strong></p> <p>Model 1 architecture but using training error to identify hard to predict drug-cell pairs for upsampling. Upsampling was done by identifying index of training samples (rows) which were at or below at certain training error threshold and then amplified by making a new copies (integer multiples) of these rows to be concatenated to original training set. </p> <p>The thinking here was that since the problem for predicting interactions for B / myeloid cells is potentially underspecified and to be extrapolated from observed interactions of other cells, the drug-cell pairs that have high row-wise accuracy or low MAE (or other regression metric) are not as important and performance on these rows can be sacrificed for better performance on the rows in training which have low row-wise accuracy or low MAE (or other regression metric). The amplified set was also manually checked for inclusion of the small number of B / myeloid cell observations in training.</p> <p>Broadly three types of this upsampling procedure were used with various models</p> <p><strong>Upsampling procedure 1:</strong> Regression based row-wise metric (MAE) for determining cut-off threshold</p> <ol> <li>Simpler smaller neural network trained for 200 epochs on original training set</li> <li>Row-wise MAE computed for each sample</li> <li>Take median of 614 row-wise MAE metrics</li> <li>Take a positive multiple of this median (e.g. 3x or 15x) to select the base set of training rows to be upsampled</li> <li>Make K times more (e.g. 7x) copies of the training subset in 4) and concatenate to original training set</li> <li>Re-train larger model (could be any model architecture) on this upsampled training set</li> </ol> <p><strong>Upsampling procedure 2:</strong> Sign classification using logistic loss for determining cut-off threshold</p> <p>The thinking behind this approach is that sign may be important to get right as an individual prediction where the magnitude (-log10(p_val)) is correct but where sign is not is very consequential for RWRMSE metric.</p> <ol> <li><p>Same procedure as in prior upsampling procedure, except neural network with regression output is trained against the sign of<br> the log fold-change (i.e. target matrix is composed of +1/-1)</p> <p>Logistic Loss = (1/n) * Sum(i from 1 to n) L(y, t) where<br> L(y, t) = ln(1 + exp(-y * t))</p> <p>With t being in {-1, +1} i.e. the sign of the log fold change</p></li> <li><p>Row-wise accuracy (%) is computed on the training set</p></li> <li><p>Choose a cutoff below which the training rows are to be upsampled. I used arbitrary cutoffs such as 75% or accuracy cutoffs<br> 3 standard deviations below the mean row-wise accuracy</p></li> <li><p>Repeat upsampling procedure as in the previous procedure amplifying this subset an integer number of times and retrain a<br> larger model on this exapnded training set</p></li> </ol> <p><strong>Upsampling procedure 3:</strong> Sign classification but focussed on rows with bad sign classification for small p-values</p> <p>Small p-values (e.g. less than 0.1) leads to large magnitudes when -log10 transformed, so intuition is get sign more correct for these as a bad sign classification flips these magnitudes to other side of real number line. </p> <p>Similar procedure to upsampling procedure, however we calculate accuracy only on subset of genes for each drug-cell pair where p-values are below a chosen threshold. Once these row-wise accuracy figures are computed, the same process as in the prior sign upsampling procedure is used to upsample a subset for retraining.</p> <p><strong>Model 5:</strong></p> <p>Triple regression head model with upsampling procedure and contrastive loss. The idea behind this architecture is to have share layers (e.g. 5 layers) between 3 different regression outputs. A "contrastive" loss (see below) was used to incentivise each regression head to learn a different hypothesis to the other 2 heads. This model architecture was mostly trained with sign upsampling procedure 2 as described in Model 4.</p> <p>Architecture:</p> <ol> <li><p>Shared weight layers: 5 Dense layers</p></li> <li><p>Activation: SELU for shared layers and regression heads, linear activation for regression outputs</p></li> <li><p>3 regression heads: [3072, 2048, 1024] neurons before output layer for training y_train SVD embeddings</p></li> <li><p>Contrastive loss: Sum(head 1 to 3) of regression loss for each head + contrast_weight * average_pairwise_dissimilarity</p> <p>K = n_head choose 2</p> <p>Average_Pairwise_Dissimilarity = 1/K * Sum(i from 1 to K) (Average Row-wise Cosine Similarity + 1.)</p> <p>If two non-zero vectors are exactly opposite, row-wise cosine similarity evaluates to -1. If they are exactly the same, we <br> get +1 and if they are orthogonal we get 0. Adding 1 to the average row-wise cosine similarity ensures the minimization<br> objective goes to 0 (instead of -1).</p> <p>Contrastive loss essentially balances between each regression driving down bias but also learning distinctive hypotheses<br> from the data. The amount of contrast between the heads is controlled by the contrast_weight</p></li> <li><p>Each regression heads' output is multiplied by the transpose of the V matrix from SVD to get back predictions for original<br> 18211 genes. </p></li> <li><p>Some submissions used the best head's predictions as determined by training error. Other predictions ensembled the 3 heads'<br> predictions by equal or training loss derived weights (lower loss -> higher weight)</p></li> </ol> <p><strong>Final Submission</strong></p> <p>The two final submissions were LB RWRMSE weighted ensembles of the 16 best and 80 best submissions.</p> <p>For each submission I took the LB RWRMSE error, cubed them and subtracted from 1. to derive a score. These scores were then normalized against each other for the final weighted addition of the submissions.\</p> <p><strong>Code</strong></p> <p><a href="https://github.com/maxleverage/kaggle-scp" target="_blank">https://github.com/maxleverage/kaggle-scp</a></p>
Open Problems – Single-Cell Perturbations	207th Place Solution for the Open Problems – Single-Cell Perturbations. Late submission 0.576 private LB.	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><h2>1. Introduction</h2> <p>I want to thank Kaggle and everyone involved for hosting such an intriguing competition.</p> <p>Two topics are what I describe.<br> 1.1. late submission<br> 1.2. solution </p> <p>It seems that one of the models is better for one compound but weak for other compound.</p> <p>The question remains: how to choose the right drug model for compound?</p> <p>Considering that cells of various types have different models.</p> <p>Could you please clarify why a model is good for a compound?<br> Why is Vorinostat's '24 place model LS RG' the best model for Myeloid cells, with a private score improvement of +0.003?</p> <p>Initially, it is necessary to cover a larger portion of the error with models. <br> With an error of 0.661 and without knowing which compounds have large errors, it is difficult to say whether the model is suitable for the compound.</p> <h2>2. Context</h2> <p>Business context: <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview</a><br> Data context: <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/data" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/data</a></p> <h2>3. Overview of the approach ( late submission)</h2> <p>I like to discover which model is better for compounds.<br> The result is better if you select one model for each drug and cell type.<br> It's possible that there's a chemical explanation for model selection.</p> <p>We lack the skill to select from all the models available.<br> All models have been added.</p> <table> <thead> <tr> <th>bland</th> <th>Private score</th> </tr> </thead> <tbody> <tr> <td>Weight sum of 10 models</td> <td>0.718</td> </tr> <tr> <td>Select one model for each compound</td> <td>0.657</td> </tr> <tr> <td>Multiply the compound by a constant (between 1.4 and 3.09)</td> <td>0.576</td> </tr> </tbody> </table> <h3>Late submission 0.577:</h3> <table> <thead> <tr> <th>Submition id</th> <th>Model</th> <th>Multiplecator is Post Processing</th> </tr> </thead> <tbody> <tr> <td>0</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>1</td> <td>2nd place result_11 776 575 50% + + 50% train <strong>B cells, Alvocidib</strong></td> <td></td> </tr> <tr> <td>2</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>3</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>4</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>5</td> <td>n9_736_3rd_place_psevdo_submission 736</td> <td></td> </tr> <tr> <td>6</td> <td>m4_775_LS_T4 775</td> <td>1.2</td> </tr> <tr> <td>7</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>8</td> <td>24plase LS RG 834</td> <td></td> </tr> <tr> <td>9</td> <td>24plase LS NK 784</td> <td>1.2</td> </tr> <tr> <td>10</td> <td>4th_Place_Ensembling_submission 746. 564</td> <td>1.2</td> </tr> <tr> <td>11</td> <td>m18_790_submission_calibrated_max_d 790</td> <td></td> </tr> <tr> <td>12</td> <td>m18_790_submission_calibrated_max_d 790</td> <td></td> </tr> <tr> <td>13</td> <td>24plase LS NK 784</td> <td></td> </tr> <tr> <td>14</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>15</td> <td>4th_Place_Ensembling_submission 746. 564</td> <td>1.2</td> </tr> <tr> <td>16</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>17</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>18</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>19</td> <td>1plase 729 569</td> <td>3.09</td> </tr> <tr> <td>20</td> <td>1plase 729 569</td> <td></td> </tr> <tr> <td>21</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>22</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>23</td> <td>n9_736_3rd_place_psevdo_submission 736</td> <td>1.3</td> </tr> <tr> <td>24</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>25</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>26</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>27</td> <td>2nd place result_11 776 575</td> <td></td> </tr> <tr> <td>28</td> <td>JK-PIECE Submit-best 719 592</td> <td></td> </tr> <tr> <td>29</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>30</td> <td>n9_736_3rd_place_psevdo_submission 736</td> <td>1.2</td> </tr> <tr> <td>31</td> <td>1plase 729 569</td> <td></td> </tr> <tr> <td>32</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>33</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>34</td> <td>24plase LS NK 784</td> <td></td> </tr> <tr> <td>35</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>36</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>37</td> <td>2nd place result_9 750. 559</td> <td></td> </tr> <tr> <td>38</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>39</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>40</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>41</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>42</td> <td>4th_Place_Ensembling_submission 746. 564</td> <td>1.2</td> </tr> <tr> <td>43</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>44</td> <td>m18_790_submission_calibrated_max_d 790</td> <td>2</td> </tr> <tr> <td>45</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>46</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>47</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>48</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>49</td> <td>24plase LS NK 784</td> <td></td> </tr> <tr> <td>50</td> <td>n9_736_3rd_place_psevdo_submission 736</td> <td>1.2</td> </tr> <tr> <td>51</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>52</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>53</td> <td>24plase LS RG 834</td> <td></td> </tr> <tr> <td>54</td> <td>24plase LS NK 784</td> <td>1.3</td> </tr> <tr> <td>55</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>56</td> <td>1plase 729 569</td> <td></td> </tr> <tr> <td>57</td> <td>24plase LS RG 834</td> <td>1.2</td> </tr> <tr> <td>58</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>59</td> <td>2nd place result_9 750. 559</td> <td></td> </tr> <tr> <td>60</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>61</td> <td>24plase LS NK 784</td> <td></td> </tr> <tr> <td>62</td> <td>1plase 729 569</td> <td>1.2</td> </tr> <tr> <td>63</td> <td>2nd place result_9 750. 559</td> <td></td> </tr> <tr> <td>64</td> <td>n9_736_3rd_place_psevdo_submission 736</td> <td>1.3</td> </tr> <tr> <td>65</td> <td>24plase LS NK 784</td> <td>2.9</td> </tr> <tr> <td>66</td> <td>24plase LS NK 784</td> <td></td> </tr> <tr> <td>67</td> <td>m4_775_LS_T4 775</td> <td>1.2</td> </tr> <tr> <td>68</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>69</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>70</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>71</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>72</td> <td>3rd place submission 732,2 548</td> <td>1.2</td> </tr> <tr> <td>73</td> <td>24plase LS NK 784</td> <td></td> </tr> <tr> <td>74</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>75</td> <td>24plase LS RG 834</td> <td>1.3</td> </tr> <tr> <td>76</td> <td>4th_Place_Ensembling_submission 746. 564</td> <td>1.3</td> </tr> <tr> <td>77</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>78</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>79</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>80</td> <td>n9_736_3rd_place_psevdo_submission 736</td> <td>1.2</td> </tr> <tr> <td>81</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>82</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>83</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>84</td> <td>24plase LS NK 784</td> <td>1.3</td> </tr> <tr> <td>85</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>86</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>87</td> <td>m18_790_submission_calibrated_max_d 790</td> <td>1.3</td> </tr> <tr> <td>88</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>89</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>90</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>91</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>92</td> <td>3rd place submission 732,2 548</td> <td>1.2</td> </tr> <tr> <td>93</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>94</td> <td>n9_736_3rd_place_psevdo_submission 736</td> <td>1.3</td> </tr> <tr> <td>95</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>96</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>97</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>98</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>99</td> <td>2nd place result_15 758 551</td> <td>1.2</td> </tr> <tr> <td>100</td> <td>24plase LS NK 784</td> <td></td> </tr> <tr> <td>101</td> <td>2nd place result_15 758 551</td> <td></td> </tr> <tr> <td>102</td> <td>2nd place result_9 750. 559</td> <td></td> </tr> <tr> <td>103</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>104</td> <td>3rd place submission 732,2 548</td> <td>1.2</td> </tr> <tr> <td>105</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>106</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>107</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>108</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>109</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>110</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>111</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>112</td> <td>1plase 729 569</td> <td></td> </tr> <tr> <td>113</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>114</td> <td>n9_736_3rd_place_psevdo_submission 736</td> <td></td> </tr> <tr> <td>115</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>116</td> <td>m4_775_LS_T4 775</td> <td>1.2</td> </tr> <tr> <td>117</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>118</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>119</td> <td>3rd place submission 732,2 548</td> <td>1.2</td> </tr> <tr> <td>120</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>121</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>122</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>123</td> <td>m4_775_LS_T4 775</td> <td>1.3</td> </tr> <tr> <td>124</td> <td>24plase LS RG 834</td> <td></td> </tr> <tr> <td>125</td> <td>2nd place result_9 750. 559</td> <td></td> </tr> <tr> <td>126</td> <td>1plase 729 569</td> <td></td> </tr> <tr> <td>127</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>128</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>129</td> <td>24plase LS NK 784</td> <td></td> </tr> <tr> <td>130</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>131</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>132</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>133</td> <td>m18_790_submission_calibrated_max_d 790</td> <td>1.675</td> </tr> <tr> <td>134</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>135</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>136</td> <td>24plase LS NK 784</td> <td>2.031</td> </tr> <tr> <td>137</td> <td>2nd place result_15 758 551</td> <td>1.2</td> </tr> <tr> <td>138</td> <td>2nd place result_15 758 551</td> <td></td> </tr> <tr> <td>139</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>140</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>141</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>142</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>143</td> <td>3rd place submission 732,2 548</td> <td>1.2</td> </tr> <tr> <td>144</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>145</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>146</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>147</td> <td>JK-PIECE Submit-best 719 592</td> <td>1.21</td> </tr> <tr> <td>148</td> <td>n9_736_3rd_place_psevdo_submission 736</td> <td></td> </tr> <tr> <td>149</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>150</td> <td>JK-PIECE Submit-best 719 592</td> <td></td> </tr> <tr> <td>151</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>152</td> <td>1plase 729 569</td> <td></td> </tr> <tr> <td>153</td> <td>1plase 729 569</td> <td></td> </tr> <tr> <td>154</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>155</td> <td>2nd place result_15 758 551</td> <td></td> </tr> <tr> <td>156</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>157</td> <td>m18_790_submission_calibrated_max_d 790</td> <td></td> </tr> <tr> <td>158</td> <td>JK-PIECE Submit-best 719 592</td> <td></td> </tr> <tr> <td>159</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>160</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>161</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>162</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>163</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>164</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>165</td> <td>JK-PIECE Submit-best 719 592</td> <td>1.65</td> </tr> <tr> <td>166</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>167</td> <td>1plase 729 569</td> <td></td> </tr> <tr> <td>168</td> <td>2nd place result_9 750. 559</td> <td></td> </tr> <tr> <td>169</td> <td>m18_790_submission_calibrated_max_d 790</td> <td>1.2</td> </tr> <tr> <td>170</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>171</td> <td>pyBoost 760. 586</td> <td>1.2</td> </tr> <tr> <td>172</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>173</td> <td>2nd place result_9 750. 559</td> <td></td> </tr> <tr> <td>174</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>175</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>176</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>177</td> <td>m4_775_LS_T4 775</td> <td></td> </tr> <tr> <td>178</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>179</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>180</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>181</td> <td>2nd place result_15 758 551</td> <td></td> </tr> <tr> <td>182</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>183</td> <td>24plase LS RG 834</td> <td>1.5</td> </tr> <tr> <td>184</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>185</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>186</td> <td>2nd place result_9 750. 559</td> <td></td> </tr> <tr> <td>187</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>188</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>189</td> <td>24plase LS NK 784</td> <td></td> </tr> <tr> <td>190</td> <td>4th_Place_Ensembling_submission 746. 564</td> <td></td> </tr> <tr> <td>191</td> <td>24plase LS NK 784</td> <td>1.3</td> </tr> <tr> <td>192</td> <td>2nd place result_9 750. 559</td> <td></td> </tr> <tr> <td>193</td> <td>2nd place result_15 758 551</td> <td></td> </tr> <tr> <td>194</td> <td>2nd place result_15 758 551</td> <td>1.2</td> </tr> <tr> <td>195</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>196</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>197</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>198</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>199</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>200</td> <td>24plase LS NK 784</td> <td></td> </tr> <tr> <td>201</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>202</td> <td>1plase 729 569</td> <td></td> </tr> <tr> <td>203</td> <td>4th_Place_Ensembling_submission 746. 564</td> <td></td> </tr> <tr> <td>204</td> <td>2nd place result_15 758 551</td> <td></td> </tr> <tr> <td>205</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>206</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>207</td> <td>JK-PIECE Submit-best 719 592</td> <td>1.2</td> </tr> <tr> <td>208</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>209</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>210</td> <td>24plase LS RG 834</td> <td>1.870</td> </tr> <tr> <td>211</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>212</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>213</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>214</td> <td>1plase 729 569</td> <td></td> </tr> <tr> <td>215</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>216</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>217</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>218</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>219</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>220</td> <td>n9_736_3rd_place_psevdo_submission 736</td> <td></td> </tr> <tr> <td>221</td> <td>2nd place result_15 758 551</td> <td></td> </tr> <tr> <td>222</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>223</td> <td>24plase LS NK 784</td> <td></td> </tr> <tr> <td>224</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>225</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>226</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>227</td> <td>24plase LS NK 784</td> <td></td> </tr> <tr> <td>228</td> <td>2nd place result_15 758 551</td> <td></td> </tr> <tr> <td>229</td> <td>24plase LS NK 784</td> <td></td> </tr> <tr> <td>230</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>231</td> <td>2nd place result_9 750. 