文献类型：期刊文献

英文题名：A general temperature-guided language model to design proteins of enhanced stability and activity

作者：Jiang, Fan[1,2,3];Li, Mingchen[4,5];Dong, Jiajun[6,7,8];Yu, Yuanxi[1,2,3];Sun, Xinyu[9,10];Wu, Banghao[1,2,3,11,12,13];Huang, Jin[1,2,3,11,12,13];Kang, Liqi[1,2,3];Pei, Yufeng[10];Zhang, Liang[1,2,3];Wang, Shaojie[6,7];Xu, Wenxue[6,7];Xin, Jingyao[6,7];Ouyang, Wanli[4];Fan, Guisheng[5];Zheng, Lirong[1,2];Tan, Yang[4,5];Hu, Zhiqiang[14];Xiong, Yi[11,12,13];Feng, Yan[11,12,13];Yang, Guangyu[11,12,13,15,16];Liu, Qian[11,12,13];Song, Jie[10];Liu, Jia[6,7];Hong, Liang[1,2,3,4,17];Tan, Pan[1,2,3,4]

机构：[1]Shanghai Jiao Tong Univ, Inst Nat Sci, Shanghai 200240, Peoples R China;[2]Shanghai Jiao Tong Univ, Shanghai Natl Ctr Appl Math, SJTU Ctr, Shanghai 200240, Peoples R China;[3]Shanghai Jiao Tong Univ, Inst Nat Sci, Shanghai 200240, Peoples R China;[4]Shanghai Artificial Intelligence Lab, Shanghai 200030, Peoples R China;[5]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200240, Peoples R China;[6]ShanghaiTech Univ, Shanghai Inst Adv Immunochem Studies, Shanghai 201210, Peoples R China;[7]ShanghaiTech Univ, Sch Life Sci & Technol, Shanghai 201210, Peoples R China;[8]Guangzhou Int Bio Isl, Guangzhou Natl Lab, 9 XingDaoHuanBei Rd, Guangzhou 510005, Guangdong, Peoples R China;[9]Univ Sci & Technol China, Dept Chem, Hefei 230026, Anhui, Peoples R China;[10]Chinese Acad Sci, Hangzhou Inst Med, Hangzhou 310018, Zhejiang, Peoples R China;[11]Shanghai Jiao Tong Univ, Sch Life Sci & Biotechnol, Shanghai 200240, Peoples R China;[12]Shanghai Jiao Tong Univ, State Key Lab Microbial Metab, Shanghai 200240, Peoples R China;[13]Shanghai Jiao tong Univ, Joint Int Res Lab Metab, Shanghai 200240, Peoples R China;[14]SenseTime Res, Shanghai 200233, Peoples R China;[15]Shanghai Acad Expt Med, Inst Key Biol Raw Mat, Shanghai 201401, Peoples R China;[16]Hzymes Biotechnol Co Ltd, Wuhan 430075, Hubei, Peoples R China;[17]Shanghai Jiao Tong Univ, Shanghai 200240, Peoples R China

年份：2024

卷号：10

期号：48

外文期刊名：SCIENCE ADVANCES

收录：;EI(收录号：20245017502957);WOS:【SCI-EXPANDED(收录号:WOS:001402031000010)】；

基金：This work was supported by the National Natural Science Foundation of China (grant nos. 12104295, 11974239, and 32471536), the National Key Research and Development Program of China (grant no. 2021YFF1200200), the Innovation Program of Shanghai Municipal Education Commission (2019-01-07-00-02-E00076), Shanghai JiaoTong University Scientific and Technological Innovation Funds (21X010200843), the Computational Biology Key Program of Shanghai Science and Technology Commission (23JS1400600), Science and Technology Innovation Key R&D Program of Chongqing (CSTB2022TIAD-STX0017),the Student Innovation Center at Shanghai JiaoTong University, and Shanghai Artificial Intelligence Laboratory. The engineering of VHH was supported by Changchun Genscience Pharmaceuticals Co., Ltd.

语种：英文

外文关键词：Antigen-antibody reactions - Antigens

摘要：Designing protein mutants with both high stability and activity is a critical yet challenging task in protein engineering. Here, we introduce PRIME, a deep learning model, which can suggest protein mutants with improved stability and activity without any prior experimental mutagenesis data for the specified protein. Leveraging temperature-aware language modeling, PRIME demonstrated superior predictive ability compared to current state-of-the-art models on the public mutagenesis dataset across 283 protein assays. Furthermore, we validated PRIME's predictions on five proteins, examining the impact of the top 30 to 45 single-site mutations on various protein properties, including thermal stability, antigen-antibody binding affinity, and the ability to polymerize nonnatural nucleic acid or resilience to extreme alkaline conditions. More than 30% of PRIME-recommended mutants exhibited superior performance compared to their premutation counterparts across all proteins and desired properties. We developed an efficient and effective method based on PRIME to rapidly obtain multisite mutants with enhanced activity and stability. Hence, PRIME demonstrates broad applicability in protein engineering.