A frontier protein-language generative model designed to decode the molecular language of proteins.
Quickly try our online server (Evolla-10B) here.
Table of contents
We have 2 PhD positions for international students at Westlake University, China! see here.
- 2025/01/06 We released our paper Decoding the Molecular Language of Proteins with Evolla.
- 2024/12/06 We uploaded the Evolla-10B model to
huggingface hub.
conda create -n Evolla python=3.10
conda activate Evolla
bash environment.sh
We provide the pre-trained Evolla-10B model in huggingface hub. You can download the model by running the following command:
cd ckpt/huggingface
git lfs install
git clone https://huggingface.co/westlake-repl/Evolla-10B
git clone https://huggingface.co/westlake-repl/SaProt_650M_AF2
git clone https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
| Name | Size |
|---|---|
| Evolla-10B | 10B |
We provide a sample input file examples/inputs.tsv for you to test the Evolla model. The input file should be a tab-separated file, where each line represents (protein_id, aa_sequence, foldseek_sequence, question_in_json_string).
Note: protein_id is the identifier of the line, aa_sequence is the amino acid sequence of the protein, foldseek_sequence is the sequence of the protein in FoldSeek format. question_in_json_string is the question which is dumped by json.dumps function.
The following provides script to run inference based on tsv file.
You should replace the /your/path/to/Evolla to your own path to Evolla directory.
cd /your/path/to/Evolla
python scripts/inference.py --config_path config/Evolla_10B.yaml --input_path examples/inputs.tsv
If you find this repository useful, please cite our paper:
@article{zhou2025decoding,
title={Decoding the Molecular Language of Proteins with Evolla},
author={Zhou, Xibin and Han, Chenchen and Zhang, Yingqi and Su, Jin and Zhuang, Kai and Jiang, Shiyu and Yuan, Zichen and Zheng, Wei and Dai, Fengyuan and Zhou, Yuyang and others},
journal={bioRxiv},
pages={2025--01},
year={2025},
publisher={Cold Spring Harbor Laboratory}
}
- ProTrek and its online server
- Pinal and its online server
- SaprotHub and its online server