559</td> <td></td> </tr> <tr> <td>232</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>233</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>234</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>235</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>236</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>237</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>238</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>239</td> <td>JK-PIECE Submit-best 719 592</td> <td>1.351</td> </tr> <tr> <td>240</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>241</td> <td>m18_790_submission_calibrated_max_d 790</td> <td>1.3</td> </tr> <tr> <td>242</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>243</td> <td>24plase LS NK 784</td> <td></td> </tr> <tr> <td>244</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>245</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>246</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>247</td> <td>2nd place result_9 750. 559</td> <td></td> </tr> <tr> <td>248</td> <td>4th_Place_Ensembling_submission 746. 564</td> <td></td> </tr> <tr> <td>249</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>250</td> <td>1plase 729 569</td> <td></td> </tr> <tr> <td>251</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> <tr> <td>252</td> <td>pyBoost 760. 586</td> <td></td> </tr> <tr> <td>253</td> <td>24plase LS RG 834</td> <td></td> </tr> <tr> <td>254</td> <td>2nd place result_15 758 551</td> <td></td> </tr> <tr> <td>255</td> <td>3rd place submission 732,2 548</td> <td></td> </tr> </tbody> </table> <h2>4. Data preprocessing ( solution)</h2> <p>The models employed are NN and pyboost.</p> <p>Cross validation is not used</p> <h2>5. Method ( late submission)</h2> <h2>Ensembling <strong>late submissions</strong></h2> <p>I evaluate for various compounds the models:</p> <table> <thead> <tr> <th>model</th> </tr> </thead> <tbody> <tr> <td>1th place</td> </tr> <tr> <td>2nd place</td> </tr> <tr> <td>3rd place</td> </tr> <tr> <td>4th place</td> </tr> <tr> <td>24th place NK</td> </tr> <tr> <td>24th place RG</td> </tr> <tr> <td>pyBoost</td> </tr> </tbody> </table> <p>Green select indicates that the model has the lowest error among all.</p> <table> <thead> <tr> <th>late submissions</th> <th>private LB</th> <th>public LB</th> </tr> </thead> <tbody> <tr> <td>1th place+2nd place+3rd place+4th place+24th place NK+24th place RG+pyBoost+50%+mult</td> <td><strong>0,597</strong></td> <td>0,548</td> </tr> </tbody> </table> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4172517%2F1dadc65287d17a1469ebbd71e0e95364%2F2023-12-13%20%2023.15.41.png?generation=1702499882391676&alt=media" alt=""></p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4172517%2F887cf9a7156a8a35b83850cdf7168c8f%2F2023-12-13%20%2023.16.16.png?generation=1702499901312868&alt=media" alt=""></p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4172517%2F8600e331c1e6304df98f7bcaab85a41e%2F2023-12-13%20%2023.16.44.png?generation=1702499920405715&alt=media" alt=""></p> <p>Why is Vorinostat's '24 place model LS RG' the best model for Myeloid cells, with a private score improvement of +0.003?</p> <h2>6. Final result ( solution, late submission)</h2> <table> <thead> <tr> <th>solution</th> <th>private LB</th> <th>public LB</th> <th>solution or late submission</th> </tr> </thead> <tbody> <tr> <td>bland</td> <td><strong>0,577</strong></td> <td>0,53</td> <td>late submission</td> </tr> <tr> <td>Pyboost max_depth 10, ntrees 5000, lr 001, colsample 035</td> <td>0,763</td> <td>0,586</td> <td>solution</td> </tr> <tr> <td>Pyboost max_depth 12, ntrees 5000, lr 001, colsample 075, n_components 49, T8 b7t17</td> <td><strong>0,760</strong></td> <td>0,586</td> <td>solution</td> </tr> <tr> <td>Pyboost max_depth 12, ntrees 1000, lr 001, colsample 035, n_components 50, T8 b7t1 bcell7 mie6</td> <td>0,761</td> <td>0,578</td> <td>solution</td> </tr> <tr> <td>quantile(0.7)</td> <td>1,003</td> <td>0,797</td> <td>solution</td> </tr> </tbody> </table> <h2>What help ( solution)</h2> <p><strong>Drop T8 cell</strong><br> <strong>Repeat 17 drug - 7 time</strong> +0,001 to Pyboost</p> <h2>What help ( late submission)</h2> <p>The main score improvement is in <strong>4th Place Magic Postprocessing</strong> - <br> <strong>multiply the compound by a constant</strong> (between 1.4 and 3.09).</p> <p>Base score 3rd place submission Private LB 732 , public LB 548</p> <table> <thead> <tr> <th>Algorithm</th> <th>Private LB improve</th> <th>Private LB</th> </tr> </thead> <tbody> <tr> <td>Base 3rd place submission</td> <td></td> <td>0.732</td> </tr> <tr> <td>select model from 10 for compound</td> <td>+0.075</td> <td>0.657</td> </tr> <tr> <td><strong>B cells, ABT-199</strong> = 50% model <strong>B cells, ABT-199</strong> + 50% train <strong>B cells, Alvocidib</strong></td> <td>+0.015</td> <td></td> </tr> <tr> <td>Add constant (+0.1, -0.1, +3 B cells BMS-387032)</td> <td>+0.008</td> <td></td> </tr> <tr> <td>50% model + 50% compound</td> <td>+0.008</td> <td>0.626</td> </tr> <tr> <td>4th Place Magic Postprocessing of 1 compound: <strong>B cells, BMS-387032</strong> MULT 3.09</td> <td>+0.027</td> <td>0.609</td> </tr> <tr> <td>4th Place Magic Postprocessing of 55 compounds MULT 1.2, 1.3, 2</td> <td>+0.009</td> <td><strong>0.600</strong></td> </tr> </tbody> </table> <h2>+0.008 Private LB detail:</h2> <p><strong>Compound A</strong> = <strong>Compound A</strong> model 50% + <strong>Compound B</strong> train * 50%</p> <table> <thead> <tr> <th>50% model submission Cell, Compound</th> <th>50% train Cell, Compound</th> </tr> </thead> <tbody> <tr> <td>27 B cells, CGM-097</td> <td>train row 3. T regulatory cells, Clotrimazole</td> </tr> <tr> <td>65 B cells, Lamivudine</td> <td>train row 7. T regulatory cells, Mometasone Furoate</td> </tr> <tr> <td>147 Myeloid cells, BMS-536924</td> <td>train row 9. Myeloid cells, Idelalisib</td> </tr> <tr> <td>152 Myeloid cells,CC-401</td> <td>train row 1. T cells CD4+, Clotrimazole</td> </tr> <tr> <td>155 Myeloid cells,CGM-097</td> <td>train row 0. NK cells, Clotrimazole</td> </tr> <tr> <td>157 Myeloid cells,Canertinib</td> <td>train row 9. Myeloid cells, Idelalisib</td> </tr> <tr> <td>207 Myeloid cells,PF-03814735</td> <td>train row 9. Myeloid cells, Idelalisib</td> </tr> <tr> <td>214 Myeloid cells,Prednisolone</td> <td>train row 6. T cells CD8+, Mometasone Furoate</td> </tr> <tr> <td>229 Myeloid cells,SLx-2119</td> <td>train row 2. T cells CD8+, Clotrimazole</td> </tr> <tr> <td>241 Myeloid cells,Tacalcitol</td> <td>train row 234. Myeloid cells, Porcn Inhibitor III</td> </tr> <tr> <td>247 Myeloid cells,Tosedostat</td> <td>train row 1. T cells CD4+, Clotrimazole</td> </tr> <tr> <td>248 Myeloid cells,Trametinib</td> <td>train row 9. Myeloid cells, Idelalisib</td> </tr> <tr> <td>251 Myeloid cells,Vanoxerine</td> <td>train row 1. T cells CD4+, Clotrimazole</td> </tr> </tbody> </table> <h2>7. Sources ( solution)</h2> <p><a href="https://www.kaggle.com/code/liudacheldieva/blend-for-single-cell-perturbations-dd4fc8" target="_blank">https://www.kaggle.com/code/liudacheldieva/blend-for-single-cell-perturbations-dd4fc8</a></p> <p><strong>0.760</strong> <a href="https://www.kaggle.com/code/jeffreylihkust/copy-of-pyboost-secret-grandmaster-s-to-1d68b4/notebook?scriptVersionId=150765833" target="_blank">https://www.kaggle.com/code/jeffreylihkust/copy-of-pyboost-secret-grandmaster-s-to-1d68b4/notebook?scriptVersionId=150765833</a><br> 0.761 <a href="https://www.kaggle.com/code/emmawilsonev/copy-of-pyboost-secret-grandmaster-s-to-1d68b4?scriptVersionId=150583811" target="_blank">https://www.kaggle.com/code/emmawilsonev/copy-of-pyboost-secret-grandmaster-s-to-1d68b4?scriptVersionId=150583811</a><br> <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/458750" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/458750</a><br> <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/460191" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/460191</a></p> <h2>8. Sources ( late submission)</h2> <p>Private score <strong>0.577</strong> <a href="https://www.kaggle.com/code/liudacheldieva/fork-of-ensembling" target="_blank">https://www.kaggle.com/code/liudacheldieva/fork-of-ensembling</a> <br> summation.csv 0.577: <a href="https://www.kaggle.com/datasets/liudacheldieva/op-0-670" target="_blank">https://www.kaggle.com/datasets/liudacheldieva/op-0-670</a> </p> <h2>9. Used submission.csv ( late submission)</h2> <p>import_nn = pd.read_csv('/kaggle/input/4th-place-neural-net/submission.csv', index_col='id')<br> import_lgbm = pd.read_csv('/kaggle/input/lgbm-with-gene-aggregation-4th-place-writeup/submission.csv', index_col='id')<br> import_nlp = pd.read_csv('/kaggle/input/nlp-regression/submission.csv', index_col='id')<br> import_760pyboost = pd.read_csv('/kaggle/input/copy-of-pyboost-secret-grandmaster-s-to-1d68b4/submission.csv', index_col='id')<br> n1_776_result_11 = pd.read_csv('/kaggle/input/2-pla-submit/result (11).csv', index_col='id')<br> n5_760_submission_pyboost = pd.read_csv('/kaggle/input/copy-of-pyboost-secret-grandmaster-s-to-1d68b4/submission.csv', index_col='id')<br> n6_776_submission_nn = pd.read_csv('/kaggle/input/4th-place-neural-net/submission.csv', index_col='id')<br> n7_792_submission_lgbm = pd.read_csv('/kaggle/input/lgbm-with-gene-aggregation-4th-place-writeup/submission.csv', index_col='id')<br> n8_813_submission_nlp = pd.read_csv('/kaggle/input/nlp-regression/submission.csv', index_col='id')<br> n3_750_result_9 = pd.read_csv('/kaggle/input/2-pla-submit/result (9).csv', index_col='id')<br> n4_767_result_8 = pd.read_csv('/kaggle/input/2-pla-submit/result (8).csv', index_col='id')<br> n2_758_result_15 = pd.read_csv('/kaggle/input/2-pla-submit/result (15).csv', index_col='id')<br> n9_736_3rd_place_psevdo_submission = pd.read_csv('/kaggle/input/3rd-place/3rd place psevdo submission(14).csv', index_col='id')<br> n12_746_OP_pub530_myModels_exp1 = pd.read_csv('/kaggle/input/4-pl-sub-late/OP_pub530_myModels_exp1.csv', index_col='id')<br> import_732 = pd.read_csv('/kaggle/input/3rd-place/3rd place submission.csv', index_col='id')<br> import_746 = pd.read_csv('/kaggle/input/4-pl-sub-late/4th_Place_Ensembling_submission.csv', index_col='id')<br> n13_729_1_pl = pd.read_csv('/kaggle/input/submit-best/submission.csv', index_col='id')<br> n14_719_sub_b = pd.read_csv('/kaggle/input/1st-place-solution/submission.csv', index_col='id')<br> import_670 = pd.read_csv('/kaggle/input/op-0-670/submission732_some_746_some760_750_558_776_736_719_729.csv', index_col='id')<br> import_657 = pd.read_csv('/kaggle/input/op-0-670/submission732_some_746_some760_750_558_776_736_719_729_784_834_785.csv', index_col='id')<br> import_626 = pd.read_csv('/kaggle/input/op-0-670/submission732_some_746_some760_750_558_776_736_719_729_784_834_785_add.csv', index_col='id')<br> import_600 = pd.read_csv('/kaggle/input/op-0-670/submission732_some_746_some760_750_558_776_736_719_729_784_834_785_add_mult.csv', index_col='id')<br> import_600 = pd.read_csv('/kaggle/input/op-0-670/submission732_some_746_some760_750_558_776_736_719_729_784_834_785_add_mult.csv', index_col='id')<br> m1_792_4th_submission = pd.read_csv('/kaggle/input/lgbm-with-gene-aggregation-4th-place-writeup/submission.csv', index_col='id')<br> m2_784_LS_NK = pd.read_csv('/kaggle/input/24th-using-linear-algebra-priv-pub-0-768-0-582/LS_NK.csv', index_col='id')<br> m3_834_LS_RG = pd.read_csv('/kaggle/input/24th-using-linear-algebra-priv-pub-0-768-0-582/LS_RG.csv', index_col='id')<br> m4_775_LS_T4 = pd.read_csv('/kaggle/input/24th-using-linear-algebra-priv-pub-0-768-0-582/LS_T4.csv', index_col='id')<br> m5_959_LS_T8 = pd.read_csv('/kaggle/input/24th-using-linear-algebra-priv-pub-0-768-0-582/LS_T8.csv', index_col='id')<br> m6_784_SVD_NK = pd.read_csv('/kaggle/input/24th-using-linear-algebra-priv-pub-0-768-0-582/SVD_NK.csv', index_col='id')<br> m7_834_SVD_RG = pd.read_csv('/kaggle/input/24th-using-linear-algebra-priv-pub-0-768-0-582/SVD_RG.csv', index_col='id')<br> m8_775_SVD_T4 = pd.read_csv('/kaggle/input/24th-using-linear-algebra-priv-pub-0-768-0-582/SVD_T4.csv', index_col='id')<br> m9_959_SVD_T8 = pd.read_csv('/kaggle/input/24th-using-linear-algebra-priv-pub-0-768-0-582/SVD_T8.csv', index_col='id')<br> m10_773_SVD_b_nk_m_t4 = pd.read_csv('/kaggle/input/24th-using-linear-algebra-priv-pub-0-768-0-582/SVD_b_nk_m_t4.csv', index_col='id')<br> m11_786_SVD_b_t4_m_nk = pd.read_csv('/kaggle/input/24th-using-linear-algebra-priv-pub-0-768-0-582/SVD_b_t4_m_nk.csv', index_col='id')<br> m12_768_SVD_nk_t4 = pd.read_csv('/kaggle/input/24th-using-linear-algebra-priv-pub-0-768-0-582/SVD_nk_t4.csv', index_col='id')<br> m13_771_SVD_nk_t4_t8_rg = pd.read_csv('/kaggle/input/24th-using-linear-algebra-priv-pub-0-768-0-582/SVD_nk_t4_t8_rg.csv', index_col='id')<br> m14_746_op_late_submission = pd.read_csv('/kaggle/input/op-late-sub-pub530-mymodels-exp1/submission.csv', index_col='id')<br> m15_863_plase30_submission = pd.read_csv('/kaggle/input/30-op2scp-transformer-deberta-v3-small-demo/submission.csv', index_col='id')<br> m17_769_submission_Pyboost_max_depth10_ntrees5000_lr001_subsample1_colsample035_n_components50 = pd.read_csv('/kaggle/input/pyboost-u900/submission_Pyboost_max_depth10_ntrees5000_lr001_subsample1_colsample035_n_components50.csv', index_col='id')<br> m18_790_submission_calibrated_max_d = pd.read_csv('/kaggle/input/pyboost-u900/submission_calibrated_max_depth10_ntrees5000_lr001_subsample1_colsample035_n_components50.csv', index_col='id')<br> M19_785_13th_place_mlp = pd.read_csv('/kaggle/input/13th-place-solution-mlp/submission_example_MLP.csv', index_col='id')<br> import_755_10pl = pd.read_csv('/kaggle/input/10th-place/sub_submission.csv', index_col='id')<br> import_748_26pl = pd.read_csv('/kaggle/input/op-26-place/submission.csv', index_col='id')<br> import_577 = pd.read_csv('/kaggle/input/op-0-670/submi_mu_0.577.csv', index_col='id')</p> <p>Thank you for taking the time to read. Feel free to ask any questions you may have.</p>
Open Problems – Single-Cell Perturbations	45 Place Solution for the Open Problems – Single-Cell Perturbations Competition	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><h1>Competition Pages</h1> <p><a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview</a></p> <p><a href="https://openproblems.bio/" target="_blank">https://openproblems.bio/</a></p> <h1>Overview of the Approach</h1> <p>We try CatBoost in multi target mode, but woking worse than constants in submission. <br> <a href="https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=&cad=rja&uact=8&ved=2ahUKEwiPs9e4jvmCAxUSDRAIHRIaC48QFnoECAoQAQ&url=https%3A%2F%2Fgithub.com%2Fsberbank-ai-lab%2FPy-Boost&usg=AOvVaw35jZARIhArmT7tiDnuD6BO&opi=89978449" target="_blank">PyBoost</a> it's a great framework for multi target.</p> <h1>Details of the submission</h1> <h1>Our blend:</h1> <p>public kernels [: 128] 0.574 * 0.2 + 0.577 * 0.8<br> [128: ] 0.584 PyBoost + 0.574 public</p> <h1>Not working:</h1> <p>Ridge regression<br> ChemBert<br> CatBoost</p>
Open Problems – Single-Cell Perturbations	SMILES😘 Data Science Competition: A Deep Dive	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><h1>Introduction:</h1> <p>In the pursuit of advancing single-cell data science and catalyzing drug discovery, the SMILES😘 competition introduces a groundbreaking dataset. Developed for the competition, this dataset features human peripheral blood mononuclear cells (PBMCs) and includes 144 compounds from the Library of Integrated Network-Based Cellular Signatures (LINCS) Connectivity Map. The experiment, replicated in three healthy human donors, provides meticulous measurements of single-cell gene expression profiles following 24 hours of treatment.</p> <h1>Exploratory Data Analysis (EDA):</h1> <h2>Distribution of Donors:</h2> <ul> <li>Visualized the frequency of each donor in the dataset using a count plot.</li> <li>The plot offers an overview of how samples are distributed across different donors.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7212220%2F75a8c97f33b9542e9d1e14f9ff873d54%2FDistDonors.png?generation=1702342943516621&alt=media" alt="image"></li> </ul> <h2>Distribution of Dose (uM):</h2> <ul> <li>Utilized a histogram to showcase the distribution of doses in microMolarity.</li> <li>This plot provides insight into how doses are spread across the dataset.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7212220%2F0fa42111ed6b467ad42bbc28cb55a711%2FDist-Dose(uM).png?generation=1702344900095659&alt=media" alt="image"></li> </ul> <h2>Average Dose at Different Timepoints:</h2> <ul> <li>Presented a bar plot illustrating the average dose (uM) at different timepoints.</li> <li>This plot helps visualize how doses vary with time.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7212220%2F70275fa6f5b4d479338c4d4d9555932d%2FAveDoseAtDiff.png?generation=1702343097669094&alt=media" alt="image"></li> </ul> <h2>Distribution of Dose (uM) Summary:</h2> <ul> <li>Provided a summary of the distribution of doses using a box plot.</li> <li>The plot includes quartiles, median, and potential outliers.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7212220%2Ff826df73e40e1c01448aba6a23d33bfc%2FDist-dose.png?generation=1702343026198358&alt=media" alt="image"></li> </ul> <h2>Dose (uM) and Timepoint (hours) Relationship:</h2> <ul> <li>Visualized the relationship between dose (uM) and timepoint (hours) using a pair plot.</li> <li>The diagonal shows kernel density estimates.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7212220%2F54fb101ac78660f4934bf3b46bbd5ab4%2FDose%20and%20Timep.png?generation=1702345034468959&alt=media" alt="image"></li> </ul> <h2>Distribution of Cell Types:</h2> <ul> <li>Displayed a count plot to visualize the occurrences of each cell type.</li> <li>This plot gives an overview of the distribution of cell types in the dataset.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7212220%2F8e094f4cf2aa946d695e1dc43eaf2a56%2FDistCellType.png?generation=1702343745263825&alt=media" alt="image"></li> </ul> <h2>Correlation Heatmap:</h2> <ul> <li>Presented a heatmap visualizing the correlation between dose (uM) and timepoint (hours).</li> <li>Values closer to 1 indicate a stronger positive correlation.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7212220%2F33c5b64b658ff3e6749524c57f7993e9%2FCorHeatmap.png?generation=1702343800299076&alt=media" alt="image"></li> </ul> <h2>Control Distribution:</h2> <ul> <li>Represented the distribution of 'control' values (True or False) using a pie chart.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7212220%2F601d850c48e2ae4a88c4c3107f6e51f9%2FDist-pie.png?generation=1702343949783969&alt=media" alt="image"></li> </ul> <h2>Dose (uM) vs. Timepoint (hours):</h2> <ul> <li>Illustrated the relationship between dose (uM) and timepoint (hours) with a scatter plot.</li> <li>Different colors represent different control values.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7212220%2F3e5768bd41279903c51770bb626b5998%2FDose%20vs%20Timepoint.png?generation=1702344027609287&alt=media" alt="image"></li> </ul> <h2>Dose (uM) by Control:</h2> <ul> <li>Used a violin plot to show the distribution of doses for each control category.</li> <li>Allows for a comparison of dose distributions.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7212220%2F6ace487693a5a1c21cfd07bca506abd6%2FDosebycontrol.png?generation=1702344109580758&alt=media" alt="image"></li> </ul> <h1>Feature Extraction:</h1> <h2>Morgan Fingerprints:</h2> <ul> <li>Introduced Morgan fingerprints as a numerical representation suitable for T-SNE and PCA.</li> <li>Provided insights into the structure and application of Morgan fingerprints in chemoinformatics and drug discovery.</li> </ul> <h2>T-SNE and PCA Visualization:</h2> <p>Applied T-SNE and PCA to the features for dimensionality reduction and visualization.</p> <h2>PCA Visualization:</h2> <ul> <li>Utilized PCA for dimensionality reduction and visualization.</li> <li>The scatter plot displays the reduced features in two dimensions.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7212220%2Fb8c9af44df865b3fb9e7da392cc29e8e%2FPCA-vis.png?generation=1702344215751186&alt=media" alt="image"></li> </ul> <h2>Molecule Visualizations:</h2> <ul> <li>Generated images for a subset of molecules using RDKit.</li> </ul> <h2>Molecule Visualizations:</h2> <ul> <li>Added a new column 'Molecule' with RDKit Mol objects.</li> <li>Visualized a subset of molecules with RDKit.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7212220%2Fe6bb7c2f447b811fe06151aad047f3ac%2FRIDkit.png?generation=1702344347921123&alt=media" alt="image"></li> </ul> <h1>Prediction Results:</h1> <h2>Prediction Results for Various Models:</h2> <ul> <li>Presented results for linear regression, logistic regression, decision tree, random forest, SVM, KNN, K-Means, naive Bayes, and neural network models.</li> <li>Included metrics such as mean absolute error, mean squared error, and R-squared (R2).<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7212220%2F58a4cc1d79d614594e8e98f1bb411ebd%2FResults.png?generation=1702344308542403&alt=media" alt="image"></li> </ul> <h1>Conclusion:</h1> <p>In conclusion, this comprehensive analysis of the SMILES😘 competition dataset provides valuable insights into the distribution of donors, doses, timepoints, and cell types. The exploration of Morgan fingerprints, T-SNE, PCA, and molecule visualizations adds depth to the understanding of the dataset. The prediction results offer a benchmark for various models, highlighting their performance in the context of the competition's objectives. This write-up serves as a resource for researchers and data scientists engaged in single-cell data analysis and drug discovery.</p> <p>SMILES😘: <a href="https://www.kaggle.com/code/jocelyndumlao/smiles/notebook" target="_blank">https://www.kaggle.com/code/jocelyndumlao/smiles/notebook</a></p>
