Zero-shot prediction of mutation effects with multimodal deep representation learning guides protein engineering

作     者：Cheng, Peng Mao, Cong Tang, Jin Yang, Sen Cheng, Yu Wang, Wuke Gu, Qiuxi Han, Wei Chen, Hao Li, Sihan Chen, Yaofeng Zhou, Jianglin Li, Wuju Pan, Aimin Zhao, Suwen Huang, Xingxu Zhu, Shiqiang Zhang, Jun Shu, Wenjie Wang, Shengqi 

作者机构：Bioinformat Ctr AMMS Beijing Peoples R China Nanjing Med Univ Womens Hosp Nanjing Matern & Child Hlth Care Hosp State Key Lab Reprod Med & Offspring Hlth Nanjing Jiangsu Peoples R China Zhejiang Lab Hangzhou Zhejiang Peoples R China ShanghaiTech Univ IHuman Inst Shanghai Peoples R China ShanghaiTech Univ Sch Life Sci & Technol Shanghai Peoples R China 

出 版 物：《CELL RESEARCH》 (细胞研究)

年 卷 期：2024年第34卷第9期

页      面：630-647页

核心收录：

学科分类：0710[理学-生物学] 07[理学] 071009[理学-细胞生物学] 09[农学] 0901[农学-作物学] 090102[农学-作物遗传育种] 

基　　金：National Key R&D Program of China [2021YFC2302400, 2022YFC2702705] National Natural Science Foundation of China [81830101, 62306334] Key Research Project [117005-AC2106/002, 2022PG0AC02] Infrastructure and Facility Construction Project of Zhejiang Lab [103000-AF2204] Open Fund of PDL [WDZC20245250107] 

摘      要：Mutations in amino acid sequences can provoke changes in protein function. Accurate and unsupervised prediction of mutation effects is critical in biotechnology and biomedicine, but remains a fundamental challenge. To resolve this challenge, here we present Protein Mutational Effect Predictor (ProMEP), a general and multiple sequence alignment-free method that enables zero-shot prediction of mutation effects. A multimodal deep representation learning model embedded in ProMEP was developed to comprehensively learn both sequence and structure contexts from similar to 160 million proteins. ProMEP achieves state-of-the-art performance in mutational effect prediction and accomplishes a tremendous improvement in speed, enabling efficient and intelligent protein engineering. Specifically, ProMEP accurately forecasts mutational consequences on the gene-editing enzymes TnpB and TadA, and successfully guides the development of high-performance gene-editing tools with their engineered variants. The gene-editing efficiency of a 5-site mutant of TnpB reaches up to 74.04% (vs 24.66% for the wild type);and the base editing tool developed on the basis of a TadA 15-site mutant (in addition to the A106V/D108N double mutation that renders deoxyadenosine deaminase activity to TadA) exhibits an A-to-G conversion frequency of up to 77.27% (vs 69.80% for ABE8e, a previous TadA-based adenine base editor) with significantly reduced bystander and off-target effects compared to ABE8e. ProMEP not only showcases superior performance in predicting mutational effects on proteins but also demonstrates a great capability to guide protein engineering. Therefore, ProMEP enables efficient exploration of the gigantic protein space and facilitates practical design of proteins, thereby advancing studies in biomedicine and synthetic biology.