<p>Training and deploying large-scale protein language models typically requires deep machine learning expertise—a barrier for researchers outside this field. SaprotHub overcomes this challenge by offering an intuitive platform that facilitates training and prediction as well as storage and sharing of models. Here we provide the ColabSaprot framework built on Google Colab, which potentially powers hundreds of protein training and prediction applications, enabling researchers to collaboratively build and share customized models.</p>

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Democratizing protein language model training, sharing and collaboration

  • Jin Su,
  • Zhikai Li,
  • Tianli Tao,
  • Chenchen Han,
  • Yan He,
  • Fengyuan Dai,
  • Qingyan Yuan,
  • Yuan Gao,
  • Tong Si,
  • Xuting Zhang,
  • Yuyang Zhou,
  • Junjie Shan,
  • Xibin Zhou,
  • Xing Chang,
  • Shiyu Jiang,
  • Dacheng Ma,
  • Anthony Gitter,
  • Milot Mirdita,
  • Kevin K. Yang,
  • Pascal Notin,
  • Debora S. Marks,
  • Pranam Chatterjee,
  • Rohit Singh,
  • Philip A. Romero,
  • Michael Heinzinger,
  • Jianming Liu,
  • Jia Zheng,
  • Stan Z. Li,
  • Anping Zeng,
  • Huaizong Shen,
  • Jijie Chai,
  • Feng Ju,
  • Noelia Ferruz,
  • Anum Glasgow,
  • Philip M. Kim,
  • Christopher Snow,
  • Vasilis Ntranos,
  • Jianyi Yang,
  • Liang Hong,
  • Caixia Gao,
  • Tong Si,
  • Michael Bronstein,
  • Xing Chang,
  • Fajie Yuan,
  • Jin Su,
  • Zhikai Li,
  • Tianli Tao,
  • Chenchen Han,
  • Yan He,
  • Fengyuan Dai,
  • Xuting Zhang,
  • Yuyang Zhou,
  • Junjie Shan,
  • Xibin Zhou,
  • Shiyu Jiang,
  • Yuan Gao,
  • Jiawei Zhang,
  • Yuliang Fan,
  • Yuyang Tao,
  • Linqi Cheng,
  • Xinzhe Zheng,
  • Lei Chen,
  • Rui Long,
  • Lingjie Kong,
  • Zhongji Pu,
  • Jiaming Guan,
  • Tianyuan Zhang,
  • Cheng Li,
  • Martin Steinegger,
  • Sergey Ovchinnikov,
  • Fajie Yuan

摘要

Training and deploying large-scale protein language models typically requires deep machine learning expertise—a barrier for researchers outside this field. SaprotHub overcomes this challenge by offering an intuitive platform that facilitates training and prediction as well as storage and sharing of models. Here we provide the ColabSaprot framework built on Google Colab, which potentially powers hundreds of protein training and prediction applications, enabling researchers to collaboratively build and share customized models.