Open Problems – Single-Cell Perturbations	20th Place Solution Writeup For Open Problems - Single-cell Perturbations Competition	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>Please find attached our detailed solution write-up, submitted for consideration for the Judge's reward. For your convenience, we have included all necessary citations within the attached PDF document.</p> <p>Additionally, the individual notebooks referenced in our write-up are accessible at the following GitHub repository: <a href="https://github.com/AntoinePassemiers/Open-Challenges-Single-Cell-Perturbations/tree/master" target="_blank">https://github.com/AntoinePassemiers/Open-Challenges-Single-Cell-Perturbations/tree/master</a></p>
NeurIPS 2023 - Machine Unlearning	6th Place Solution for the NeurIPS 2023 - Machine Unlearning Competition	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: NeurIPS 2023 - Machine Unlearning <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>First of all, we would like to thank the organizing committee, it was an incredible experience, and we are so grateful for all the hard work and effort you and your team put into making it happen.</p> <h1>Context</h1> <ul> <li>Business context: <a href="https://www.kaggle.com/competitions/neurips-2023-machine-unlearning/overview" target="_blank">https://www.kaggle.com/competitions/neurips-2023-machine-unlearning/overview</a></li> <li>Data context: <a href="https://www.kaggle.com/competitions/neurips-2023-machine-unlearning/data" target="_blank">https://www.kaggle.com/competitions/neurips-2023-machine-unlearning/data</a></li> </ul> <h1>Overview of the approach</h1> <p>In our solution, we present a simple yet effective machine unlearning approach that uses a selective model parameter reset, a warm-up phase employing knowledge distillation and finally, a fine-tuning phase. Specifically, our method focuses on resetting the first and last layer of the original model, which is trained on the full training set. By resetting the first layer, we enable a disruption on the initial hidden representations of the data, leading to a direct decline in model performance, facilitation the forgetting of previously trained data. Resetting the last layer enables the model to diverge from its original output patterns, allowing it to approximate a new output distribution, which can result in similar output distribution to that of a model trained on a specific data subset, i.e., the retain set. </p> <ul> <li>We followed the data processing pipeline as provided in the starter notebook(run-unlearn-finetune), without further data augmentations.</li> <li>We submitted two final versions: one that uses the entire validation set and another that uses only samples from the first two classes for the warm-up phase. Note that these two classes were the only ones with samples in the forget set.</li> <li>Our method does not require the forget set.</li> </ul> <h1>Details of the submission</h1> <h2>Insights from Cifar-10</h2> <p>The initial phases involve resetting the first and layers of the original model. These two layers are chosen because the first layer significantly influences the rest of the model layers and the last layer determines the model’s final output distribution. With this reset step, we enable the model to deviate from its original state. <br> In addition, empirical observations from local experiments on the CIFAR-10 dataset showed that these two layers exhibited mostly negative cosine similarity between model weights trained on the full training set and models trained from scratch on a smaller subset (i.e., the retain set). <br> Thus, in terms of global weight parameters, this means that the two models found a similar solution with respect to predictive performance, but with different directions (See Figure "Weight Similarities" on the CIFAR-10 dataset between the pretrained and retrained on retain set model).</p> <h3>Weight Similarities</h3> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4512660%2Ffa884bf7bbac22713c58b723cea9d13e%2Fcos_sim_layer.png?generation=1701973645041086&alt=media" alt=""></p> <p>Furthermore, we measured the differences in terms of activation distributions between the pre-trained model and the model trained from scratch on the retain set. This experiment revealed that the differences in terms of cosine similarity are clearly evident even regarding their activations (See figures below) These observations lay the foundations for resetting the first and the last layer parameters of the original model. </p> <h3>Similarity of Activations after MaxPooling layer</h3> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4512660%2Fc887eea40d7e4d6087598c2aed603d6b%2F5.Maxpool_Embeddings_Cropped.png?generation=1701974052559749&alt=media" alt=""></p> <h3>Embedding Similarity (after AvgPool layer)</h3> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4512660%2F202a742464afbd7f0de798730944545d%2F1.Avgpool_Embeddings_Cropped.png?generation=1701974207236188&alt=media" alt=""><br> Finally, we performed experiments with baseline unlearning algorithms including simple finetuning, finetuning by resetting only the final layer, eu-k and cf-k forgetting [1], unlearning by maximizing the loss on the forget set [2], unlearning with bad teaching [3] and SCRUB [4], which minimizes the divergence of a student model from the teacher on the retain set and maximizes the divergence on forget set. In all of the above cases, none of the methods achieved significantly higher public score compared to the baseline fine-tuning approach.</p> <p>After resetting the first and the last layer of the network, we include a rapid warm-up phase using the validation set. The goal in this phase is to prepare the model for the third phase by minimizing the Kullback-Leibler (KL) divergence between the outputs of the original pre-trained model (teacher) and the reinitialized model (student).</p> <p>The final phase includes fine-tuning the student model on the retain set. In this stage, we combine three types of losses: standard cross-entropy loss, soft cross-entropy loss and KL divergence. The cross-entropy loss ensures the model's accuracy on the underlying task using hard labels from the retain set. The soft cross-entropy loss involves comparing softened predictions of the student model with soft labels from the teacher model. The KL divergence loss combined with the soft cross-entropy facilitates rapid knowledge transfer and broader information capture. Additionally, the cosine annealing scheduler is integrated to optimize training dynamics, promoting faster convergence and efficient learning.<br> The Figure below shows a summary of the proposed pipeline.</p> <h2>Unlearning Pipeline Visualization</h2> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4512660%2Feb7b840f4ca0ea41f5df37386440712d%2FMachineUnleaning.drawio.png?generation=1701971655736516&alt=media" alt=""></p> <h1>Final Submissions</h1> <p>As mentioned earlier, we selected two variations of our pipeline. The first uses the entire validation set and the second employs the warm-up phase only a subset, specifically using the samples from the first two classes. This inspiration of this strategy derives from the distribution of forget set, which exclusively contains samples from the first two classes (0,1).</p> <p>To extract the samples belonging to the first two classes, we used the following function:</p> <pre><code> (): val_ds = HiddenDataset(split=) samples = [] sample val_ds: y = sample[] (y) == (y) == : samples.append(sample) val_loader = DataLoader(samples, batch_size=batch_size, shuffle=) val_loader </code></pre> <p>The scores of these two approaches are summarized in the following table:</p> <table> <thead> <tr> <th>Warm-up Approach</th> <th>Public Score</th> <th>Private Score</th> </tr> </thead> <tbody> <tr> <td>All classes</td> <td>0.08383</td> <td>0.07219</td> </tr> <tr> <td>Classes 0,1</td> <td>0.08324</td> <td><strong>0.07831</strong></td> </tr> </tbody> </table> <p>Notably, both approaches resulted in almost equivalent public scores. However, the approach which uses the first two classes from the validation set for warming-up the model demonstrated improved performance in the hidden test set. </p> <h2>Useful Tricks</h2> <ul> <li>Resetting a portion of model parameters </li> <li>CosineAnnealingLR Scheduling for Finetuning Phase</li> </ul> <h2>Strategies</h2> <ul> <li>Threefold Optimization Loss during Finetuning Phase </li> <li>High Temperature in both stages</li> </ul> <h2>What didn't work</h2> <ul> <li>Use of class weights (Despite their use in the original training pipeline)</li> <li>Algorithms that did not employ resetting resulted lower scores</li> <li>Variants of retraining (Starting from pretrained model on ImageNet resulted to low scores or threw exception probably due to exploding gradients)</li> </ul> <h1>Conclusion</h1> <p>In conclusion, throughout this competition we gained a better understanding of Machine Unlearning which has been both enlightening and challenging. Special thanks also to the non-Kaggle participant of our team, Nikos Komodakis for his contribution.</p> <h1>Sources</h1> <ol> <li>Goel, S., Prabhu, A., Sanyal, A., Lim, S. N., Torr, P., & Kumaraguru, P. (2022). Towards adversarial evaluations for inexact machine unlearning. arXiv preprint arXiv:2201.06640.</li> <li>Golatkar, A., Achille, A., & Soatto, S. (2020). Eternal sunshine of the spotless net: Selective forgetting in deep networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 9304-9312).</li> <li>Can bad teaching induce forgetting? Unlearning in deep networks using an incompetent teacher. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 37, No. 6, pp. 7210-7217).</li> <li>Kurmanji, M., Triantafillou, P., & Triantafillou, E. (2023). Towards Unbounded Machine Unlearning. arXiv preprint arXiv:2302.09880.</li> </ol> <ul> <li>Starter Notebook (run-unlearne-finetune) <a href="https://www.kaggle.com/code/eleni30fillou/run-unlearn-finetune" target="_blank">https://www.kaggle.com/code/eleni30fillou/run-unlearn-finetune</a></li> </ul> <p>Code for <a href="https://www.kaggle.com/code/stathiskaripidis/unlearning-by-resetting-layers-7th-on-private-lb" target="_blank">7th Place Solution</a></p> <h2>Team</h2> <ul> <li><a href="https://scholar.google.com/citations?user=jif2JYsAAAAJ&hl=en" target="_blank">Efstathios Karypidis</a>, PhD Student Archimedes Unit, Athena RC \| NTUA</li> <li><a href="https://scholar.google.com/citations?user=V1t6u_YAAAAJ&hl=en&oi=ao" target="_blank">Vasileios Perifanis</a>, PhD Student, DUTH</li> <li><a href="https://scholar.google.com/citations?user=srkOEMYAAAAJ&hl=el&oi=ao" target="_blank">Christos Chrysanthos Nikolaidis</a>, PhD Student, DUTH</li> <li><a href="https://scholar.google.com/citations?user=xCPoT4EAAAAJ&hl=en&oi=ao" target="_blank">Nikos Komodakis</a>, Assistant Professor, (non-Kaggle Participant), UoC</li> <li><a href="https://scholar.google.com/citations?user=Dxz0pLsAAAAJ&hl=en" target="_blank">Pavlos Efraimidis</a>, Professor, DUTH</li> </ul>
Open Problems – Single-Cell Perturbations	178th Place Solution for the Open Problems – Single-Cell Perturbations	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>Many thanks to the organizers for hosting the Open Problems – Single-Cell Perturbations competition. Congratulations to the winners and everyone who participated, I really learnt alot from the discussions and great notebooks!</p> <p>I thought particularly great contributions and insights were from the following:</p> <p><a href="https://www.kaggle.com/alexandervc" target="_blank">@alexandervc</a><br> <a href="https://www.kaggle.com/antoninadolgorukova" target="_blank">@antoninadolgorukova</a><br> <a href="https://www.kaggle.com/mehrankazeminia" target="_blank">@mehrankazeminia</a><br> <a href="https://www.kaggle.com/somayyehgholami" target="_blank">@somayyehgholami</a></p> <p>Context:</p> <p>Business context: <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview</a><br> Data context: <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/data" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/data</a><br> Integration of Biological Knowledge:</p> <p>Even though I was not at the top of the leader-board I wanted to share my experience in this competition and my approach! </p> <p>One of the objectives of this competition is to determine how compounds are involved in changes in gene expression within cells. For this competition, the organizers designed and generated a novel single-cell perturbational dataset in human peripheral blood mononuclear cells (PBMCs). 144 compounds were selected from the Library of Integrated Network-Based Cellular Signatures (LINCS) Connectivity Map dataset (PMID: 29195078) and measured single-cell gene expression profiles after 24 hours of treatment. The experiment was repeated in three healthy human donors, and the compounds were selected based on diverse transcriptional signatures observed in CD34+ hematopoietic stem cells.</p> <p>Before I started to use ML models, I was interested in exploring the dataset within this competition to determine the compounds involved and the distribution of cell types associated with them as outlined in the following notebook:</p> <p><a href="https://www.kaggle.com/code/insiyajafferji/op-single-cell-dataset-and-cell-type-distribution" target="_blank">https://www.kaggle.com/code/insiyajafferji/op-single-cell-dataset-and-cell-type-distribution</a></p> <p>In this notebook some initial dataset exploration helped me to understand cell type differences within PBMC samples treated with the compounds. I found that NK, CD4+ T cells, CD8+ T cells and Tregs are in all PBMC samples of the compounds being treated and there are a subset of PBMCs where compounds treated also have B and myeloid cells. PBMCs have been reported to contain a multitude of distinct multipotent progenitor cell populations and therefore treatment of certain drug compounds could have the ability to affect cell type distribution aswell as gene expression which can have an impact on the DE/DGE analysis.</p> <p>Interestingly some notebooks have suggested that the highest bias (differences between predicted and true values) and variability of gene DE predictions are related to individual drugs rather than cell types. <br> <a href="https://www.kaggle.com/code/antoninadolgorukova/op2-analysis-of-different-models-predictions" target="_blank">https://www.kaggle.com/code/antoninadolgorukova/op2-analysis-of-different-models-predictions</a></p> <p>Based on this information, the specific embeddings that I thought would help my ML models would be based on cell type, compound (sm_name and SMILES), and DE of genes (gene name).</p> <p>Exploration of the problem:</p> <p>When I was exploring the ways to approach the challenges associated with this competition I found the following paper useful:<br> <a href="https://genomebiology.biomedcentral.com/articles/10.1186/s13059-021-02544-3" target="_blank">https://genomebiology.biomedcentral.com/articles/10.1186/s13059-021-02544-3</a></p> <p>Here, feature selection an essential technique for single-cell data analysis in high-dimensional datasets.<br> Importantly, feature selection is an effective strategy to reduce the feature dimension and redundancy and can alleviate issues such as model overfitting in downstream analysis. Different from dimension reduction methods (e.g. principal component analysis) where features in a dataset are combined and/or transformed to derive a lower feature dimension, feature selection methods do not alter the original features in the dataset but only identify and select features that satisfy certain pre-defined criteria or optimise certain computational procedures. Some of the most popular research directions include selecting genes that can discriminate certain cell types. </p> <p>In this competition setup, participants were tasked with modelling differential expression (DE), which enables us to estimate the impact of an experimental perturbation on the expression level of every gene in the transcription (18211 genes in this dataset). The Limma model was used to determine ‘differential expression’ (DE) methods for biological data analysis in this dataset.</p> <p>The cell type proportion differs in PBMCs treated with different compounds and would therefore have different differential gene expression. For example T cells have a very distinct gene expression profile (i.e express CD3E) compared to B cells (CD79a, MSA41) and Myeloid cells (CD14, FCGR3A(CD16)). Also T cell sub-types also express differences, for example Regulatory T cells are classified by the expression of FOXP3, IL2RA and CTLA4 and Cytotoxic CD8 T cells are enriched in cytotoxic-related genes including GNLY, CCL5, NKG7, GZMH, LYZ, GZMB, and GZMK. CD4 T cells will express the CD4 gene whereas CD8 T cells will express CD8A and CD8B genes. Typically in single cell analysis the result is displayed as TSNE or UMAP plot showing distinct clusters with ideally one cell type and marker plots and DGE analysis can be used to confirm cell types such as in the following paper (<a href="https://pubmed.ncbi.nlm.nih.gov/34911770/" target="_blank">https://pubmed.ncbi.nlm.nih.gov/34911770/</a>)</p> <p>The following paper shows the combined protein and transcript analysis of single-cell RNA sequencing in human peripheral blood mononuclear cells (<a href="https://bmcbiol.biomedcentral.com/articles/10.1186/s12915-022-01382-4" target="_blank">https://bmcbiol.biomedcentral.com/articles/10.1186/s12915-022-01382-4</a>)</p> <p>Supervised ensemble classification models are popular among bioinformatics applications and have recently seen their increasing integration with deep learning models. Ensemble feature selection methods, typically, rely on either perturbation to the dataset or hyperparameters of the feature selection algorithms for creating ‘base selectors’ from which the ensemble could be derived. Generally, hybrid methods are motivated by the aim of taking advantage of the strengths of individual methods while alleviating or avoiding their weaknesses.</p> <p>Model design:</p> <p>I tried a number of approaches for the ML model and found that ensembeling models gave the best approach as described in section 2 of exploration of the problem. I used a combination of blends and ridge models. Selection of certain cell types such as B cells, T regulatory cells and NK cells did help improve the model and including CD8 T cells gave a worse score.</p> <p>I used the features "cell_type" and "sm_name" and used certain a 'cell_type' with a selection of compounds that will have similar responses on each of these cell divisions. </p> <p>RMSE was calculated for each line and then to select the best model for each compound there were two submissions for every line that has RMSE >1</p> <p>I experimented with a number of blends and I would like to acknowledge the following notebooks from the following participants:<br> -Daphne Anga <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/457081" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/discussion/457081</a><br> -Mehran Kazeminia, Somayyeh Gholami <a href="https://www.kaggle.com/code/mehrankazeminia/3-op2-feature-augment-fragments-of-smiles" target="_blank">https://www.kaggle.com/code/mehrankazeminia/3-op2-feature-augment-fragments-of-smiles</a></p> <p>For including the Ridge model thanks to AMBROSM and MT for the following:<br> <a href="https://www.kaggle.com/code/masato114/scp-quickstart-another-cv-strategy/notebook" target="_blank">https://www.kaggle.com/code/masato114/scp-quickstart-another-cv-strategy/notebook</a></p> <p>Robustness:<br> When using the cross-validation it did help in improving the robustness of the model in this competition and could help with over fitting. I included the cross-validation strategy that makes four folds.</p> <p>Documentation, Code and Reproducibility:<br> Please see the Kaggle link to my approach below.<br> <a href="https://www.kaggle.com/code/insiyajafferji/code-178th-priv-pub-0-759-0-531" target="_blank">https://www.kaggle.com/code/insiyajafferji/code-178th-priv-pub-0-759-0-531</a></p>
