{"id":13685277,"url":"https://github.com/OpenProteinAI/PoET","last_synced_at":"2025-05-01T01:31:18.029Z","repository":{"id":205457158,"uuid":"711019142","full_name":"OpenProteinAI/PoET","owner":"OpenProteinAI","description":"Inference code for PoET: A generative model of protein families as sequences-of-sequences","archived":false,"fork":false,"pushed_at":"2024-04-24T21:15:33.000Z","size":791,"stargazers_count":44,"open_issues_count":1,"forks_count":2,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-08-03T14:08:47.454Z","etag":null,"topics":["deep-learning","generative-model","protein-engineering","protein-language-model","protein-sequences","proteins"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/OpenProteinAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2023-10-28T01:30:26.000Z","updated_at":"2024-07-16T22:17:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"288ca7df-0ba7-4cce-9d10-90d9e0ff4312","html_url":"https://github.com/OpenProteinAI/PoET","commit_stats":null,"previous_names":["openproteinai/poet"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenProteinAI%2FPoET","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenProteinAI%2FPoET/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenProteinAI%2FPoET/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenProteinAI%2FPoET/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/OpenProteinAI","download_url":"https://codeload.github.com/OpenProteinAI/PoET/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224230791,"owners_count":17277373,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","generative-model","protein-engineering","protein-language-model","protein-sequences","proteins"],"created_at":"2024-08-02T14:00:48.041Z","updated_at":"2024-11-12T06:31:41.957Z","avatar_url":"https://github.com/OpenProteinAI.png","language":"Python","funding_links":[],"categories":["Sequence generation"],"sub_categories":[],"readme":"# PoET: A generative model of protein families as sequences-of-sequences\n\nThis repo contains inference code for [\"PoET: A generative model of protein families as sequences-of-sequences\"](https://arxiv.org/abs/2306.06156), a state-of-the-art protein language model for variant effect prediction and conditional sequence generation.\n\n## Environment Setup\n\n1. Have `mamba` (faster alternative to `conda`) installed ([Instructions](https://mamba.readthedocs.io/en/latest/installation/mamba-installation.html))\n1. Have `conda-lock` installed in your base conda/mamba environment ([Instructions](https://github.com/conda/conda-lock#installation))\n1. Run `make create_conda_env`. This will create a conda environment named `poet`.\n1. Run `make download_model` to download the model (~400MB). The model will be located at `data/poet.ckpt`. Please note the [license](#License).\n\n## Scoring variants\n\nUse the script `scripts/score.py` to obtain fitness scores for a list of protein variants given a MSA of homologs of the WT sequence.\n\n1. Be on a machine with a NVIDIA GPU. The model cannot run on CPU only.\n1. Activate the `poet` conda environment\n1. Run the script, replacing the values in angle brackets with the appropriate paths.\n\n   ```\n   python scripts/score.py \\\n   --msa_a3m_path \u003cpath to MSA of homologs of WT sequence\u003e \\\n   --variants_fasta_path \u003cpath to fasta file containing variants to score\u003e \\\n   --output_npy_path \u003cpath to output file where scores for each variant will be stored as a numpy array\u003e\n   ```\n\nYou can pass a lower value for the batch size (`--batch_size`) if you run out of VRAM. The script was tested on an A100 GPU with 40GB VRAM.\n\n## Example\n\nRun the scoring script without arguments `python scripts/score.py` to score variants in the `BLAT_ECOLX_Jacquier_2013` dataset from ProteinGym.\n\n- the dataset is located at `data/BLAT_ECOLX_Jacquier_2013.csv`\n- the variants to score as a fasta file is located at `data/BLAT_ECOLX_Jacquier_2013_variants.fasta`\n- the MSA of homologs of the WT sequence, generated using ColabFold MMseqs2 with the UniRef2202 database, is located at `data/BLAT_ECOLX_ColabFold_2202.a3m`\n- the scores will be saved as a numpy array at `data/BLAT_ECOLX_Jacquier_2013_variants.npy`\n\nThe scores obtained from the script should obtain `\u003e0.65` Spearman correlation with the measured fitness (DMS_score column in the dataset file).\n\n## Citation\n\nYou may cite the paper as\n\n```\n@inproceedings{NEURIPS2023_f4366126,\n author = {Truong Jr, Timothy and Bepler, Tristan},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {A. Oh and T. Neumann and A. Globerson and K. Saenko and M. Hardt and S. Levine},\n pages = {77379--77415},\n publisher = {Curran Associates, Inc.},\n title = {PoET: A generative model of protein families as sequences-of-sequences},\n url = {https://proceedings.neurips.cc/paper_files/paper/2023/file/f4366126eba252699b280e8f93c0ab2f-Paper-Conference.pdf},\n volume = {36},\n year = {2023}\n}\n```\n\n## License\n\nThis source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree.\n\nThe [PoET model weights](https://zenodo.org/records/10061322) (DOI: `10.5281/zenodo.10061322`) are available under the [CC BY-NC-SA 4.0](http://creativecommons.org/licenses/by-nc-sa/4.0/) license for academic use only. The license can also be found in the LICENSE file provided with the model weights. For commercial use, please reach out to us at contact@ne47.bio about licensing. Copyright (c) NE47 Bio, Inc. All Rights Reserved.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOpenProteinAI%2FPoET","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FOpenProteinAI%2FPoET","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOpenProteinAI%2FPoET/lists"}