{
 "id": "AI4Protein/PETA_LGK_Sol",
 "owner": "AI4Protein",
 "name": "PETA_LGK_Sol",
 "downloads": 330,
 "likes": 0,
 "last_modified": "2025-04-12T08:57:31.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@article{tan2024peta,\n  title={PETA: evaluating the impact of protein transfer learning with sub-word tokenization on downstream applications},\n  author={Tan, Yang and Li, Mingchen and Zhou, Ziyi and Tan, Pan and Yu, Huiqun and Fan, Guisheng and Hong, Liang},\n  journal={Journal of Cheminformatics},\n  volume={16},\n  number={1},\n  pages={92},\n  year={2024},\n  publisher={Springer}\n}\n\n@article{tan2025venusfactory,\n  title={VenusFactory: A Unified Platform for Protein Engineering Data Retrieval and Language Model Fine-Tuning},\n  author={Tan, Yang and Liu, Chen and Gao, Jingyuan and Wu, Banghao and Li, Mingchen and Wang, Ruilin and Zhang, Lingrong and Yu, Huiqun and Fan, Guisheng and Hong, Liang and Zhou, Bingxin},\n  journal={arXiv preprint arXiv:2503.15438},\n  year={2025}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "036f8a18a83b6bfc169d84cfb5ba7f89484e69a1",
 "stated_evidence": "https://huggingface.co/datasets/AI4Protein/PETA_LGK_Sol/blob/036f8a18a83b6bfc169d84cfb5ba7f89484e69a1/README.md",
 "file_evidence": "https://huggingface.co/datasets/AI4Protein/PETA_LGK_Sol/tree/036f8a18a83b6bfc169d84cfb5ba7f89484e69a1",
 "card_nc": false
}