Open Problems – Single-Cell Perturbations	3rd Place Solution for the Open Problems – Single-Cell Perturbations	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><h1>1. Integration of Biological Knowledge</h1> <p>Generally, I treated this problem as a regression with 2 feature columns and 18211 targets, but I had tried to utilize SMILES sequences in neural network with LSTM unit. Both the sm_name and SMILES columns can be encoded exactly in the same way, so the sm_name column can be replaced with the SMILES column. Moreover, SMILES column is more informative, because every single character of the sequence can be encoded (not only a single value like in sm_name) and the order of these characters provides extra information. Theoretically, In the worst case, the performance of the neural network using SMILES column instead of sn_name should be not worse than using original columns. Unfortunate, I have reached an unsatisfactory public score with this neural network and I stopped further research. </p> <h1>2. Exploration of the problem</h1> <p>For simplicity, the analysis is done for the single best model without pseudolabeling. Since mrrmse metric is sensitive to outliers, a distribution of ranges for columns should be checked.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6882624%2F523b491c0054eae38b031b945b7eb168%2FScreenshot%20from%202023-12-05%2009-36-00.png?generation=1701849069283853&alt=media" alt=""><br> The majority of columns have a range of values in an interval (4, 50). Naturally, the columns with high range lead to high mae or mse, so in order to determine genes which are easy and hard to predict, the standardized (divided by std) colwise mse is applied. The table below shows the hardest and easiest genes for prediction.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6882624%2Fd8bf3ee03e6d6154593170a5db43cab3%2FScreenshot%20from%202023-12-05%2009-45-05.png?generation=1701849594906441&alt=media" alt=""><br> The scheme of the applied cross validation. Every fold contains one cell type chosen from NK cells, T cells CD4+, T cells CD8+, T regulatory cells and only sm_names being in public and private test was involved. The lowest value of this validation split corresponds to the lowest value on public and private dataset. In my opinion this is a reliable split and the perfect split depends on the model architecture, so every model can have its perfect validation split. <br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6882624%2Fb4a580c8349343ab853a40cf6ee8b43e%2FScreenshot%20from%202023-12-05%2009-49-01.png?generation=1701849988973830&alt=media" alt=""><br> The easiness of learning per cell types is shown below. <br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6882624%2F64d7f90af54659c0e8477d4faa3a3c51%2FScreenshot%20from%202023-12-05%2009-56-05.png?generation=1701850210915961&alt=media" alt=""><br> The values of loss are different, because they are calculated in truncated space. T cells CD4+ and NK cells are learning well. T regulatory cells are harder for training. The T cells CD8 are weakly improving on validation dataset. This split uses about 25% of the dataset for validation, so I believe more reliable splits exist. My new proposition of split is: <br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6882624%2F718b580e65a5654a92880f8a6bcf6d1b%2FScreenshot%20from%202023-12-05%2010-08-16.png?generation=1701850452329548&alt=media" alt=""><br> This split is similar to the previous one, but for each validation fold, randomly selected examples are moved to training. Let's check an impact of the new split for training. <br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6882624%2F8a68fc6a4b3025b48d37dabc67a50c05%2FScreenshot%20from%202023-12-05%2010-12-19.png?generation=1701850788086187&alt=media" alt=""><br> For each cell type, more data improved performance on this same, constant and small validation set. Metric is calculated on full dimension this time. The first value at 480 training examples corresponds to the previous split. Theoretically, decreasing the size of validation set to one example can lead to the best performance. Since it will be very similar to training on whole dataset, what is done finally.</p> <h1>3. Model design</h1> <h2>Solution</h2> <p>The prediction system is two staged, so I publish two versions of the notebook. <br> The first stage predicts pseudolabels. To be honest, if I stopped on this version, I would not be the third. <br> The predicted pseudolabels on all test data (255 rows) are added to training in the second stage.</p> <h3>Stage 1 preparing pseudolabels</h3> <p>The main part of this system is a neural network. Every neural network and its environment was optimized by optuna. Hyperparameters that have been optimized:<br> a dropout value, a number of neurons in particular layers, an output dimension of an embedding layer, a number of epochs, a learning rate, a batch size, a number of dimension of truncated singular value decomposition.<br> The optimization was done on custom 4-folds cross validation. In order to avoid overfitting to cross validation by optuna I applied 2 repeats for every fold and took an average. Generally, the more, the better. The optuna's criterion was MRRMSE. <br> Finally, 7 models were ensembled. Optuna was applied again to determine best weights of linear combination. The prediction of test set is the pseudolabels now and will be used in second stage.</p> <h3>Stage 2 retraining with pseudolabels</h3> <p>The pseudolabels (255 rows) were added to the training dataset. I applied 20 models with optimized parameters in different experiments for a model diversity.<br> Optuna selected optimal weights for the linear combination of the prediction again.<br> Models had high variance, so every model was trained 10 times on all dataset and the median of prediction is taken as a final prediction. The prediction was additionally clipped to colwise min and max. </p> <p><strong>History of improvements:</strong></p> <ol> <li>a replacing onehot encoding with an embedding layer</li> <li>a replacing MAE loss with MRRMSE loss</li> <li>an ensembing of models with mean</li> <li>a dimension reduction with truncated singular value decomposition</li> <li>an ensembling of models with weighted mean</li> <li>using pseudolabeling</li> <li>using pseudolabeling and ensembling of 20 models and weighted mean. </li> </ol> <p><strong>What did not work for me</strong>:</p> <ul> <li>a label normalization, standardization</li> <li>a chained regression</li> <li>a denoising dataset</li> <li>a removal of outliers</li> <li>an adding noise to labels</li> <li>a training on selected easy / hard to predict columns</li> <li>a huber loss.</li> </ul> <h1>4. Robustness</h1> <p>I have tested 3 types of the robustness: increasing dataset size, adding noise to labels and inputs. Adding the noise to inputs failed totally, it is logical for me, because the nominal and categorical values are changed and are behaving like the continues values, what is not beneficial.<br> Let's see the performance on 40%, 50%,…, 100% of training dataset. It started from 40%, because singular values decomposition is limited by number of examples.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6882624%2Fb684812f2feb70c2b9f28f2df5714cd7%2FScreenshot%20from%202023-12-05%2013-11-10.png?generation=1701852018611279&alt=media" alt=""><br> The experiment was 5 times repeated, so the interval of uncertainty is visible. More data improves the performance significantly. <br> The last test of robustness is adding noise to the labels. The random gaussian (a distribution with 0 mean and scale * std) noise was added to the labels.<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6882624%2F8625a5cb1af874f4986277c98e76ab8e%2FScreenshot%20from%202023-12-05%2011-45-22.png?generation=1701852528532795&alt=media" alt=""><br> Adding some noise (0.01 * std) can even improve the model's performance. Generally, the model is robust to the noise. </p> <h1>5. Documentation & code style</h1> <p>The code on GitHub is documented. </p> <h1>6. Reproducibility</h1> <p>GitHub code:<br> <a href="https://github.com/okon2000/single_cell_perturbations" target="_blank">repo</a><br> Notebook. The version 264 is first a stage and 266 the second one:<br> <a href="https://www.kaggle.com/code/jankowalski2000/3rd-place-solution" target="_blank">notebook</a>.</p> <p>The code runs in approximately 1 hour using CPU Intel(R) Core(TM) i5-9300H CPU @ 2.40GHz and 8GB RAM.</p>
Open Problems – Single-Cell Perturbations	Kaggle Solution Write-up	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>import pandas as pd<br> import numpy as np</p> <p>df1 = pd.read_csv("/kaggle/input/open-problems-single-cell-perturbations/sample_submission.csv")</p> <p>df1.to_csv("submission.csv", index=False)</p>
Child Mind Institute - Detect Sleep States	1790th Place Solution - code details, attempts and insights	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Child Mind Institute - Detect Sleep States <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>Hello fellow Kagglers,</p> <p>Firstly, I would like to congratulate all the winners and participants of the recently concluded Child Mind Institute - Detect Sleep States Competition. Although my result was in the "top 96%", which isn't quite where I had hoped, I wanted to share my solution and the insights I gained throughout the competition. My aim is to contribute to the community and hopefully offer some insights for other newcomers.</p> <p><strong>Context</strong></p> <ul> <li>Business context: <a href="https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states" target="_blank">https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states</a></li> <li>Data context: <a href="https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/data" target="_blank">https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/data</a></li> </ul> <p><strong>Overview of the approach</strong></p> <ul> <li>Target<ul> <li>classification of 4-class events<ul> <li>Awake, Sleep (negative when submitted)</li> <li>Onset, Wakeup (positive when submitted)</li></ul></li></ul></li> <li>Features<ul> <li>enmo, anglez: as default</li> <li>shift_anglez: lagged feature varied from anglez to capture time-series data characteristics (step=1)</li> <li>hour_sin, hour_cos: cycled features varied from timesteps</li></ul></li> <li>Training method: LightGBM</li> <li>Validation：Hold-out<ul> <li>train, valid = 221, 56</li></ul></li> <li>Evaluation<ul> <li>AP (LB score: 0.004)</li></ul></li> </ul> <p><strong>Details of the submission</strong><br> All parts of the code are open in the following notebooks so feel free to refer to them:<br> * Dataset: <a href="https://www.kaggle.com/datasets/coyamax/cmi-anglezlag" target="_blank">https://www.kaggle.com/datasets/coyamax/cmi-anglezlag</a><br> * Training model and validation: <a href="https://www.kaggle.com/code/coyamax/fork-of-cmi-train2-11?kernelSessionId=153365353" target="_blank">https://www.kaggle.com/code/coyamax/fork-of-cmi-train2-11?kernelSessionId=153365353</a><br> * Inference: <a href="https://www.kaggle.com/code/coyamax/cmi-infer-final?kernelSessionId=153746953" target="_blank">https://www.kaggle.com/code/coyamax/cmi-infer-final?kernelSessionId=153746953</a></p> <p><strong>Attempts and insights</strong><br> Lagged features: </p> <ul> <li>lagged features derived from anglez and enmo (shift_anglez and shift_enmo, respectively) have different impacts on scores; shift_anglez leads better results than shift_enmo and both of two used together.<ul> <li>Only shift_anglez used: 0.004</li> <li>Only shift_enmo used: 0.003</li> <li>Both of shitf_anglez and shift_enmo used: 0.002</li></ul></li> <li>The result may suggest using more features derived from anglez is more effective than those from enmo if computational resources are limited.<br> [Feature importance of features at the same time]<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F11605610%2F04fc8780b328d777d9575cb0dac2543e%2Ff_imp.jpg?generation=1701835769332359&alt=media" alt=""></li> </ul> <p>Post-process:</p> <ul> <li>The model predicts four labels, awake (the state of not sleeping), sleep (the state of sleeping), onset (when the state of sleeping begins), and wakeup (when the state of sleeping ends).</li> <li>Final submission only uses the predictions of onset and wakeup directly, by extracting the peaks of prediction scores for each series id.</li> <li>In the development process, I also hypothesized the predicted results of awake and sleep may be the key to predict onset and wakeup; valleys of prediction scores (near 0, in other words) of awake and sleep correspond to the steps of onset and wakeup, respectively. However, it turns out detecting score valleys of awake and sleep don’t have significant effect on predicting positive labels compared to detecting the score peaks of wakeup and onset, which ends up with LB score 0.</li> <li>It concludes that simple peak detection on the onset/wakeup scores performs better in my case.<br> [Prediction scores of awake for 3 samples of series ids]<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F11605610%2F5be8559d565383751d601c4eec60dd66%2Fawake.png?generation=1701835788873540&alt=media" alt=""><br> [Prediction scores of sleep for 3 samples of series ids]<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F11605610%2Fee640d2040c9f10ea95736f2757496e0%2Fsleep.png?generation=1701835824555093&alt=media" alt=""></li> </ul> <p><strong>Sources</strong></p> <ul> <li><a href="https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/discussion/452940" target="_blank">https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/discussion/452940</a></li> </ul>
Stanford Ribonanza RNA Folding	403rd Place Solution for the Stanford Ribonanza RNA Folding Competition	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Stanford Ribonanza RNA Folding <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>Thank you to the organizers and Kaggle for hosting such a great competition.<br> I value everyone's sharing at Kaggle. <br> The public notebook provided by SWORDSMAN is amazing and I am thankful for it <a href="https://www.kaggle.com/code/liuyanfeng/stanford-rrf-tensorflow-tpu?scriptVersionId=150578739" target="_blank">https://www.kaggle.com/code/liuyanfeng/stanford-rrf-tensorflow-tpu?scriptVersionId=150578739</a>. 感谢您创建笔记本.</p> <h1>Context</h1> <p>Business context: <a href="https://www.kaggle.com/competitions/stanford-ribonanza-rna-folding/overview" target="_blank">https://www.kaggle.com/competitions/stanford-ribonanza-rna-folding/overview</a><br> Data context: <a href="https://www.kaggle.com/competitions/stanford-ribonanza-rna-folding/data" target="_blank">https://www.kaggle.com/competitions/stanford-ribonanza-rna-folding/data</a></p> <h1>Overview of the approach</h1> <p>The SN_filter is set to 1 the signal_to_noise>1.0 and reads > 100.<br> Two files for training experiments with DMS_MaP and 2A3_MaP.<br> Repeat dataset 5 time.</p> <h1>Described the models or algorithms used</h1> <p>Tensorflow keras RNN with Attention.</p> <table> <thead> <tr> <th>Public LB</th> <th>Private LB</th> </tr> </thead> <tbody> <tr> <td>0.15803</td> <td>0.24428</td> </tr> </tbody> </table> <p>Attention 8 heads.<br> 6 layers.</p> <p>GaussianNoise 0.01.<br> Dense 400 relu.<br> GaussianNoise 0.01.<br> Dense 40 relu.<br> Dense 2.</p> <h4>RNN Model:</h4> <table> <thead> <tr> <th>Layer type</th> <th>Output Shape</th> </tr> </thead> <tbody> <tr> <td>PositionalEmbedding</td> <td>990</td> </tr> <tr> <td>EncoderLayer</td> <td>1458968</td> </tr> <tr> <td>EncoderLayer</td> <td>1458968</td> </tr> <tr> <td>EncoderLayer</td> <td>1458968</td> </tr> <tr> <td>EncoderLayer</td> <td>1458968</td> </tr> <tr> <td>EncoderLayer</td> <td>1458968</td> </tr> <tr> <td>EncoderLayer</td> <td>1458968</td> </tr> <tr> <td>Dropout</td> <td>0</td> </tr> <tr> <td>Dense</td> <td>79600</td> </tr> <tr> <td>Dense</td> <td>16040</td> </tr> <tr> <td>Dense</td> <td>82</td> </tr> <tr> <td>GaussianNoise</td> <td>0</td> </tr> <tr> <td>GaussianNoise</td> <td>0</td> </tr> </tbody> </table> <p>Params: 8,850,520</p> <h1>Described the data preprocessing, feature engineering, and/or feature selection strategy</h1> <p>Encoding sin and cos.<br> Embedding 2048.</p> <h1>Details of the submission</h1> <p>What work:<br> A Custom Loss Function hat take two arguments: target value and predicted value Sum 0 / Sum 1,0.<br> Epoch 0 Lr 0.0005. Epoch 1-60 Lr is calculated by multiplying Lr by 0.904.</p> <h1>Preventing overfitting and Validation Strategy</h1> <p>KFold.</p> <p>Values outside the interval 0 1 are clipped.</p> <h1>Code samples</h1> <p>Source public notebook <a href="https://www.kaggle.com/code/liuyanfeng/stanford-rrf-tensorflow-tpu?scriptVersionId=150578739" target="_blank">https://www.kaggle.com/code/liuyanfeng/stanford-rrf-tensorflow-tpu?scriptVersionId=150578739</a></p> <h4>Code samples prepare dataset</h4> <pre><code> n (): df = df_c.get_chunk() df = df[df[] > ] df_DMS_MaP = df[df[] == ] df_2A3_MaP = df[df[] == ] delete_list = [] k df.columns: k k: delete_list.append(k) df_DMS_MaP = df_DMS_MaP.drop(delete_list, axis=) df_2A3_MaP = df_2A3_MaP.drop(delete_list, axis=) n == : df_DMS_MaP.to_csv(+train_file, header=df_DMS_MaP.keys() ,index=) df_2A3_MaP.to_csv(+train_file, header=df_2A3_MaP.keys() ,index=) : df_DMS_MaP.to_csv(+train_file, mode=, header=,index=) df_2A3_MaP.to_csv(+train_file, mode=, header=,index=) </code></pre> <h4>Code samples demonstrating model training</h4> <pre><code> GlobalSelfAttention( num_heads=num_heads, key_dim=d_model, dropout=dropout_rate) </code></pre> <pre><code> x = self.pos_embedding(x) x = tf.keras.layers.Dropout(dropout_rate)(x) x = GlobalSelfAttention( num_heads=num_heads, key_dim=d_model, dropout=dropout_rate)(x) x = FeedForward(d_model, dff)(x) x = tf.keras.layers.GaussianNoise(stddev=)(x) x1 = tf.keras.layers.Dense(, activation=)(x) x1 = tf.keras.layers.GaussianNoise(stddev=)(x1) x1 = tf.keras.layers.Dense(,activation=)(x1) o1 = tf.keras.layers.Dense()(x1) </code></pre> <h4>Code samples model inference</h4> <p>Predict two chemical modifiers DMS Y[:,1] and 2A3 Y[:,0].</p> <pre><code> Y = model.predict( np.array(test_df.loc[spang_i:span(g_i+)-,].to_list()).astype() ) np.clip(Y,,) </code></pre> <h1>Sources</h1> <p><a href="https://www.kaggle.com/code/liuyanfeng/stanford-rrf-tensorflow-tpu?scriptVersionId=150578739" target="_blank">https://www.kaggle.com/code/liuyanfeng/stanford-rrf-tensorflow-tpu?scriptVersionId=150578739</a><br> <a href="https://www.kaggle.com/code/misakimatsutomo/stanford-rrf-tensorflow-tpu/edit/run/153311838" target="_blank">https://www.kaggle.com/code/misakimatsutomo/stanford-rrf-tensorflow-tpu/edit/run/153311838</a></p> <p>Thank you for taking the time to read the writeup.</p>
NeurIPS 2023 - Machine Unlearning	From top 50 to 800th place	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: NeurIPS 2023 - Machine Unlearning <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>This was definitely a great experience, a bittersweet one because of the final standings but great nonetheless. I have open source the <a href="https://github.com/luispintoc/machine-unlearning" target="_blank">repo</a> with all the different approaches we tried, includes a combination of:</p> <ul> <li>Retrain on retain set</li> <li>Gradient ascent on forget set</li> <li>Add noise</li> <li>Reset layers</li> <li>Pruning</li> <li>KL loss (e.g. SCRUBS)</li> <li>GANs (train a discriminator on differentiating retain/val loss)</li> <li>Contrastive learning</li> <li>Perturb weights guided by the gradient (SSD paper and variations)</li> <li>Reduce retain set to remove images with embeddings closer to forget set images</li> <li>Label poisoning</li> </ul> <p>Moreover, we trained a model from scratch on a downsampled version of CIFAR, with the same distribution as the competition dataset.</p> <p>Our <a href="https://www.kaggle.com/code/luispintoc/pruning-forget-and-retrain" target="_blank">final submission</a> consisted on:</p> <ul> <li>Pruning the model</li> <li>Adding a small noise to the fc</li> <li>Within one epoch, and using warmup: first 10% retrain, then for every forget batch retrain with X batches and finalize the epoch with only retrain.</li> </ul> <p>I believe our mistake was using CIFAR to test our approaches, where we found that using 1 epoch was enough and almost never tried more epochs (now that I see everyone's solutions, I can confirm that more epochs was indeed needed). Most likely the reason 1 epoch was enough for CIFAR, as mentioned in one of the discussion threads, is that the model is already overfitting to the data, which is not the case for the competition dataset (i.e. need for more epochs).</p> <p>PS: We'll be at NeurIPS if anyone wants to chat</p>
