文献类型：期刊文献

英文题名：SESNet: sequence-structure feature-integrated deep learning method for data-efficient protein engineering

作者：Li, Mingchen[1,4]; Kang, Liqi[1,2]; Xiong, Yi[5]; Wang, Yu Guang[1]; Fan, Guisheng[4]; Tan, Pan[1]; Hong, Liang[1,2,3]

机构：[1] Shanghai National Center for Applied Mathematics [SJTU Center], Institute of Natural Sciences, Shanghai Jiao Tong University, Shanghai, 200240, China; [2] School of Physics and Astronomy, School of Pharmacy, Shanghai Jiao Tong University, 200240, China; [3] Shanghai Artificial Intelligence Laboratory, Shanghai, 200240, China; [4] School of Information Science and Engineering, East China University of Science and Technology, Shanghai, 200240, China; [5] School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200240, China

年份：2022

外文期刊名：arXiv

收录：EI(收录号：20230013782)

语种：英文

外文关键词：Biochemical engineering - Bioinformatics - Deep learning - Forecasting - Genetic engineering - Learning systems - Semantics

摘要：Deep learning has been widely used for protein engineering. However, it is limited by the lack of sufficient experimental data to train an accurate model for predicting the functional fitness of high-order mutants. Here, we develop SESNet, a supervised deep-learning model to predict the fitness for protein mutants by leveraging both sequence and structure information, and exploiting attention mechanism. Our model integrates local evolutionary context from homologous sequences, the global evolutionary context encoding rich semantic from the universal protein sequence space and the structure information accounting for the microenvironment around each residue in a protein. We show that SESNet outperforms state-of-the-art models for predicting the sequence-function relationship on 26 deep mutational scanning datasets. More importantly, we propose a data augmentation strategy by leveraging the data from unsupervised models to pre-train our model. After that, our model can achieve strikingly high accuracy in prediction of the fitness of protein mutants, especially for the higher order variants (> 4 mutation sites), when finetuned by using only a small number of experimental mutation data ( ? 2022, CC BY-NC-SA.