|
--- |
|
license: mit |
|
language: protein |
|
tags: |
|
- protein language model |
|
datasets: |
|
- Uniref50 |
|
--- |
|
|
|
# DistilProtBert model |
|
|
|
Distilled version of [ProtBert](https://huggingface.co/Rostlab/prot_bert) model. |
|
In addition to cross entropy and cosine teacher-student losses, DistilProtBert was pretrained on a masked language modeling (MLM) objective and it only works with capital letter amino acids. |
|
|
|
# Model description |
|
|
|
DistilProtBert was pretrained on millions of proteins sequences. |
|
|
|
Few important differences between DistilProtBert model and the original ProtBert version are: |
|
1. Size of the model |
|
2. Size of the pretraining dataset |
|
3. Hardware used for pretraining |
|
|
|
## Intended uses & limitations |
|
|
|
The model could be used for protein feature extraction or to be fine-tuned on downstream tasks. |
|
|
|
### How to use |
|
|
|
The model can be used the same as ProtBert. |
|
|
|
## Training data |
|
|
|
DistilProtBert model was pretrained on [Uniref50](https://www.uniprot.org/downloads), a dataset consisting of ~43 million protein sequences (only sequences of length between 20 to 512 amino acids were used). |
|
|
|
# Pretraining procedure |
|
|
|
Preprocessing was done using ProtBert's tokenizer. |
|
The details of the masking procedure for each sequence followed the original Bert (as mentioned in [ProtBert](https://huggingface.co/Rostlab/prot_bert)). |
|
|
|
The model was pretrained on a single DGX cluster 3 epochs in total. local batch size was 16, the optimizer used was AdamW with a learning rate of 5e-5 and mixed precision settings. |
|
|
|
## Evaluation results |
|
|
|
When fine-tuned on downstream tasks, this model achieves the following results: |
|
|
|
| Task/Dataset | secondary structure (3-states) | Membrane | |
|
|:-----:|:-----:|:-----:| |
|
| CASP12 | 72 | | |
|
| TS115 | 81 | | |
|
| CB513 | 79 | | |
|
| DeepLoc | | 86 | |
|
|
|
Distinguish between: |
|
|
|
### BibTeX entry and citation info |