Google - Fast or Slow? Predict AI Model Runtime	2nd Place Solution for the Google - Fast or Slow? Predict AI Model Runtime Competition	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Google - Fast or Slow? Predict AI Model Runtime <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>We express our gratitude to Kaggle as well as Google’s TPU team for organizing this remarkable challenge.</p> <p>The code of the solution is available on <a href="https://github.com/Obs01ete/kaggle_latenciaga/tree/master" target="_blank">Github: Fast or Slow by Latenciaga</a>.</p> <h2>Introduction</h2> <p>Our implementation is a SageConv-based graph neural network (GNN) operating on whole graphs and trained in PyTorch/PyTorch-Geometric. The GNN was trained with the help of one or two losses, including a novel DiffMat loss, which we will discuss later.</p> <h2>Dataset preprocessing</h2> <p>We preprocess data from all 5 subsets by removing duplicates by config. We discovered that for each graph, several instances of configurations (all node-wise concatenated together for Layout and subgraph for Tile) are identical, while the corresponding runtimes are different with a 0.4% max-to-min difference. We reduce these groups by a minimum. For Layout-XLA, we filtered out all Unet graphs since we identified that <code>unet_3d.4x4.bf16</code> is badly corrupted. For the same reason, we removed <code>mlperf_bert_batch_24_2x2</code> from Layout-XLA-Default validation to improve the stability of the validation. We identified many other graphs whose data is seemingly corrupted, but we did not filter them out. As a part of preprocessing, we repack the NPZs for Layout so that for each graph, each config+runtime measurement (out of 100k or less) can be loaded from NPZ individually without loading the entire NPZ. With this repacking, thanks to lazy loading, random reads were accelerated 5-10 times, resulting in a similar reduction of training wall clock time, whereas the training became GPU-bound instead of data-loading bound.</p> <h2>Model</h2> <p>We train 5 models from scratch, one for each subset, applying different hyperparameters as summarized in the table below. All GNN layers are SageConv layers with residual connections whenever the number of input and output channels are the same.</p> <table> <thead> <tr> <th>subsets</th> <th>layers x channels</th> <th># parameters</th> </tr> </thead> <tbody> <tr> <td>Layout-XLA</td> <td>2x64 + 2x128 + 2x256</td> <td>270k</td> </tr> <tr> <td>Layout-NLP & Tile</td> <td>4x256 + 4x512</td> <td>2.3M</td> </tr> </tbody> </table> <p><br></p> <p>The node types are embedded into 12 dimensions. Node features are compressed with <code>sign(x)*log(abs(x))</code> and shaped into 20 dimensions by a linear layer. For Layout, the configs are not transformed; for Tile, the graph configuration is broadcast to all nodes. We apply early fusion by combining the three above into a single feature vector before passing it to GNN layers. Features produced by the GNN layer stack are transformed to one value per node and then sum-reduced to form a single graph-wise prediction. </p> <h2>Training procedure</h2> <p>We follow training and validation splits provided by the competition authors. For all 5 subsets, the training was only performed on a training split.</p> <p>The batch is organized into 2 levels of hierarchy: the upper level is different graphs, and the lower level is the same graph and different configurations, grouped in microbatches of the same size (also known as slates). This procedure allows applying ranking loss to the group of samples within a microbatch. We found that using some sort of ranking loss is essential for the score. Models trained with a ranking loss (ListMLE, MarginRankingLoss) heavily outperformed element-wise losses (MAPE, etc). </p> <table> <thead> <tr> <th>hyperparameter</th> <th>Tile subset</th> <th>Layout- XLA-Random</th> <th>Layout- XLA-Default</th> <th>Layout- NLP-Random</th> <th>Layout- NLP-Default</th> </tr> </thead> <tbody> <tr> <td>microbatch size</td> <td>10</td> <td>4</td> <td>4</td> <td>10</td> <td>10</td> </tr> <tr> <td>number of microbatches in a batch</td> <td>100</td> <td>10</td> <td>10</td> <td>4</td> <td>4</td> </tr> <tr> <td>batch size</td> <td>1000</td> <td>40</td> <td>40</td> <td>40</td> <td>40</td> </tr> </tbody> </table> <p><br></p> <p>The following hyperparameters were set:</p> <ol> <li>Adam/AdamW optimizer,</li> <li>Learning rate 1e-3,</li> <li>400k iterations,</li> <li>Step learning rate scheduler at 240k, 280k, 320k, and 360k by factor of <code>1/sqrt(10)</code>.</li> </ol> <p>Training time is approximately 20 hours on A100 for each of 5 subsets. No early stopping was employed. All snapshots for submission were taken from the 400k-th iteration.</p> <p>Losses used for training:</p> <ol> <li>ListMLE for Layout-NLP,</li> <li>A novel DiffMat loss for Tile,</li> <li>For Layout-XLA, it is a combination of 2 losses: the DiffMat loss and MAPE loss.</li> </ol> <p>For ListMLE loss, we used prediction norm-clipping to avoid numerical instability resulting from dividing a big number by a big number. We do not use prediction L2 normalization before ListMLE loss since we find it damages the score.</p> <p>The novel DiffMat loss is described with the following algorithm. Within a microbatch, a full antisymmetric matrix of pairwise differences is constructed for the predictions and for the targets. The upper triangular matrix is taken from the difference matrix and flattened. Margin Ranking Loss with a margin of 0.01 is applied between predicted values and zeros. This novel loss, combined with MAPE loss, consistently outperformed ListMLE on XLA.</p> <p><img src="https://raw.githubusercontent.com/Obs01ete/latenciaga_materials/191000e669012bb9d8cae52a309d73ac4d9a57a7/assets/diffmat.png" alt="difffmat"></p> <h2>Remarks on the validation (CV) stability</h2> <p>We found Kendall tau on the validation splits extremely unstable for XLA Random and Default since the dataset is relatively small, and there is a significant domain gap between train and validation, and presumably test. Repeats of training results in up to 13 percentage points of difference between outcomes. </p> <h2>Experiments that did not work</h2> <h3>Data filtration</h3> <p>Some graphs’ data is badly damaged. For example, <code>magenta_dynamic</code> has the following rollout of runtimes vs config ID. In no way can these be measurements from the same graph. </p> <p><img src="https://raw.githubusercontent.com/Obs01ete/latenciaga_materials/main/assets/damaged1.png" alt=""></p> <p>Below are other examples where we are unsure about the conditions in which these measurements were performed.</p> <p><img src="https://raw.githubusercontent.com/Obs01ete/latenciaga_materials/main/assets/damaged2.png" alt=""><br> <img src="https://raw.githubusercontent.com/Obs01ete/latenciaga_materials/main/assets/damaged3.png" alt=""></p> <p>Nevertheless, we do not filter out these graphs and others since we could not reliably observe the improvement from their removal due to the earlier mentioned instability of validation Kendall numbers.</p> <h3>Data recovery</h3> <p>We tried to find the damaged data and remove it in an automatic manner by computing block-wise entropy of the runtimes between adjacent blocks. While the detection seems to work visually, we observed a negative impact on the score and did not proceed with this feature.</p> <p>Example 1:</p> <p><img src="https://raw.githubusercontent.com/Obs01ete/latenciaga_materials/main/assets/entropy1.png" alt="link"></p> <p>Example 2:</p> <p><img src="https://raw.githubusercontent.com/Obs01ete/latenciaga_materials/main/assets/entropy2.png" alt="link"></p> <p>Before and after entropy filtration:</p> <p><img src="https://raw.githubusercontent.com/Obs01ete/latenciaga_materials/main/assets/entropy3.png" alt="link"></p> <h3>Other experiments we tried that did NOT work:</h3> <ol> <li>GATv2Conv, GATv2 backbone, GINEConv,</li> <li>Dropout,</li> <li>Training on merged Random and Default - hurts both,</li> <li>Adding reverse edges,</li> <li>Online hard negative mining (OHEM) - did not help since train loss is nowhere near zero,</li> <li>Train blindly on the merged train and valid (trainval),</li> <li>Train 4 folds and merge by mean latency and by mean reciprocal rank (MRR),</li> <li>Periodic LR schedule.</li> </ol> <h2>Conclusion</h2> <p>We found Google Fast or Slow to be a great competition, and we enjoyed it a lot, along with learning many new things, especially ranking losses.</p> <p>Partially inspired by this competition, Dmitrii published an article <a href="https://pub.towardsai.net/ten-patterns-and-antipatterns-of-deep-learning-experimentation-e91bb0f6feda" target="_blank">Ten Patterns and Antipatterns of Deep Learning Experimentation</a> at Towards AI.</p>
Open Problems – Single-Cell Perturbations	... & I'd like to thank Kaggle, the challenge host, and everyone who made their notebooks public.	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>The prediction in this competition included more than eighteen thousand columns, which may have less history in machine learning competitions, while the number of features was also very limited. These themes made every detail seem very important. Even regardless of the result of the match, it was definitely a good experience for us.</p> <p>In this challenge, there are only two features, namely "cell_type" and "sm_name". That's why we used "Feature Augmentation". We added two new columns (two new features) separately for each prediction column as follows:</p> <p>If we separate the cells based on 'cell_type' and assume that the drugs will usually have similar responses on each of these divisions, we can hope that by finding the average effects, we have obtained a new feature. For example, for y0 and the new feature of zero column, the correlation coefficient is 0.24. Of course, this amount is repeated for other columns as well.</p> <p>Also, if we separate the cells based on 'sm_name', we get a new feature by finding the average effects. In this case, for y0 and the new feature of column zero, the correlation coefficient is 0.62, and this value is almost repeated for other columns.</p> <p>In addition, we added other features by using "SMILES", which were used for all prediction columns at the same time. At first, we added about five hundred binary features using "fragments of SMILES" and then we added about two thousand new binary features using "morgan fingerprint from SMILES".</p> <p>We have publicly released two notebooks that cover the above topicss:</p> <p><a href="https://www.kaggle.com/code/mehrankazeminia/1-op2-eda-linearsvr-regressorchain" target="_blank">https://www.kaggle.com/code/mehrankazeminia/1-op2-eda-linearsvr-regressorchain</a></p> <p><a href="https://www.kaggle.com/code/mehrankazeminia/3-op2-feature-augment-fragments-of-smiles" target="_blank">https://www.kaggle.com/code/mehrankazeminia/3-op2-feature-augment-fragments-of-smiles</a></p> <p>Finally, the results of LinearSVR and neural network and NLP and PYBOOST were combined and we used "Separately Ensembling for Each Column". That is, Ensembling was done with different coefficients (based on the correlation value).</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4288268%2Ffc0fcd5fe67f70542c4e5409a76b81ad%2Fphoto_2023-12-03_01-15-24.jpg?generation=1701553548981440&alt=media" alt=""></p>
Open Problems – Single-Cell Perturbations	118th Place Solution for the Open Problems – Single-Cell Perturbations Competition draft	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>I would like to express gratitude to Kaggle for hosting the competition and Open Problems in Single-Cell Analysis scientific collaboration for a single-cell perturbational dataset and for select 144 compounds from the Library of Integrated Network-Based Cellular Signatures (LINCS) Connectivity Map dataset (<a href="https://pubmed.ncbi.nlm.nih.gov/29195078/" target="_blank">PMID: 29195078</a>) <a href="https://www.cell.com/action/showPdf?pii=S0092-8674%2817%2931309-0" target="_blank"> L1000</a></p> <h1>1. Integration of biological knowledge</h1> <h2>Context</h2> <p>• Business context: <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/overview</a><br> • Data context: <a href="https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/data" target="_blank">https://www.kaggle.com/competitions/open-problems-single-cell-perturbations/data</a></p> <h1>2. Exploration of the problem</h1> <p><a href="https://ru.wikipedia.org/wiki/%D0%9A%D0%BE%D0%BB%D0%B8%D1%87%D0%B5%D1%81%D1%82%D0%B2%D0%B5%D0%BD%D0%BD%D1%8B%D0%B9_%D0%B0%D0%BD%D0%B0%D0%BB%D0%B8%D0%B7_%D1%8D%D0%BA%D1%81%D0%BF%D1%80%D0%B5%D1%81%D1%81%D0%B8%D0%B8_%D0%B3%D0%B5%D0%BD%D0%BE%D0%B2" target="_blank">Gene expression profiling</a></p> <p>The wiki contains models such as the Generalized Linear Model, which is used by the … place :</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16791068%2F3e1cc01e2e176b1984ddebf6537d029b%2FIMG_20231220_155835.jpg?generation=1703080145948652&alt=media"></p> <p>Train</p> <table> <thead> <tr> <th>Compound</th> <th>Gene 0</th> <th>1</th> <th>..</th> <th>18 211</th> </tr> </thead> <tbody> <tr> <td>1, ABT-199 (GDC-0199)</td> <td>2547</td> <td>2006</td> <td>..</td> <td>3387</td> </tr> <tr> <td>2, ABT737</td> <td>780</td> <td>381</td> <td>..</td> <td>2093</td> </tr> <tr> <td>3, AMD-070 (hydrochloride)</td> <td>3335</td> <td>3424</td> <td>..</td> <td>1355</td> </tr> <tr> <td>..</td> <td>..</td> <td>..</td> <td>..</td> <td>..</td> </tr> <tr> <td>613,Myeloid cells,YK 4-279</td> <td>3373</td> <td>1433</td> <td>..</td> <td>1618</td> </tr> </tbody> </table> <p>Inference</p> <table> <thead> <tr> <th>Compound</th> <th>Gene 0</th> <th>1</th> <th>..</th> <th>18 211</th> </tr> </thead> <tbody> <tr> <td>254,Myeloid cells,YK 4-279</td> <td>?</td> <td>?</td> <td>?</td> <td>?</td> </tr> </tbody> </table> <p>Predict: signed -log10(p-values)</p> <h1>3. Model design</h1> <p>3.1 Gene order model<br> 3.2 Plot line model<br> 3.3 Marker point on plot model<br> 3.4 Multiplier model</p> <h3>3.1 Gene order model</h3> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16791068%2F66047a0cc4015b2b6e3280bf543d6a68%2F2023-12-20%20%2015.34.41.png?generation=1703075796711416&alt=media"></p> <p>Search Queries: 19,B cell, BMS-387032<br> Search Results: </p> <table> <thead> <tr> <th>Gene</th> <th>Rank 0 .. 18 211</th> </tr> </thead> <tbody> <tr> <td>AL1173282</td> <td>2547</td> </tr> <tr> <td>AC2397982</td> <td>2006</td> </tr> <tr> <td>AC0118992</td> <td>682</td> </tr> <tr> <td>AP0056711</td> <td>3470</td> </tr> <tr> <td>…</td> <td>…</td> </tr> <tr> <td>ACAP1</td> <td>2072</td> </tr> <tr> <td>ARHGAP15</td> <td>3590</td> </tr> </tbody> </table> <p>Predict rank. Not predict value.</p> <h3>3.2 Plot line model</h3> <p>Curve class prediction Attachments compound.pdf :</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16791068%2F59437c342447b7260b22e2020552a7b0%2F2023-12-20%20%2018.47.27.png?generation=1703088550144370&alt=media"></p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16791068%2F9f5120b3fbb36e68e40ac8feef6dfa0e%2F2023-12-20%20%2018.45.03.png?generation=1703088579086403&alt=media"></p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16791068%2Fc043c2cd488217adf1a1fabb95f71dbe%2F2023-12-20%20%2018.40.33.png?generation=1703088612243004&alt=media"></p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16791068%2F805ea55569935020bf6bb5a1e68b03b6%2F2023-12-20%20%2018.53.40.png?generation=1703088628570177&alt=media"></p> <h3>3.3 Multiplier model</h3> <p>Predict point:</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16791068%2F859c65d626ecc5312a34953294675b9a%2F2023-12-20%20%2019.11.37.png?generation=1703089042788063&alt=media"></p> <p>Predict R for points.</p> <h3>3.4 Multiplier model</h3> <p>Predict zoom:<br> Magic of 4th place:</p> <p>Examine the multiplier coefficient in the attachments: Multiplier.xlsx</p> <table> <thead> <tr> <th>Gene</th> <th>Cell</th> <th>Multiplier</th> </tr> </thead> <tbody> <tr> <td>BMS-387032</td> <td>B cells</td> <td>3 ,09</td> </tr> <tr> <td>Lamivudine</td> <td>B cells</td> <td>2 ,9</td> </tr> <tr> <td>AZD-8330</td> <td>Myeloid cells</td> <td>2 ,031</td> </tr> <tr> <td>Perhexiline</td> <td>Myeloid cells</td> <td>1 ,870</td> </tr> <tr> <td>AT13387</td> <td>Myeloid cells</td> <td>1 ,675</td> </tr> </tbody> </table> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16791068%2Ffb4c98e53f29150d2bbe8c6cb587e618%2F2023-12-20%20%2021.47.14.png?generation=1703098200209837&alt=media"></p> <h2>Overview of the approach</h2> <h2>Data preprocessing, feature engineering:</h2> <h2>The models</h2> <h2>Validation Strategy</h2> <h2>Details of the submission</h2> <h2>What was impactful about the submission.</h2> <h2>What was tried and didn’t work.</h2> <h1>4. Robustness</h1> <table> <thead> <tr> <th>Model</th> <th>Private</th> <th>Public</th> </tr> </thead> <tbody> <tr> <td></td> <td></td> <td></td> </tr> </tbody> </table> <h1>5. Documentation & code style</h1> <h2>Code samples feature engineering:</h2> <h2>Code samples model training:</h2> <h2>Code samples model inference:</h2> <h1>6. Reproducibility</h1> <table> <thead> <tr> <th>name</th> <th>link</th> </tr> </thead> <tbody> <tr> <td>118th Place notebook</td> <td><a href="https://www.kaggle.com/emmawilsonev/118th-place-solution-for-the-open-problems-singl" target="_blank">https://www.kaggle.com/emmawilsonev/118th-place-solution-for-the-open-problems-singl</a></td> </tr> </tbody> </table> <h2>Helpful notebooks:</h2>
Child Mind Institute - Detect Sleep States	685th Place Solution for the Child Mind Institute - Detect Sleep States Competition	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Child Mind Institute - Detect Sleep States <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>I would like to express gratitude to Kaggle for hosting the competition and Child Mind Institute for providing a dataset. </p> <p>I'm so grateful to 213TUBO for sharing the public notebook <a href="https://www.kaggle.com/code/tubotubo/cmi-submit?scriptVersionId=149255724" target="_blank">https://www.kaggle.com/code/tubotubo/cmi-submit?scriptVersionId=149255724</a>.<br> I gained a lot of knowledge from github <a href="https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states" target="_blank">https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states</a>.</p> <h1>Context</h1> <p>• Business context: <a href="https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/overview" target="_blank">https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/overview</a><br> • Data context: <a href="https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/data" target="_blank">https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/data</a></p> <h1>Overview of the approach</h1> <h2>The models</h2> <p>The framework Torch, models UNet, and AutoModel were used.</p> <table> <thead> <tr> <th>Owner</th> <th>Github</th> </tr> </thead> <tbody> <tr> <td>213TUBO</td> <td><a href="https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states/tree/main/src/models" target="_blank">https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states/tree/main/src/models</a></td> </tr> </tbody> </table> <pre><code> src.models.detr2D DETR2DCNN src.models.spec1D Spec1D src.models.spec2Dcnn Spec2DCNN src.models.transformerautomodel TransformerAutoModel src.models.centernet CenterNet </code></pre> <h2>Data preprocessing, feature engineering:</h2> <table> <thead> <tr> <th>Name</th> <th>Value</th> </tr> </thead> <tbody> <tr> <td>Score th</td> <td>0.02</td> </tr> <tr> <td>Distance</td> <td>10</td> </tr> </tbody> </table> <p>Add feature:</p> <table> <thead> <tr> <th>Field</th> <th>Function</th> </tr> </thead> <tbody> <tr> <td>Anglez, enmo</td> <td>diff</td> </tr> <tr> <td>Anglez, enmo</td> <td>mean, avg</td> </tr> <tr> <td>Hour</td> <td>sin, cos</td> </tr> </tbody> </table> <h2>Augmentations:</h2> <table> <thead> <tr> <th>Type</th> <th>Name</th> <th>Value</th> </tr> </thead> <tbody> <tr> <td>Mixup</td> <td>prob</td> <td>0.0</td> </tr> <tr> <td>Mixup</td> <td>alpha</td> <td>0.4</td> </tr> <tr> <td>Cutmix</td> <td>prob</td> <td>0.0</td> </tr> <tr> <td>Cutmix</td> <td>alpha</td> <td>0.4</td> </tr> </tbody> </table> <h2>Validation Strategy</h2> <p>Use a train_series_ids and a valid_series_ids.<br> The rate of downsample is 2.</p> <h1>Details of the submission</h1> <p><a href="https://www.kaggle.com/code/emmawilsonev/cmi-submit/edit/run/153313645" target="_blank">https://www.kaggle.com/code/emmawilsonev/cmi-submit/edit/run/153313645</a></p> <table> <thead> <tr> <th>Private Score</th> <th>Public Score</th> </tr> </thead> <tbody> <tr> <td>0.728</td> <td>0.707</td> </tr> </tbody> </table> <h2>Code samples model training:</h2> <table> <thead> <tr> <th>Training/Configuration</th> <th>Code</th> </tr> </thead> <tbody> <tr> <td>Training</td> <td><a href="https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states/blob/main/src/modelmodule.py" target="_blank">https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states/blob/main/src/modelmodule.py</a></td> </tr> <tr> <td>Configuration</td> <td><a href="https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states/blob/main/run/conf/train.yaml#L41" target="_blank">https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states/blob/main/run/conf/train.yaml#L41</a></td> </tr> </tbody> </table> <p>Configuration:</p> <table> <thead> <tr> <th>Parameter</th> <th>Value</th> </tr> </thead> <tbody> <tr> <td>epochs</td> <td>50</td> </tr> <tr> <td>gradient_clip_val</td> <td>1.0</td> </tr> <tr> <td>lr</td> <td>0.0005</td> </tr> </tbody> </table> <h2>Code samples feature engineering:</h2> <pre><code>num_frames = upsampled_num_frames downsample_rate </code></pre> <pre><code> onset, wakeup this_event_df[[, ]].to_numpy(): onset_pos = ((onset - start) / duration * num_frames) onset_offset = (onset - start) / duration * num_frames - onset_pos wakeup_pos = ((wakeup - start) / duration * num_frames) wakeup_offset = (wakeup - start) / duration * num_frames - wakeup_pos bbox_size = ((wakeup_pos, num_frames) - (onset_pos, )) / num_frames </code></pre> <h2>Code samples model inference:</h2> <pre><code> feature_extractor = get_feature_extractor( cfg.feature_extractor, feature_dim, num_timesteps ) decoder = get_decoder(cfg.decoder, feature_extractor.height, n_classes, num_timesteps) model = Spec2DCNN( feature_extractor=feature_extractor, decoder=decoder, in_channels=feature_extractor.out_chans, mixup_alpha=cfg.aug.mixup_alpha, cutmix_alpha=cfg.aug.cutmix_alpha, **cfg.model.params, ) </code></pre> <h2>What was impactful about the submission.</h2> <p>Grait concept 213TUBO concerning sin and cos:<br> <a href="https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states/blob/main/run/prepare_data.py" target="_blank">https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states/blob/main/run/prepare_data.py</a></p> <h2>What was tried and didn’t work.</h2> <p>Skillet-learn gradient boosting.</p> <h2>Helpful notebooks:</h2> <table> <thead> <tr> <th>Author</th> <th>notebook/github</th> <th>link</th> </tr> </thead> <tbody> <tr> <td>213TUBO</td> <td>notebook</td> <td><a href="https://www.kaggle.com/code/tubotubo/cmi-submit?scriptVersionId=149255724" target="_blank">https://www.kaggle.com/code/tubotubo/cmi-submit?scriptVersionId=149255724</a></td> </tr> <tr> <td>213TUBO</td> <td>github</td> <td><a href="https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states" target="_blank">https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states</a></td> </tr> </tbody> </table> <p>Thank you for reading.</p>
