update

app.py

@@ -32,7 +32,8 @@ def run_inference(
     model = MoLeR(configuration=config)
     samples = list(model.sample(number_of_samples))
 
-    return draw_grid_generate(samples)
+    seed_mols = [] if scaffolds == "" else scaffolds.split(".")
+    return draw_grid_generate(seed_mols, samples)
 
 
 if __name__ == "__main__":

model_cards/article.md

@@ -1,4 +1,4 @@
-# Usage instructions -- MoLeR
+# MoLeR -- Documentation
 
 ## Parameters
 
@@ -6,6 +6,7 @@
 Which model checkpoint to use (trained on different datasets).
 
 ### Scaffolds
+One or multiple scaffolds (or seed molecules), provided as '.'-separated SMILES. If empty, no scaffolds are used.
 
 ### Number of samples:
 How many samples should be generated (between 1 and 50). 

model_cards/description.md

@@ -1,7 +1,27 @@
 
-### Concurrent sequence regression and generation for molecular language modeling
+# MoLeR (MOlecule-LEvel Representation)
 
-The RT is a multitask Transformer that reformulates regression as a conditional sequence modeling task.
-This yields a dichotomous language model that seamlessly integrates property prediction with property-driven conditional generation. For details see the [arXiv preprint](https://arxiv.org/abs/2202.01338), the [development code](https://github.com/IBM/regression-transformer) and the [GT4SD endpoint](https://github.com/GT4SD/gt4sd-core) for inference.
+<img src="https://raw.githubusercontent.com/GT4SD/gt4sd-core/main/docs/_static/gt4sd_logo.png" alt="logo" width="800">
 
-Each `algorithm_version` refers to one trained model. Each model can be used for **two tasks**, either to *predict* one (or multiple) properties of a molecule or to *generate* a molecule (given a seed molecule and a property constraint).
+### Model card
+
+*Model Details*: MoLeR is a graph-based molecular generative model that can be conditioned (primed) on scaffolds. The model decorates scaffolds with realistic structural motifs.
+*Developers*: Krzysztof Maziarz and co-authors from Microsoft Research and Novartis (full reference at bottom).
+*Distributors*: Developer's code wrapped and distributed by GT4SD Team (2023) from IBM Research.
+*Model date*: Released around March 2022.
+*Model version*: Model provided by original authors, see:
+*Model type*: An encoder-decoder-based GNN for molecular generation.
+*Information about training algorithms, parameters, fairness constraints or other applied approaches, and features*: Trained by the original authors with the default parameters provided [on GitHub](https://github.com/microsoft/molecule-generation).
+*Paper or other resource for more information*: Learning to Extend Molecular Scaffolds with Structural Motifs (ICLR 2022).
+*License*: MIT
+*Where to send questions or comments about the model*: Open an issue on original author's [GitHub repository](https://github.com/microsoft/molecule-generation).
+*Intended Use. Use cases that were envisioned during development*: Chemical research, in particular drug discovery.
+*Primary intended uses/users*: Researchers and computational chemists using the model for model comparison or research exploration purposes.
+*Out-of-scope use cases*: Production-level inference, producing molecules with harmful properties.
+*Factors*: Not applicable.
+*Metrics*: Validation loss on decoding correct molecules. Evaluated on several downstream tasks.
+*Datasets*: 1.5M drug-like molecules from GuacaMol benchmark. Finetuning on 20 molecular optimization tasks from GuacaMol.
+*Ethical Considerations*: Unclear, please consult with original authors in case of questions.
+*Caveats and Recommendations*: Unclear, please consult with original authors in case of questions.
+
+Model card prototype inspired by [*Mitchell et al. (2019),  Proceedings of the Conference on Fairness, Accountability, and Transparency*](https://dl.acm.org/doi/abs/10.1145/3287560.3287596?casa_token=XD4eHiE2cRUAAAAA:NL11gMa1hGPOUKTAbtXnbVQBDBbjxwcjGECF_i-WC_3g1aBgU1Hbz_f2b4kI_m1in-w__1ztGeHnwHs)

model_cards/examples.csv

@@ -1,5 +1,5 @@
 v0,,1,4,0
 v0,CC(=O)NC1=NC2=CC(OCC3=CC=CN(CC4=CC=C(Cl)C=C4)C3=O)=CC=C2N1,1,10,0
-v0,C12C=CC=NN1C(C#CC1=C(C)C=CC3C(NC4=CC(C(F)(F)F)=CC=C4)=NOC1=3)=CN=2,3,5,5
+v0,C12C=CC=NN1C(C#CC1=C(C)C=CC3C(NC4=CC(C(F)(F)F)=CC=C4)=NOC1=3)=CN=2.CCO,3,5,5
 
 

utils.py

@@ -14,8 +14,9 @@ logger.addHandler(logging.NullHandler())
 
 
 def draw_grid_generate(
-    samples: List[Tuple[str]],
-    n_cols: int = 5,
+    seeds: List[str],
+    samples: List[str],
+    n_cols: int = 3,
     size=(140, 200),
 ) -> str:
     """
@@ -32,11 +33,14 @@ def draw_grid_generate(
 
     result = defaultdict(list)
     result.update(
-        {"SMILES": samples, "Name": [f"sample_{i}" for i in range(len(samples))]}
+        {
+            "SMILES": seeds + samples,
+            "Name": [f"Seed_{i}" for i in range(len(seeds))]
+            + [f"Generated_{i}" for i in range(len(samples))],
+        },
     )
 
     result_df = pd.DataFrame(result)
-    print("RESTULT", result_df)
     obj = mols2grid.display(
         result_df,
         tooltip=list(result.keys()),