---
license: mit
---

# ESM-2 for General Protein Binding Site Prediction

This model is trained to predict general binding sites of proteins using on the sequence. This is a finetuned version of 
`esm2_t6_8M_UR50D`, trained on [this dataset](https://huggingface.co/datasets/AmelieSchreiber/general_binding_sites). The data is 
not filtered by family, and thus the model may be slightly overfit. 

## Training

```
epoch 3: 
'eval_loss': 0.08215777575969696,
'eval_precision': 0.4673852829840273,
'eval_recall': 0.9587594696969697,
'eval_f1': 0.6284215753212091,
'eval_auc': 0.9730582015280457
```