Open Problems – Single-Cell Perturbations	A model used in the 24th solution - pure linear algebra!	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><h1>Intro</h1> <p>I share a linear algebra method, an unbiased and reproducible approach, resulting in decent Private/Public scores of 0.768/0.582. My final submission is an ensemble of this <a href="https://www.kaggle.com/code/makio323/24th-using-linear-algebra-priv-pub-0-768-0-582" target="_blank">Linear Algebra</a> approach along with AE NN mimicking the linear algebra approach by NN, whose joint weight is 0.70, and the combination of the public notebooks, <a href="https://www.kaggle.com/code/makio323/pyboost-secret-grandmaster-s-tool-0-592" target="_blank">Pyboost</a>, <a href="https://www.kaggle.com/code/makio323/fork-of-nlp-regression-12a31a-0-594" target="_blank">NN</a>, and <a href="https://www.kaggle.com/code/mehrankazeminia/1-op2-eda-linearsvr-regressorchain" target="_blank">Linear SVR</a>, with the total weight of 0.3. It turns out that the pure Linear Algebra model gets the best private leaderboard score.</p> <p>In the first half of this competition, I struggled to overcome the wall of a 0.600 public score. Some lucky runs of some NN models got over the wall, but not always. There was also the second formidable wall of 0.585, which blended the results of public models.</p> <p>After the first half, I came up with this linear algebra approach and overcame the walls; the prediction is deterministic and reproducible and helped me to move on. </p> <p>The code of this linear model is available at <a href="https://www.kaggle.com/code/makio323/24th-using-linear-algebra-priv-pub-0-768-0-582" target="_blank">my code notebook</a>. </p> <h1>Biological Hypothesis</h1> <p>It is a bit old, before the deep neural network, I had research experience using linear algebra to predict the missing values in a matrix - <a href="https://www.cs.uic.edu/~mtamura/MakioTamuraMasterProject.pdf" target="_blank">Missing Value Expectation of Matrix Data by Fixed Rank Approximation Algorithm</a>, and it may inspire me.</p> <p>An assumption behind this method is that the differential expressions (DEs) of 18,211 genes at one cell line (e.g. NK cells) can be linearly transferable to those of another cell line (e.g. B Cells) on the same chemical perturbation.</p> <p>A chemical perturbation triggers a complex activity interaction among the 18,211 genes, and different chemical perturbations make different activity patterns, resulting in various DEs from the same baseline condition. However, there would be an unseen “master rule” to govern these interactions on each cell line. If the master rule of one cell line (e.g. NK cells) could be similar to another cell (e.g. B cells), DEs on the same chemical perturbation could be predictable from one to another. Even not knowing the master rule of each cell line, their relationship among cell lines could be captured such that</p> <ul> <li><em>f</em>(DE<em>_i_c</em>) = DE<em>_j_c</em></li> </ul> <p>where DE<em>_i_x</em>and DE<em>_j_x</em> are the differential expressions of cell line <em>i</em> (NK cells, T cells CD4+, T cells CD8+, T regulatory cells) and <em>j</em> ('B cells', 'Myeloid cells') of chemical <em>c</em> perturbation, <em>f</em> is some special function.</p> <p>My approach is to assume that the linear system can be the proxy function, and to solve a system may provide the "transfer" such that</p> <ul> <li>DE<em>_i_core</em> x T = DE<em>_j_core</em></li> </ul> <p>where DE<em>_i_core</em> and DE<em>_j_core</em> are <em>m</em> x <em>n</em> matrix, <em>m</em> is the number of chemicals shared by cel line <em>i</em> (NK cells, T cells CD4+, T cells CD8+, T regulatory cells) and <em>j</em> ('B cells', 'Myeloid cells') as shown below (including positive controls) and n is the number of genes (18,211). T is an <em>n</em> x <em>n</em> matrix, considered a transformer matrix from one cell line to another.</p> <p>NK cells B cells 17<br> NK cells Myeloid cells 17<br> T cells CD4+ B cells 17<br> T cells CD4+ Myeloid cells 17<br> T cells CD8+ B cells 15<br> T cells CD8+ Myeloid cells 15<br> T regulatory cells B cells 17<br> T regulatory cells Myeloid cells 17</p> <p>Once the transformer T is solved on the core chemicals, it may be applied to predict DEs of the target cell (e.g. B cells) from the known cell (e.g. NK cells)</p> <ul> <li>Prediction of DE<em>_i_target</em> = DE<em>_j_target</em> x T</li> </ul> <p>where DE<em>_i_target</em> is the DEs of prediction cell line i (B cells and Myeloid cells) of the target chemicals, 128 for B cells and 127 for Myoloid cells, and DE<em>_j_target</em> is the DEs of known cell line j (NK cells, T cells CD4+, T cells CD8+, T regulatory cells) of the target chemicals.</p> <p>This approach may provide a robust and unbiased prediction.</p> <h1>Observation</h1> <p>Using SVD to get the 1st and 2nd projected expression of the shared chemicals across 6 cell lines, and visualize the disperse among them (17 including positive controls, missing chemicals in T8 is replaced with those of T4). Well, it is a bit difficult to recognize a clear pattern.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F577034%2Fb9f7d6b1595bae80513bbcd2fa786bb4%2Fs_plot.png?generation=1701966557440410&alt=media" alt=""></p> <p>Here is a grid plot of the previous one by chemicals. In most of the chemicals, there is not much difference among 6 cell cline. However, NK cell seems to be similar to the B Cell and Myoloid cell on the chemical perturbations that create the larger difference among 6 cell lines such as Belinostat (one of the positive controls), MNL 2238, and Oprozomib. In the end, accuracy in predicting such chemicals may be important. </p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F577034%2Fa5aac54f6b18ab37d2cdaa3e3c4c921e%2Fsg_plot.png?generation=1701966669627694&alt=media" alt=""></p> <h1>Model</h1> <h3>Simpler model as in the background section.</h3> <ol> <li><p>Solve linear system, transformer, from a base cell line (NK cells, T cells CD4+, T cells CD8+, T regulatory cells) to a target cell line ('B cells', 'Myeloid cells') of the DE using the chemicals tested in the two cell lines (15 plus 2 positive control).</p> <p>The transformer can be computed by multiplying a pseudo-inverse of DE<em>_i_core</em> with DE<em>_j_core</em> from the left.</p> <p>DE<em>_i_core</em> x T = DE<em>_j_core</em><br> T = DE<em>_i_core</em>-t * DE<em>_j_core</em></p> <p>where DE<em>_i_core</em>-t is a pseudo-inverse of DE<em>_i_core</em> </p></li> <li><p>Apply the transformer to the DE of the base cell line/target chemicals and get the DE of the target cell line/chemicals.</p></li> </ol> <p>The simpler model consumes a lot of memory > 20Gb, and it cannot be performed on the free version of the Saturn Cloud, which I had used for convenience, I also propose an alternative solution using SVD with a projection space.</p> <h3>SVD projection</h3> <p>It first reduces the gene dimension (18,211) to the full rank dimension of the entire data set (614) by SVD, create the transformer in the projected space, and applies the transformer in projected space from known cell to target cell on the target chemicals, reconstruct the original gene dimension of the prediction.</p> <ol> <li>Project the DE data by SVD with the whole dimension.</li> <li>Solve linear system from a base cell line (NK cells, T cells CD4+, T cells CD8+, T regulatory cells) to a target cell line ('B cells', 'Myeloid cells') of the projected DE using the chemicals tested in the two cell lines (15 plus 2 positive control).</li> <li>Apply the transformer to the projected DE of the base cell line/target chemicals and get the projected DE of the target cell line/chemicals.</li> <li>Inverse the projected DE of the target cell line/chemicals to the predicted DE.</li> </ol> <h1>Robustness, Code, and Reproducibility</h1> <p>Please refer to <a href="https://www.kaggle.com/code/makio323/24th-using-linear-algebra-priv-pub-0-768-0-582" target="_blank">my notebook</a>: the code can run on the notebook, and the result is deterministic, so reproducible. </p> <h1>Key Findings from the results</h1> <p>This method indeed can be used to diagnose the similarity of the "master rule" among the cell lines for scientific insight, and my result suggests that NK cells, along with T cells CD4+ can be stronger predictor cell lines for B Cell and Myeloid cells. Interestingly, T cells CD4+ is a better predictor for B cell while NK cell is a better predictor for Myeloid cells.</p> <p>This finding may align with the biological findings - <a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3072878/" target="_blank">NK cells can be derived from the myeloid lineage, Blood - The Journal of the American Society of Hematology 2011 3548 </a> and <a href="https://www.cell.com/trends/immunology/fulltext/S1471-4906(21)00117-4" target="_blank">T follicular helper cells cognately guide differentiation of antigen primed B cells in secondary lymphoid tissues - Trends in immunology 42.8 2021</a>.</p> <h3>Prediction by single base cell line</h3> <table> <thead> <tr> <th>base cell</th> <th>public</th> <th>private</th> </tr> </thead> <tbody> <tr> <td>NK cells</td> <td>0.784</td> <td>0.596</td> </tr> <tr> <td>T cells CD4+</td> <td>0.775</td> <td>0.607</td> </tr> <tr> <td>T cells CD8+</td> <td>0.959</td> <td>0.706</td> </tr> <tr> <td>T regulatory cells</td> <td>0.834</td> <td>0.680</td> </tr> </tbody> </table> <h3>Prediction by two base cell lines</h3> <table> <thead> <tr> <th>base cell/target cell</th> <th>public</th> <th>private</th> </tr> </thead> <tbody> <tr> <td>Predict B Cell by NK, Myeloid cells by T4</td> <td>0.786</td> <td>0.616</td> </tr> <tr> <td>Predict B Cell by T4, Myeloid cells by NK</td> <td>0.773</td> <td>0.587</td> </tr> </tbody> </table> <ol> <li><p>Differences in DE among certain cell lines can be captured linearly very well, and the linear relation is well transferable across different chemical responses, 0.768 in private and 0.582 in public</p></li> <li><p>DE of NK cell and T cells CD4+ cells are quite predictable for that of B Cell and Myeloid cells</p></li> <li><p>T cells CD4+ is a better predictor for B cell, and NK cells is a better predictor for Myeloid cell</p></li> </ol>
Open Problems – Single-Cell Perturbations	Predicting Gene Expression Changes	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><h1>Write-Ups Guide</h1> <p>Small Molecule Impact on Gene Expression<br> 1. Problem Statement:<br> - The goal of this competition is to predict how small molecules influence gene expression in various cell types. Given a dataset of small molecules and their effects on gene expression in different cell lines, the objective is to develop a model that accurately predicts the impact of a given small molecule on gene expression in unseen data. OurWrite-Ups Format <br> Small Molecule Impact on Gene Expression<br> 1. Problem Statement:<br> - The goal of this competition is to predict how small molecules influence gene expression in various cell types. Given a dataset of small molecules and their effects on gene expression in different cell lines, the objective is to develop a model that accurately predicts the impact of a given small molecule on gene expression in unseen data.Our objective is to predict the differential expression values for Myeloid and B cells based on a majority of compounds. The training data consists of measurements from 144 compounds in T cells (CD4+, CD8+, regulatory) and NK cells. However, only 10% of compounds have measurements in Myeloid and B cells. This scenario simulates a scientific context where predictions are needed for new cell types, but only limited measurements are available.</p> <p>Exploratory Data Analysis (EDA):</p> <ul> <li>Investigated data distribution, missing values, and statistical properties.</li> <li>Explored relationships between molecular descriptors and gene expression.</li> <li>Visualized the distribution of gene expression levels across different cell types.</li> </ul> <p>Model Architecture:</p> <ul> <li>Model selection as it showed promising results in initial experiments.</li> <li>Experimented with different architectures, considering the complex relationships between small molecules and gene expression.</li> </ul> <h3>Training:</h3> <p> Training Strategy:</p> <ul> <li>Trained the model on the available T cell data (CD4+, CD8+, regulatory) and NK cell data, which comprises the majority of compounds.</li> </ul> <h3>Transfer Learning:</h3> <ul> <li>Utilized transfer learning techniques to adapt the model to Myeloid and B cell predictions using the limited available data for these cell types.</li> </ul> <p>Future Improvements:</p> <ul> <li>Considered potential enhancements, such as fine-tuning model architecture or incorporating external data.</li> </ul> <h1>Write-Ups Implementation</h1> <h1>Title: Predicting Gene Expression Changes in Different Cell Types due to Small Molecules</h1> <h2>Introduction:</h2> <ul> <li>Describe the problem and the dataset. Importance of understanding how small molecules impact gene expression in various cell types.</li> </ul> <h2>Dataset Overview:</h2> <ul> <li>Dataset key features:<ul> <li>cell_type: The annotated cell type of each cell based on RNA expression.</li> <li>sm_name: The primary name for the parent compound in a standardized representation.</li> <li>sm_lincs_id: The global LINCS ID for the parent compound.</li> <li>SMILES: Simplified molecular-input line-entry system.</li></ul></li> </ul> <h1>Exploratory Data Analysis (EDA):</h1> <ul> <li>Analysis of dataset, including visualizations and insights. Example:<br> `# Import necessary libraries<br> plt.figure(figsize=(10, 6))<br> sns.histplot(data['target_variable'], bins=50, kde=True)<br> plt.title('Distribution of Target Variable')<br> plt.xlabel('Differential Expression Values')<br> plt.ylabel('Frequency')<br> plt.show()</li> </ul> <h1>Summary statistics</h1> <p>print(data.describe())</p> <h1>Distribution of cell types</h1> <p>plt.figure(figsize=(12, 6))<br> sns.countplot(x='cell_type', data=data)<br> plt.title('Distribution of Cell Types')<br> plt.show()</p> <h1>Relationships between variables</h1> <p>plt.figure(figsize=(12, 8))<br> sns.scatterplot(x='sm_name', y='gene_A1BG', hue='cell_type', data=data)<br> plt.title('Gene Expression vs Small Molecule for A1BG')<br> plt.show()<br> `</p> <h4>EDA - Feature Analysis:</h4> <ul> <li><p>Distribution of gene expression features in T cells, NK cells, and the limited set of Myeloid and B cells.<br> `t_cell_genes = data[data['cell_type'].isin(['CD4+', 'CD8+', 'regulatory'])]['gene_expression']<br> nk_cell_genes = data[data['cell_type'] == 'NK']['gene_expression']<br> myeloid_b_cell_genes = data[data['cell_type'].isin(['Myeloid', 'B'])]['gene_expression']</p> <p>plt.figure(figsize=(14, 8))<br> sns.kdeplot(t_cell_genes, label='T Cells (CD4+, CD8+, Regulatory)')<br> sns.kdeplot(nk_cell_genes, label='NK Cells')<br> sns.kdeplot(msns.kdeplot(myeloid_b_cell_genes, label='Myeloid and B Cells (Subset)')<br> plt.title('Distribution of Gene Expression Features Across Cell Types')<br> plt.xlabel('Gene Expression Values')<br> plt.ylabel('Density')<br> plt.legend()<br> plt.show()<br> `</p></li> </ul> <h1>Feature engineering on SMILES data (example: convert to molecular fingerprints)</h1> <h1>…</h1> <h1>Split data into train and test sets</h1> <p>X_train, X_test, y_train, y_test = train_test_split(data[['sm_name', 'cell_type', 'SMILES']], data['gene_A1BG'], test_size=0.2, random_state=42)</p> <h1>Random Forest Regressor</h1> <p>model = RandomForestRegressor(n_estimators=100, random_state=42)<br> model.fit(X_train, y_train)</p> <h1>Predictions on test set</h1> <p>predictions = model.predict(X_test)</p> <h1>Model Evaluation</h1> <p>mse = mean_squared_error(y_test, predictions)<br> print(f'Mean Squared Error: {mse}')<br> `</p>
Stanford Ribonanza RNA Folding	15th place solution	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Stanford Ribonanza RNA Folding <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>First and foremost, I'd like to express my gratitude to Kaggle for hosting this competition, and to the organizers for their active involvement and responsiveness in the forums. I gained valuable insights from participating in this competition. Special thanks to my teammates, Anton <a href="https://www.kaggle.com/ant0nch" target="_blank">@ant0nch</a> and María <a href="https://www.kaggle.com/manaves" target="_blank">@manaves</a>, and a shout-out to María for her extensive domain knowledge as a biotechnologist. Lastly, I want to extend my thanks to my employer, Freepik, for providing additional computing resources that proved crucial in the final weeks.</p> <p>Our solution is based on a single transformer encoder module. We used the standard pytorch implementation with <code>d_model: 256</code>, <code>dim_feedforward: 768</code>, <code>num_layers: 16</code>, <code>dropout: 0.1</code>, GELU activation and normalization first.</p> <p>The model was trained on a 5-fold split grouped by clusters, and clusters were obtained using KMeans of A, C, G, U -> 1, 2, 3, 4 mapped vectors.</p> <p>We used AdamW with weight decay 1e-2 and OneCycleLR schedule with <code>pct_start: 0.02</code> and <code>max_lr: 1e-3</code>.</p> <p>The encoder input is:</p> <ul> <li>A 252 dimensional vector encoding the sequence as the sum of nucleotide embeddings:</li> </ul> <pre><code> self.embs = nn. </code></pre> <ul> <li>We also encoded the secondary structures from the 47 provided algorithms using an embedding bag where only present data counted towards the mean. Data from the structures were encoded like this: . -> 1, ( -> 2, ) -> 3, [ or < or { -> 4, ] or > or } -> 5.</li> </ul> <pre><code> self.se_embs = nn. </code></pre> <ul> <li><p>The two embeddings were added together, and then the following features from the BPP files were concatenated for each nt: max, median, mean and std.</p></li> <li><p>Additionally, both the eternafold BPP data and adjacency matrices computed from the secondary structures were used as attention biases via a learnable linear layer. We used 48 matrices for regular pair adjacency and another 48 matrices for pseudoknot adjacency, plus the BPP matrix (so total = 48 * 2 + 1). We augmented the given data by generating additional secondary structures with mxfold2.</p></li> </ul> <pre><code> self.algo_conv = nn.Conv2d(48 * 2 + 1, nhead, =1, =0, =) </code></pre> <ul> <li>Positional encoding: we used the standard sinusoidal positional encoding from the original transformer paper. We attempt to achieve longer sequence generalization by assigning each nucleotide in the sequence random correlative positions sampled uniformly from <code>[0, 512[</code>. This hopefully forces the network to learn from the relative order of the nucleotides rather than their absolute position.</li> </ul> <pre><code> rnd_pos = torch.empty((n, s), dtype=torch.int64, device=pred.device) row row[] = torch.randperm(.max_seq_len, device=pred.device)[].sort().values pos = .pos(rnd_pos) </code></pre> <p>We trained several models for 100 epochs with a batch size of 32 and different ablations of the above features, different SNR filtering strategies (>1 and >0.5) and different GroupKFold shuffle seeds. In the end, we averaged the predictions of all 5 folds of our 7 best models.</p> <h2>What didn't work:</h2> <ul> <li>training in bfloat16 gave substantially poorer results</li> <li>pseudolabels, or we just didn't know how to implement this properly</li> </ul>
Open Problems – Single-Cell Perturbations	9th solution write-up: Pure NN model	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Open Problems – Single-Cell Perturbations <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><h1>9th solution: pure NN model</h1> <p>Hi everyone! I am Dave, this is my first time completing a kaggle competition, and I feel honored to win a gold. I want to use a pure NN model to solve this problem. I would be happy if you find this solution interesting and helpful.</p> <h2>Problem definition</h2> <p>I have seen many good solutions using each row of the data as one sample, however, I view this problem in a different way. I extracted (cell,sm,gene,value) pairs from the dataset and for each time, the model will predict the object value for a given cell type, sm type, and gene type.</p> <h2>The architecture of Model</h2> <p>The overview of the model is shown as follows:<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4090067%2F244e8db36e50bc5eeb7ae04d1b4657b1%2F2023-12-12%204.07.55.png?generation=1702368531932768&alt=media" alt=""><br> You can see that I used three kinds of features: sm features, gene features and cell features. Let’s first check how to get the sm features:<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4090067%2F0c1cf4496cea2ad183a03910b46793ce%2F2023-12-12%202.30.23.png?generation=1702365244366440&alt=media" alt=""><br> Here I involved many different kinds of features:</p> <ul> <li>MACC: Molecular ACCess System keys, are one of the most commonly used structural keys, check details <a href="https://chem.libretexts.org/Courses/Intercollegiate_Courses/Cheminformatics/06%3A_Molecular_Similarity/6.01%3A_Molecular_Descriptors" target="_blank">here</a>.</li> <li>ECFP: extended-connectivity fingerprints, are generated using a variant of the Morgan algorithm, check details <a href="https://chem.libretexts.org/Courses/Intercollegiate_Courses/Cheminformatics/06%3A_Molecular_Similarity/6.01%3A_Molecular_Descriptors" target="_blank">here</a>.</li> <li>WHIM: Weighted Holistic Invariant Molecular descriptors, are geometrical descriptors based on statistical indices calculated on the projections of the atoms along principal axes, check details <a href="https://chemgps.bmc.uu.se/help/dragonx/WHIMdecriptors1.html" target="_blank">here</a>.</li> <li>sm type: the types of small molecules.</li> <li>sm hba: the number of H-bond acceptors for a molecule.</li> <li>sm hbd: the number of H-bond donors for a molecule.</li> <li>sm rotb: the number of rotatable bonds for a molecule.</li> <li>sm mw: the molecular weight for a molecule.</li> <li>sm psa: the Polar surface area for a molecule.</li> <li>sm logp: the log of the partition coefficient of a solute between octanol and water.</li> </ul> <p>Now let's check how to get the gene features:<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4090067%2Ffcadf4701630dbb7774bc4d4616ba1c7%2F2023-12-12%202.46.18.png?generation=1702365793278185&alt=media" alt=""><br> I have involved the PCA of the genes and the additional features. To calculate the PCA feature, I set the n_components as 10 so that I can get a 10-dimensional vector to represent each gene.</p> <p>Then let's check how to get the cell features:<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4090067%2Fd0c22eba36b90129dd4ff4053bd52e88%2F2023-12-12%202.50.06.png?generation=1702365903775022&alt=media" alt=""><br> Something new here is that I used a GCN layer to help extract the feature contained in the relationship between different cells. The graph used here is very simple: cells are denoted as nodes, so there are only 6 nodes in this graph. Each pair of two nodes has an un-directed edge. I found it helpful in LB.<br> What's more, given this problem is unbalanced, we need to improve the generalization on different cell types, so you may notice that I have involved random noise in the cell features.</p> <p>Another important part is the attention layers, the structure is shown as follows:<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4090067%2F7ab9b5fff9e6588b8d3b3d17020a87e0%2F2023-12-12%203.43.25.png?generation=1702367027176571&alt=media" alt=""></p> <p>Now we know the structure of the model, but before directly training them, to improve the performance, I built a larger model based on 3 models with the same structure mentioned earlier:<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4090067%2F9269c6e48312dcde4897c6a95fe4c783%2F2023-12-12%204.17.34.png?generation=1702369066405973&alt=media" alt=""></p> <h2>Others</h2> <p>I used MSE as the loss function, AdamW as the optimizer, the learning rate is 3e-4, weight decay is 1e-3, and the batch size is 128.</p> <ul> <li>loss function: MSE</li> <li>optimizer: AdamW</li> <li>learning rate: 3e-4</li> <li>weight decay: 1e-3</li> <li>batch size: 128</li> <li>CV: 5-fold cross-validation</li> </ul>
