中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 上海药物研究所
  3. 中国科学院上海药物研究所
  4. 新药研究国家重点实验室
Learning protein fitness landscapes with deep mutational scanning data from multiple sources

文献类型：期刊论文

作者Chen, Lin1,2; Zhang, Zehong1,2; Li, Zhenghao1,3; Li, Rui1; Huo, Ruifeng5; Chen, Lifan1,2; Wang, Dingyan6; Luo, Xiaomin1,2; Chen, Kaixian1,2,4; Liao, Cangsong2,7
刊名CELL SYSTEMS
出版日期2023-08-16
卷号14期号:8页码:22
ISSN号2405-4712
DOI10.1016/j.cels.2023.07.003
通讯作者Liao, Cangsong(csliao@simm.ac.cn) ; Zheng, Mingyue(myzheng@simm.ac.cn)
英文摘要One of the key points of machine learning-assisted directed evolution (MLDE) is the accurate learning of the fitness landscape, a conceptual mapping from sequence variants to the desired function. Here, we describe a multi-protein training scheme that leverages the existing deep mutational scanning data from diverse pro-teins to aid in understanding the fitness landscape of a new protein. Proof-of-concept trials are designed to validate this training scheme in three aspects: random and positional extrapolation for single-variant ef-fects, zero-shot fitness predictions for new proteins, and extrapolation for higher-order variant effects from single-variant effects. Moreover, our study identified previously overlooked strong baselines, and their unexpectedly good performance brings our attention to the pitfalls of MLDE. Overall, these results may improve our understanding of the association between different protein fitness profiles and shed light on developing better machine learning-assisted approaches to the directed evolution of proteins. A record of this paper's transparent peer review process is included in the supplemental information.
WOS关键词EPISTASIS ; PREDICTION ; DESIGN
资助项目National Natural Science Foundation of China[82273855] ; National Natural Science Foundation of China[2022YFC3400504] ; National Key Research and Development Program of China[LG202102-01-02] ; Shanghai Municipal Science and Technology Major Project ; Lingang Laboratory ; [T2225002] ; [E2G805H]
WOS研究方向Biochemistry & Molecular Biology ; Cell Biology
语种英语
出版者CELL PRESS
WOS记录号WOS:001058619600001
源URL[http://119.78.100.183/handle/2S10ELR8/307043]  
专题新药研究国家重点实验室
通讯作者Liao, Cangsong; Zheng, Mingyue
作者单位1.Chinese Acad Sci, Shanghai Inst Mat Med, Drug Discovery & Design Ctr, State Key Lab Drug Res, Shanghai 201203, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.ShanghaiTech Univ, Sch Life Sci & Technol, Shanghai Inst Adv Immunochem Studies, Shanghai 201210, Peoples R China
4.China Pharmaceut Univ, Sch Pharm, Nanjing 211198, Peoples R China
5.Nanjing Univ Chinese Med, Sch Chinese Mat Med, Nanjing 210023, Peoples R China
6.Lingang Lab, Shanghai 200031, Peoples R China
7.Chinese Acad Sci, Shanghai Inst Mat Med, Chem Biol Res Ctr, Shanghai 201203, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Lin,Zhang, Zehong,Li, Zhenghao,et al. Learning protein fitness landscapes with deep mutational scanning data from multiple sources[J]. CELL SYSTEMS,2023,14(8):22.
APA Chen, Lin.,Zhang, Zehong.,Li, Zhenghao.,Li, Rui.,Huo, Ruifeng.,...&Zheng, Mingyue.(2023).Learning protein fitness landscapes with deep mutational scanning data from multiple sources.CELL SYSTEMS,14(8),22.
MLA Chen, Lin,et al."Learning protein fitness landscapes with deep mutational scanning data from multiple sources".CELL SYSTEMS 14.8(2023):22.

入库方式： OAI收割

来源：上海药物研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。