Optiver - Trading at the Close	89th Place Solution for the Optiver - Trading at the Close Competition	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Optiver - Trading at the Close <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>First of all, I would like to express my gratitude to the hosts for organizing such an amazing competition.</p> <p>Congratulations to all the winners! While my solution may not measure up to theirs, I still hope that sharing my solution can be helpful to someone.</p> <h1>Context</h1> <ul> <li>Business context: <a href="https://www.kaggle.com/competitions/optiver-trading-at-the-close/overview" target="_blank">https://www.kaggle.com/competitions/optiver-trading-at-the-close/overview</a></li> <li>Data context: <a href="https://www.kaggle.com/competitions/optiver-trading-at-the-close/data" target="_blank">https://www.kaggle.com/competitions/optiver-trading-at-the-close/data</a></li> </ul> <h1>Overview of the approach</h1> <p>I built a LightGBM and Neural Network incorporating the structures of Transformer Encoder, which I named Stock-wise Transformer. For each model, I took the average of 8 folds and then blended them. Around 400 features were fed into LightGBM, out of which the top 200 features in terms of importance were fed into the NN model. Additionally, no further training was conducted during the private period. In fact, inference time was tight, leaving any time for additional training.</p> <h1>Details of the submission</h1> <h2>Cross-Validation</h2> <p>I conducted an 8-fold split without shuffling along the date_id axis. I chose this number of folds as the amount of data in the private test set was approximately 1/8 of the training data. Additionally, this approach did not employ TimeSeriesSplit, which could lead to strict temporal leaks. However, contrary to intuition, such a splitting method often does not pose a problem in financial time series. In fact, in this competition, there were no significant differences in metrics between the last fold and the others, and the CV mean showed a very strong correlation with the leaderboard.</p> <h2>Features</h2> <p>The features I fed into LightGBM were as follows:</p> <ul> <li>Bid-ask spread</li> <li>Imbalances of each features</li> <li>Aggregates per stock_id for each feature (including the target) from the previous day</li> <li>Aggregates per seconds_in_bucket from the previous day (including the target)</li> <li>Aggregates for all stocks from the previous day</li> <li>Rolling aggregates for each stock within the same day</li> <li>Aggregates along the column axis for the current timestamp</li> <li>Day of the week ID</li> <li>Encoding for stock_id composition weight</li> <li>Global aggregates across all stock_id and date_id</li> </ul> <p>I conducted comprehensive aggregation using methods such as min, max, mean, median, std, skew, and quantile.<br> After training LightGBM with all these features, I extracted 200 features based on feature importance for each fold in the CV and fed them into the NN model.</p> <h2>Preprocessing</h2> <h3>LightGBM</h3> <p>In this competition, features related to price were already given in a normalized state within each trading day. However, size-related features were not normalized. Since financial time series data often exhibits non-stationarity, I initially assumed that normalizing or taking differences of such features would make them more manageable, as is common practice. Surprisingly, in the case of LightGBM training, leaving these features untouched yielded the best performance. Even applying logarithmic transformations to size-related features proved to be detrimental for LightGBM. Of course, I believe this result was also influenced by the robust problem design in this competition. However, a significant lesson learned from this competition is that blindly applying traditional methods of financial time series without consideration may not be advisable.</p> <h3>Stock-wise Transformer</h3> <p>On the other hand, it was crucial to normalize the features during the training of the NN model. To minimize the impact of domain shifts, we performed rank gauss transformations within each data sharing the same timestamp. By adopting this method, each feature was transformed into relative values within the timestamp, thus allowing us to ignore changes in feature distributions over time.</p> <h2>Models</h2> <p>I computed the averages of LightGBM and Stock-wise Transformer over 8-folds respectively and generated the final predictions through blending these models. The optimal weight was determined to be 0.6 for LightGBM and 0.4 for the NN model. I was slightly surprised by the extent to which the weight of the NN model could be increased.</p> <h3>LightGBM</h3> <p>Hyperparameter tuning was crucial, and the optimal parameters led to an improvement of around +0.005 on the Public LB compared to the initial parameters. In many problem designs concerning financial time series, tuning often quickly leads to overfitting. However, in this competition, it seems to have been effective due to the robust problem design.</p> <h3>Stock-wise Transformer</h3> <p>I constructed a Neural Network based on the structure of Transformer Encoder. Specifically, I input a matrix of dimensions 200 stocks * 200 features belonging to the same timestamp at once, and applied Multi-head Attention along the stock dimension to consider the relationships between stocks for prediction. The output of this model is 200-dimensional, predicting the target variable for each stock simultaneously. <br> Additionally, when outputting predictions (before calculating gradients), I devised a method to efficiently learn specific returns by subtracting the mean of all output values from each output value for centering.<br> Furthermore, I performed augmentation using mixup for each mini-batch. Specifically, I extracted data points (features, target variable) belonging to two timestamps from the mini-batch and synthesized them into input data using a single random variable $\alpha (0 < \alpha < 1)$. During this process, for a given constant application rate $r (0 < r < 1)$, I randomly applied masks to stocks with a proportion of $1 - r$ to avoid performing mixup. $r$ is a hyperparameter. In this case, I adopted a value of 0.7.</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F4849759%2Fb9ab53c014757cb71c907a6eb5d4b12f%2Fstock_wise_transformer.png?generation=1711184235093172&alt=media"></p> <h2>Postprocessing</h2> <p>I calculated the average of predicted values for each timestamp and then performed centering by subtracting the mean from each prediction. Additionally, I further improved both the CV and LB scores by approximately +0.0006 by multiplying the predicted values by a constant factor (around 1.1).</p> <h2>What Didn't Work</h2> <p>I'll also share some ideas that didn't work out despite experimentation:</p> <ul> <li>Rank gauss transformation of the target variable and optimization with RMSE:<ul> <li>While the correlation coefficient improved with this transformed target variable, it didn't contribute to the original metric.</li></ul></li> <li>Stacking</li> <li>Target Encoding:<ul> <li>Despite the robust problem design, it seemed to be a stretch.</li></ul></li> <li>Decomposing the model into sign prediction and absolute value prediction:<ul> <li>It's generally believed that features capable of predicting the sign and magnitude of returns differ. Although I trained LightGBM on two separate problem designs and combined them, the prediction tendencies didn't differ much from a single LightGBM model and didn't contribute to the ensemble.</li></ul></li> <li>Building models for each stock:<ul> <li>Overfitting occurred quickly, rendering this approach ineffective.</li></ul></li> <li>Constructing a volatility prediction model to correct return predictions:<ul> <li>Typically, the predicted distribution of returns has a much smaller variance compared to the original distribution. Thus, I tried building a two-stage model by training a model to predict the volatility of the target variable and then applying this predicted volatility to the return predictions. However, it didn't work out.</li></ul></li> </ul>
Child Mind Institute - Detect Sleep States	8th Place Solution for the Child Mind Institute - Detect Sleep States Competition	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Child Mind Institute - Detect Sleep States <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><h1>8th Place Solution for the Child Mind Institute - Detect Sleep States Competition</h1> <p>I thank CMI and Kaggle for hosting this interesting competition, and other competitors who worked hard to push up LB improving the quality of the event detection methods. I got my first medal 🦾 and I've learnt a lot from it.</p> <h2>Context</h2> <p>Study context: <a href="https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/overview" target="_blank">https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/overview</a><br> Data: <a href="https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/data" target="_blank">https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/data</a></p> <h1>Overview of the approach</h1> <p>The main idea of my solution is to use as little pre/postprocessing as possible, and try to detect sleep/wake events in an end to end fashion. This is because I've observed that different postprocessing methods influence the mAP inconsistently on different folds (increase on some and decrease in others), probably due to the inconsistencies in the labels.</p> <p>My pipeline contains two kinds of models, one to detect the accurate position of events (aka "Regressor"), and one to detect the probability density of the event happening inside a day (aka "DensityNet").</p> <h1>Details</h1> <h2>Regressor</h2> <p>This is a simple 1D <a href="https://arxiv.org/pdf/1505.04597.pdf" target="_blank">unet</a> which <strong>only</strong> uses <em>local information</em> and <em>anglez</em> to detect where the event occurs. This is motivated by <a href="https://arxiv.org/pdf/1506.01497.pdf" target="_blank">Faster-RCNN</a> and subsequent bounding box RPN regression methods like <a href="https://arxiv.org/pdf/1506.02640.pdf" target="_blank">YOLO</a>. As we are working with 1D data and the events are well-separated, it is enough to predict two values, (onset, wakeup) per step.</p> <h3>Training</h3> <p>A fixed hyperparameter "width" is chosen for training. The data loader will shuffle and load the onset and wakeup events of the training series_id(s), and the time series interval between $ [\text{event} - \text{width}, \text{event} + \text{width}] $. The target to optimize the model against is the following:</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6066624%2Fcf5c6f25986330c81b40ac34c076ca23%2Fboxes.png?generation=1702111977884619&alt=media" alt=""></p> <ul> <li>Each box corresponds to a time step (5s)</li> <li>Coloured box is the ground truth location of the event</li> <li>i.e model predicts the relative position of the current step vs location of the event</li> </ul> <p>Since the data is noisy, I found out that Huber loss works the best, just like the smooth L1 regression loss in <a href="https://arxiv.org/pdf/1504.08083.pdf" target="_blank">Fast-RCNN</a>, so it is less sensitive to outliers.</p> <h3>Inference</h3> <p>For inference, the Regressor network will be run on the whole time series, to predict relative (onset, wakeup) values per step, which gives locations of interest. Gaussian kernels with std=12 and centered at the locations of interest will be accumulated together. </p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6066624%2Fe0ecf143f5e15170f341a58ad81b474c%2Foutput.gif?generation=1702113013116745&alt=media" alt=""></p> <ul> <li>First row: Relative location predictions by model</li> <li>Second row: Time step</li> <li>Blue color: Current iteration of accumulation</li> <li>Green color: Location of interest at current iteration</li> <li>Graph: Accumulated score </li> </ul> <p>There will be two accumulated scores, one for onset and one for wakeup. The peak of the scores gives the possible locations for the onset and wakeup events. I used the simplest peak detection method:<br> <code> locations = np.argwhere((score[1:-1] > score[:-2]) & (score[1:-1] > score[2:])).flatten() + 1 </code></p> <p>An extra NMS postprocessing step so that predicted locations must be at least 6mins from each other.</p> <h3>Model architecture</h3> <p>The Regressor is a simple 1D Unet, with 1-channel input and 2-channels output, with a <a href="https://arxiv.org/pdf/1512.03385.pdf" target="_blank">1D ResNet</a> backbone. The hidden channels are 2, 2, 4, 8, 16, 32, 32, and 2 ResNet blocks between each pooling operation. I did not include <a href="https://arxiv.org/pdf/1709.01507.pdf" target="_blank">SE</a> modules and used BatchNorm1D instead of InstanceNorm/GroupNorm/LayerNorm to make the network insensitive to global changes.</p> <h3>Ensembling</h3> <p>I trained 3 models on the whole training dataset, with width 120, 180, 240 (10, 15, 20 mins resp.). The score of the 3 models are subsequently averaged before obtaining the locations.</p> <h3>Local location prediction quality</h3> <p>To validate the performance of this model, I computed the argmax of the scores of the steps within 120 steps (10 mins) of each event. The CDF (5 fold out of fold) looks as follows:<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6066624%2F9fba37237efdbc6768746993ebeda0bb%2Fpercentile.png?generation=1702187284014701&alt=media" alt=""></p> <ul> <li>x-axis percentile</li> <li>y-axis distance in steps</li> <li>model trained with Huber loss performs best</li> </ul> <p>Around 85% of the argmax predictions lie between 3mins of the actual event. As there may be multiple peaks in the 240 step interval around the event, we expect the min distance to have less error:<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6066624%2F03bd38590d9224abe6e5360199899b1f%2Fpercentile2.png?generation=1702187925749506&alt=media" alt=""></p> <ul> <li>same x, y-axis</li> <li>min distance between events and all predicted peaks</li> <li>model trained with Huber loss</li> <li>["Huber", "Gaussian" , "Laplace"] is the shape of the kernel to reconstruct the score</li> </ul> <h2>DensityNet</h2> <p>Another network (aka "DensityNet") is needed to assign scores to each event. This network has to determine which bout of wake and sleep is the most likely (pick the longest one within a day), and honor the 30-min length and interruption rules as stipulated by <a href="url" target="_blank">https://www.kaggle.com/competitions/child-mind-institute-detect-sleep-states/data</a>. Therefore a longer context is necessary. </p> <p>To this end, I added transformer encoder modules in the deepest feature level of the 1D Unet to model global information. Since there are at most one event per day, the DensityNet will predict the probability density of the onset/wakeup event in the window of time. I used symmetric <a href="https://arxiv.org/pdf/2108.12409.pdf" target="_blank">ALiBi</a> encodings to make the transformer encoder blocks translation equivariant.</p> <h3>Training</h3> <p>I found it useful to train the model on a larger interval than that for inference to include more global context. However, my model does not predict onset/wakeup probabilities per step. Motivated by signal processing, the unknown onset/wakeup signal is a random variable within a fixed interval of interest. As such, the DensityNet is fitted against the ground truth onset+wakeup locations in a 2-day interval. </p> <p>This is simply the cross entropy loss with 12 * 60 * 24 * 2 = 34560 classes. Since the labels are noisy (and are clipped to nearest min), the target probability distribution is smoothed with the Laplace distribution. Pseudocode:</p> <pre><code> = get_distribution(interval_min, interval_min + , series_onset_lbls, series_wakeup_lbls) = model(time_series) = cross_entropy_loss(pred_logits.permute(, , ), target_distribution) </code></pre> <p>Since the data is imputed with fake intervals when the watch is taken off, the DensityNet also predicts two probabilities - whether there is any onset/wakeup event respectively in the whole interval.</p> <ul> <li>Trained 3 kinds of models<ul> <li>With anglez input only</li> <li>With enmo input only</li> <li>With anglez + time input (time randomly shifted with uniform distribution [-30min, 30min] to avoid overfitting)</li></ul></li> <li>Random flipping</li> <li>Random elastic deformation</li> </ul> <h3>Inference</h3> <p>The model now does inference only on the center 1-day subinterval of the 2-day interval. To assign scores to the events predicted by the Regressor, we use the conditional probability</p> <p>$$p(t\|\text{actual event in Regressor events}) = \frac{p(t)}{\sum_{t' \in \text{Regressor events}} p(t')}$$</p> <p>where p(t) is the probability density predicted by the DensityNet. To account for the fake intervals, the final scores are</p> <p>$$\text{score} = q * p(t\|\text{actual event in Regressor events})$$</p> <p>where q is the predicted probability that the interval contains some event (onset, wakeup respectively).</p> <p>The scores for the events in entire series are computed by shifting the prediction window over the whole series and averaged when each prediction window overlaps.</p> <p>The conditional probability can easily be computed by restricting the softmax to only on the logits of the suggested locations by the Regressor.</p> <h2>Postprocessing</h2> <h3>Shifting predictions</h3> <p>Similar to other teams, I shifted the events to xx:xx:15, xx:xx:45 to increase the mAP. Note that xx:xx:30 is undesirable too as there is a 7.5 min window in the mAP score.</p> <h3>Augmentations</h3> <p>I am surprised not much top solutions used this trick to increase the mAP. It stands to reason that events cannot be accurately labelled to 3mins / 1min precision, a slight move of the mouse will perturb the label by 1min. Below are the local 5fold out of fold mAP scores (computed with bad series and portions with missing labels removed):<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6066624%2Fc9953f4b90940237b76fb9c26aa61fa5%2Fmap.png?generation=1702188844055651&alt=media" alt=""><br> (no augmentation)</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6066624%2Fd73e12be795498ae06ae23764f5c487b%2Fmap_augmented.png?generation=1702188937356696&alt=media" alt=""><br> (with augmentation, ~+0.002 mAP)</p> <ul> <li>Similar performance for tolerance >3 min</li> <li>Gains for tolerance 1, 3 mins</li> </ul> <h3>Use matrix profile to remove fake data</h3> <p>Matrix profile can detect exact repetitions. I added that as an extra postprocessing step to remove predictions located in fake data.</p> <h1>Possible things to improve</h1> <h2>Use result from matrix profile as input</h2> <p>Some top solutions added a binary feature (1, 0) to indicate whether the step lies inside the fake data, or trained only on the intervals with clean data. This should make the model more performant as compared to my current approach of letting the model predict if the events are present in the window.</p> <h2>Make use of per-15 min labelling error distribution</h2> <p>Many top solutions made use of the pattern (uneven distribution of events per 15min). This suggests including the pattern either as input to the model or as a postprocessing step could improve the performance.</p>
Lux AI Season 2 - NeurIPS Stage 2	PPO using Jux - Lux AI Season 2 - NeurIPS Stage 2 Competition Solution	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Lux AI Season 2 - NeurIPS Stage 2 <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>Kaggle competition: <a href="https://www.kaggle.com/competitions/lux-ai-season-2-neurips-stage-2" target="_blank">Lux AI Season 2 - NeurIPS Stage 2</a></p> <p>Kaggle code submission: <a href="https://www.kaggle.com/sgoodfriend/lux2-neurips2-ppo-using-jux" target="_blank">https://www.kaggle.com/sgoodfriend/lux2-neurips2-ppo-using-jux</a></p> <p>Training repo: <a href="https://github.com/sgoodfriend/rl-algo-impls" target="_blank">https://github.com/sgoodfriend/rl-algo-impls</a>. Best submission is from <a href="https://github.com/sgoodfriend/rl-algo-impls/commit/28e662dc34fb32a22a14ec2018e13a3b30aa6699" target="_blank">28e662d</a>.</p> <p>JUX fork: <a href="https://github.com/sgoodfriend/jux" target="_blank">https://github.com/sgoodfriend/jux</a>. Biggest changes are to support environments not being in lockstep, stats collection, and allowing for adjacent factories (for 16x16 map training).</p> <p>Weights & Biases report: <a href="https://wandb.ai/sgoodfriend/rl-algo-impls-lux-nips1/reports/Lux-S2-NeurIPS-Training-Report--Vmlldzo2MTMyODc3?accessToken=a8xwpu4xi7zavhwmyavxt5lbiejk6wjn1o2eh3v8c3lc416bo11oatirp2pxlzet" target="_blank">Lux S2 NeurIPS Training Report</a></p> <h2>Environment</h2> <p>Jux allows training with vectorized environments using Jax. I used 1024 environments for training on 16x16 and 32x32 maps and 512 environments for training on 64x64 maps. I’m using a fork of <a href="https://github.com/sgoodfriend/jux" target="_blank">Jux</a> for training. The fork has the following changes and extensions:</p> <ul> <li><a href="https://github.com/sgoodfriend/jux/commit/5f40da58e5fd05537484abcd02d2c9af48bb6fc4" target="_blank">Fix incorrectly computing valid_spawns_mask.</a> This was broken on 16x16 maps. I'm not certain if it was wrong on competition-size maps.</li> <li>EnvConfig option to support adjacent factory spawns (default off). I use this for 16x16 map training because the default requirement of 6 spaces away could push factories too far away from resources on such small maps.</li> <li>Reward -1000 if player lost game for no factories (mimics Lux)</li> <li>step_unified combines step_factory_placement and step_late_game</li> <li>Environments don’t need to run in lockstep and can have different numbers of factories to place (externally replace individual envs with new ones when they finish)</li> <li>Stats collection (generation [resources, bots, kills], resources [lichen, bots, factories], actions)</li> </ul> <p>I convert the Jux observation to a GridNet observation with the following observation features for every position:<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1298%2F3f878f9ba51a34d536107f98e3d40001%2FScreenshot%202023-12-06%20at%2015.21.57.png?generation=1701904948509595&alt=media" alt="observation_space.png"></p> <p>I take care of computing amounts of resources in my action handling logic. The model only handles position for factory placement while I assign the initial water per factory (150) and enough metal for 1 or 2 heavy units (100 or 200) or 150 if not possible. For example, for 1 to 4 factories to place:<br> <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1298%2F460d5be764d8e1b750f131673e199c60%2FScreenshot%202023-12-06%20at%2015.22.30.png?generation=1701904993242219&alt=media" alt="metal_for_factories_to_place.png"></p> <p>I only allow factories to be placed on tiles that would be adjacent to ice OR ore. I allow factories to be placed adjacent to ore but not ice to help the model learn to mine ore and build robots.</p> <p>I split direction and resources between the action subtypes, resulting in the following action space per position:</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1298%2F6d62f2cd4d73d74f74d63e35014268ff%2FScreenshot%202023-12-06%20at%2015.24.01.png?generation=1701905061027060&alt=media" alt="action_space.png"></p> <p>I heavily used invalid action masking to both eliminate no-op actions (e.g. actions on non-own unit or factory positions, moves or transfers off map or onto opponent factory, or invalid actions because insufficient power or resources) and ill-advised actions:</p> <ul> <li>Don’t water lichen if it would result in water being less than the number of game steps remaining.</li> <li>Don’t transfer resources off factory tiles.<ul> <li>Exception: Allow transferring power to a unit from a factory tile if the destination unit has been digging.</li></ul></li> <li>Cannot pickup resources other than power<ul> <li>Exception: Light robots can pickup water if the factory has sufficient water.</li></ul></li> <li>Only allow digging on resources, opponent lichen, and rubble that is adjacent to a factory’s lichen grow area (prevents digging on distant rubble).</li> <li>Only allow moving in a rectangle containing all resources, diggable areas (see above), own units, and opponent lichen.</li> <li>Only lights can self-destruct and only if they are on opponent lichen that isn’t eliminable by a single dig action.</li> </ul> <p>The action handling logic will also cancel conflicting actions (instead of attempting to resolve them):</p> <ul> <li>Cancel moves if they are to a stationary own unit, unit to be spawned, or into the destination of another moving own unit. This is done iteratively until no more collisions occur.</li> <li>Cancel transfers if they aren’t going to a valid target (no unit or factory or unit or factory is at capacity)</li> <li>Cancel pickups if multiple units are picking up from the same factory and they’d cause the factory to go below 150 water or 0 power.</li> </ul> <h2>Neural Architecture</h2> <p>I started with a similar neural architecture to <a href="https://www.kaggle.com/competitions/lux-ai-season-2/discussion/406702" target="_blank">FLG’s DoubleCone</a>, but added an additional 4x-downsampling layer within the original 4x-downsampling layer to get the receptive field to 64x64:</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1298%2Fd9adf36a478568489a4415f6ddc20e94%2FScreenshot%202023-12-06%20at%2015.24.38.png?generation=1701905097172444&alt=media" alt="squnet.png"></p> <p>The policy output consists of 24 logits for unit actions, 4 logits for factory actions, and 1 logit for factory placement. Each unit’s action type and subactions are assumed independent and identically distributed, as are the factory actions. The factory placement logit undergoes a softmax transformation across all valid factory spawn positions (all factory spawn positions are masked out if it’s not the agent’s turn to place factories).</p> <h2>PPO Training</h2> <p>Similar to <a href="https://www.kaggle.com/competitions/lux-ai-season-2/discussion/406702" target="_blank">FLG’s Lux AI Season 2 Approach</a> and <a href="https://github.com/sgoodfriend/rl-algo-impls/blob/07083d6e5170ae9d2a16668e2aeadf04225f637c/rl_algo_impls/microrts/technical-description.md" target="_blank">my 2023 microRTS competition solution</a>, I progressively trained the model on larger maps, starting with 16x16, then 32x32, and finally 64x64. The best performing agent had the following training runs:</p> <table> <thead> <tr> <th>Name</th> <th>Map Size</th> </tr> </thead> <tbody> <tr> <td><a href="https://wandb.ai/sgoodfriend/rl-algo-impls-lux-nips1/runs/jk8u688d" target="_blank">ppo-LuxAI_S2-v0-j1024env16-80m-lr30-opp-resources-S1-2023-11-16T23:18:33.978764</a></td> <td>16x16</td> </tr> <tr> <td><a href="https://wandb.ai/sgoodfriend/rl-algo-impls-lux-nips1/runs/ewbq4e71" target="_blank">ppo-LuxAI_S2-v0-j1024env32-80m-lr20-2building-S1-2023-11-18T09:16:46.921499</a></td> <td>32x32</td> </tr> <tr> <td><a href="https://wandb.ai/sgoodfriend/rl-algo-impls-lux-nips1/runs/idaxlrl0" target="_blank">ppo-LuxAI_S2-v0-j512env64-80m-lr5-ft32-2building-S1-2023-11-19T09:30:01.096368</a></td> <td>64x64</td> </tr> </tbody> </table> <p>Each larger map training run was initialized with the weights from the best performing checkpoint of the previous map size. The 16x16 map training run’s weights were initialized randomly.</p> <p>I used my <a href="https://github.com/sgoodfriend/rl-algo-impls/blob/07083d6e5170ae9d2a16668e2aeadf04225f637c/rl_algo_impls/ppo/ppo.py" target="_blank">own implementation of PPO</a> (inspired by <a href="https://github.com/vwxyzjn/ppo-implementation-details/blob/fbef824effc284137943ff9c058125435ec68cd3/ppo_multidiscrete_mask.py" target="_blank">Costa Huang's implementation</a>) with the following hyperparameters:</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1298%2F5e27c6ca82f5622963a15a45abd5f9d8%2FScreenshot%202023-12-06%20at%2015.25.15.png?generation=1701905136626107&alt=media" alt="ppo_hyperparams.png"></p> <p>Each training run was for 80 million steps with the following schedule for learning rate and entropy coefficient (cosine interpolation during transition phases):</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1298%2F473071dbcba3ef72fc8882ad6f554b0d%2FScreenshot%202023-12-06%20at%2015.25.45.png?generation=1701905167868722&alt=media" alt="training_schedule.png"></p> <p>Training was done on Lambda Cloud GPU instances each with 1 Nvidia A10. I also used Nvidia A100 instances for the larger maps (not these specific training runs) where I could double the mini-batch size. I used PyTorch’s autocast to bfloat16 to reduce memory usage and gradient accumulation to take optimizer steps on the full batch.</p> <p>While training was scheduled to run 80 million steps, I would stop training early if it looked like progress was stuck. This let me schedule different training runs with limited resources.</p> <h3>Reward structure</h3> <p>RL solutions from the prior Lux Season 2 competition had to start training with shaped rewards. Similar to <a href="https://www.kaggle.com/competitions/lux-ai-season-2/discussion/406791" target="_blank">my prior solution</a>, I used generation and resource statistics to generate the reward. However, instead of determining the scaling factors myself, I scaled each statistic by dividing each statistic by its exponential moving standard deviation (window size 5 million steps). The environment would return all of these scaled statistics and a WinLoss reward (+1 win, -1 loss, 0 otherwise), and the rollout computes an advantage for each statistic. The PPO implementation has element-wise scaling factors for each advantage and reward for computing policy and value losses:</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1298%2F3c651a4b1df678206a17ab30c990e397%2FScreenshot%202023-12-06%20at%2015.26.15.png?generation=1701905196003519&alt=media" alt="reward.png"></p> <p>The advantage of the above was that I could keep the same model and simply change the weights in the value and reward coefficients to adjust the strategy. For example, the training runs for 32x32 and 64x64 maps rewarded building robots more by increasing the reward weights for ore, metal, and robot generation.</p> <h2>Training Results</h2> <h3>Reaches End of Game</h3> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1298%2F77e3e145ef3c9ba11df7c25b67abdb6a%2Freach_game_end.png?generation=1701825369443112&alt=media" alt="reach_game_end.png"></p> <p>The chart above shows the rate of games that reach the step limit. The 16x16 agent (light green) averages about 600 steps/game by the end of training. Even though I require maps to have at least 2 ice and ore each, later agents I’ve trained rarely reach over 900 steps/game, implying the small map with competitive resources is a difficult environment to reliably reach the step limit. The 32x32 (magenta) and 64x64 agents (blue) get to the step limit regularly.</p> <h3>Metal Generation</h3> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1298%2Fb02290583ed05522c03042211847f189%2Fmetal_generation.png?generation=1701825389976619&alt=media" alt="metal_generation.png"></p> <p>The chart above shows average metal generation per game. The dashed lines represents evaluations that on average beat the prior 4 best evaluation checkpoints (cumulative win-rate of at least 57% in 128 games [64 games for 64x64]). Notice that the last dashed line for 64x64 is before 20 million steps. 32x32 does continue to make models that beat prior checkpoints (dashed line continues to 60 million steps), but metal generation falls below 100 (the cost of a heavy robot). All of this implies training stopped being useful before the end.</p> <h3>KL Divergence and Loss</h3> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1298%2Fc64ab76fd68a7a92d2cc3ab7345c0237%2Flosses.png?generation=1701825409120403&alt=media" alt="losses.png"></p> <p>The charts above shows the KL divergence and training loss. 3 things jump out at me:</p> <ol> <li>KL divergence for 32x32 is too high (over 0.02), especially after 30 million steps. This is around when metal generation drops below 100.</li> <li>Losses are periodically spiky for 64x64 (and to a lesser extent 32x32). This is likely caused by training games ending at the same time every 1000 steps.</li> <li>The variability of KL divergence means a constant learning rate is not ideal. Training reaches milestones that changes game dynamics. For example, the 16x16 spike at 25 million steps coincides with games beginning to reach the step limit a sizable portion of the time. A constant learning rate means a training agent can easily be training too slowly or too quickly in the same training run depending on how much game dynamics are changing.</li> </ol> <h2>Next steps</h2> <p>I spent a lot of time creating a GridNet observation space from Jux using Jax. I believe there are a few things I could do to improve the model:</p> <ol> <li>Fix the periodic spikes in losses by doing a rolling reset of environments at the beginning of training.</li> <li>Track L2 gradient norm to gauge training stability. Loss, value loss, policy loss, KL divergence, and entropy loss are all important, but I noticed that I could end up in situations where everything would be stable until a sudden spike. Rising gradient norm is one possible indicator that training is becoming unstable even if other metrics show little change.</li> <li>Use a learning rate schedule that takes into account the changing game dynamics. I’m currently working on raising and lowering learning rate depending on the KL divergence. This is tricky because KL divergence isn’t the only indicator of instability. Currently, if the L2 gradient norm is above a cutoff, learning rate isn’t increased. This has been very finicky so this will either be supplemented with or abandoned for the next item.</li> <li>Normalization layers. <a href="https://www.kaggle.com/competitions/lux-ai-season-2/discussion/406702" target="_blank">FLG’s solution</a> called out that normalization layers didn’t appear necessary given the use of Squeeze-and-Excitation layers, but did mention LayerNorm could be useful if there wasn’t Squeeze-and-Excitation layers. Given my convergence issues, I’m trying out adding LayerNorm after fully connected layers and a spatial dimension-independent ChannelLayerNorm2d after convolutional layers. So far this has <a href="https://wandb.ai/sgoodfriend/rl-algo-impls-lux-nips1/runs/2t5tcjes" target="_blank">helped with stability at the cost of training memory and performance</a>.</li> </ol> <h2>Appendix</h2> <p>Environment hyperparameters:</p> <p><img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1298%2F227bc5e2f75df25b8cb4ca3de6bc66f4%2FScreenshot%202023-12-06%20at%2015.26.55.png?generation=1701905235576550&alt=media" alt="env_hyperparams.png"></p>
Optiver - Trading at the Close	9th Place Solution	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Optiver - Trading at the Close <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>A big thanks to Optiver and Kaggle for hosting this competition. This competition has a really stable correlation between local cv and lb. </p> <p>Actually I entered this game a little late, about 30 days before its ends and I am not good at NN, so I only focus on Gradient Boosting tree models and its feature engineering. I noticed there are many top solutions using NN and it is really a good opportunity for me to learn NN.</p> <h3>Model</h3> <ul> <li>Xgboost with 3 different seeds and same 157 features<ul> <li>There is not much difference between Xgboost and Lightgbm in lb score. But GPU Xgboost trains faster than GPU Lightgbm.</li></ul></li> </ul> <h3>Feature Engineering</h3> <ul> <li>Firstly, create some "basic features" based on raw features(i.e. add, subtract, multiply, divide from raw features). Also, create some median-scaled raw size features.</li> </ul> <pre><code>size_col = [,,,] _ size_col: train[] = train[_] / train.groupby([])[_].transform() </code></pre> <ul> <li>Secondly, do further feature engineering/aggregation on raw features and "basic features"<ul> <li>imb1, imb2 features</li> <li>market_urgency feateures I copied from public notebook</li> <li>diff features on different time window</li> <li>shift features on different time window</li> <li>rolling_mean/std features on different time window</li> <li>using history wap to calculate target of 6 second before. Then, do some rolling_mean </li> <li>some global date_id+seconds weighted features</li> <li>MACD feateures</li> <li>target rolliong_mean over stock_id + seconds_in_bucket</li></ul></li> </ul> <h3>Feature Selection</h3> <ul> <li>Because we have limit on inference time and memory, it's essential to do some feature selection. I add features group by group and check whether the local cv improves. Each feature group usually have 10 - 30 features. If one groups make local cv improve, I add feature one by one insides this feature group and usually kept only 5-10 most effective features.</li> <li>I keep 157 features in my final model.</li> </ul> <h3>Post-processing:</h3> <ul> <li>Subtract weighted sum. From the definition of target, we can know weighted sum of target for all stocks should be zero.</li> </ul> <pre><code>test_df[] = lgb_predictions test_df[] = test_df[] * test_df[] test_df[] = test_df.groupby([,])[].transform() / test_df.groupby([,])[].transform() test_df[] = test_df[] - test_df[] </code></pre> <h3>Others:</h3> <ul> <li>xgb mae objective</li> <li>xgb sample_weight 1.5 weight for latest 45 days data </li> <li>Online training. I only retrain model twice. one is N day (N is the start date of private lb), the other is N+30 day.</li> <li>polars and <code>reduce_mem_usage function</code> helps a lot</li> </ul> <h3>Codes</h3> <p>train: <a href="https://github.com/ChunhanLi/9th-kaggle-optiver-trading-close" target="_blank">https://github.com/ChunhanLi/9th-kaggle-optiver-trading-close</a><br> inference: <a href="https://www.kaggle.com/code/hookman/9th-submission" target="_blank">https://www.kaggle.com/code/hookman/9th-submission</a></p>
Optiver - Trading at the Close	14th Place Solution for the Optiver - Trading at the Close Competition	Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge	<\|system\|>You can successfully explain and teach others topics and concepts from Kaggle competition solution write-ups. You are a highly talented data scientist who has shown exceptional performance in this data-science Kaggle competition: Optiver - Trading at the Close <\|user\|>Explain and teach me concepts from Kaggle competition solution write-ups that solved this challenge <\|assistant\|><p>This post outlines our approach which got us 14th on the private leaderboard</p> <p>Firstly, thanks to <a href="https://www.kaggle.com/ravi20076" target="_blank">@ravi20076</a>, <a href="https://www.kaggle.com/mcpenguin" target="_blank">@mcpenguin</a>, <a href="https://www.kaggle.com/madarshbb" target="_blank">@madarshbb</a>, <a href="https://www.kaggle.com/cody11null" target="_blank">@cody11null</a> for the collaboration, and Optiver for organizing </p> <p>Also, thanks to <a href="https://www.kaggle.com/wenxuanxx" target="_blank">@wenxuanxx</a>, <a href="https://www.kaggle.com/zhangyue199" target="_blank">@zhangyue199</a>, <a href="https://www.kaggle.com/lblhandsome" target="_blank">@lblhandsome</a>, for upholding the Kaggle spirit and sharing your feature ideas and notebooks</p> <h1><strong>Context</strong></h1> <p>Business context: <a href="https://www.kaggle.com/competitions/optiver-trading-at-the-close" target="_blank">https://www.kaggle.com/competitions/optiver-trading-at-the-close</a><br> Data context: <a href="https://www.kaggle.com/competitions/optiver-trading-at-the-close/data" target="_blank">https://www.kaggle.com/competitions/optiver-trading-at-the-close/data</a></p> <h1><strong>Overview of the approach</strong></h1> <p>To begin with, we fixed bugs in the public notebook, and made a small change to our local validation such that it does not have data leakage when handling global features</p> <pre><code>df = df(periods=)(lambda x: x > (- x < )) to df = df()(periods=)(lambda x: x > (- x < )) </code></pre> <p>(Btw this fix improved CV but worsened public LB score. Idk why LOL)</p> <p>Also, we wrote our own functions for RSI, MACD and bollinger bands indicators as the public one gave inaccurate results in inference</p> <p><strong>What worked (impact on CV)</strong></p> <ul> <li>Features based on revealed targets. We used lags 1,2,3 for target grouped by stock_id and seconds_in_bucket as features into our models (-0.005)</li> <li>Signed representation of imbalance_size (-0.003)</li> <li>Continuous model training with revealed targets. We refitted our LGB and CatBoost model at fixed intervals (elaborated later) (-0.006)</li> <li>Performing CV in streaming fashion. To do this, we saved the data each time period in _.csv and delivered them one by one in chronological order when calculating CV. This took much longer but correlated better with the public LB</li> <li>Zero sum post processing (-0.005) (but we are not sure in private LB so we only chose 1 submission with this)</li> <li>Global Features (-0.004). We have to re-initialize these values this whenever we want to retrain the model to keep it up to date</li> <li>Technical indicators RSI, MACD and bollinger bands. We had to rewrite them for good results (-0.002)</li> </ul> <p><strong>What did not work (impact on CV)</strong></p> <ul> <li>Group by date_id and stock_id for rolling features instead of stock_id (+0.003). We didn’t do this in the end</li> <li>Lagged features shift(x) where x is large. Made CV better but worsened LB</li> <li>Rolling features over a window x where x is large. Made CV better but worsened LB</li> <li>Sector features (+0.002)</li> <li>Neural Networks</li> <li>Triplet Imbalances (+0.001) realised this feature gave very unstable values because of precision issues so we decided to discard this even though they improved the public LB score (worsened from 5.3315 to 5.3327)</li> <li>Dropping features based on feature importances</li> <li>Zero mean postprocessing. It makes our ensembles and LB/CV correlation worse for some reason so we didn’t choose this. In fact the ensemble does worse with zero mean (5.333) compared to zero sum (5.3327)</li> </ul> <p>Some additional discussion points of the approach are outlined <a href="https://www.kaggle.com/competitions/optiver-trading-at-the-close/discussion/485985" target="_blank">here</a></p> <h1><strong>Details of the submission</strong></h1> <p>Overall, after much consideration, the submissions that we chose were these two. Thank you <a href="https://www.kaggle.com/cody11null" target="_blank">@cody11null</a> for tuning the parameters and testing it with your huge 91 model script</p> <p>170 features, no postprocessing. Public 5.3384. Private 5.4457. LGB + CatBoost<br> Refitting strategy (assuming day X is the first day where currently_scored is True)</p> <ul> <li>Day X: Refit LGB, CAT</li> <li>Day X+6: Refit LGB</li> <li>Day X+12: Refit CAT</li> <li>Day X+18: Refit LGB<br> …</li> <li>Day X+54: Refit LGB</li> <li>Day X+60: Refit CAT</li> </ul> <p>193 features, zero sum postprocessing. Public 5.3327. Private 5.4458. LGB + CatBoost<br> Refitting strategy (assuming day X is the first day where currently_scored is True)</p> <ul> <li>Day X: Refit LGB, CAT</li> <li>Day X+9: Refit LGB</li> <li>Day X+18: Refit CAT</li> <li>Day X+27: Refit LGB<br> …</li> <li>Day X+54: Refit CAT</li> </ul> <p>At each time period, we use the latest LGB and latest CAT and submitted the average prediction of the 2 models</p> <p>We tried to use the stock weights for a while but got submission scoring error when refitting so didn’t proceed 😢</p>