人工智能在蛋白质-配体结合亲和力预测中的研究进展  

Advances in using artificial intelligence for predicting protein-ligand binding affinity

作　　者：云轶楠 刘诗梦 代琦[1] 张瑾[2] 王筱 YUN Yinan;LIU Shimeng;DAI Qi;ZHANG Jin;WANG Xiao(School of Life Sciences and Medicine,Zhejiang Sci-Tech University,Hangzhou 310018,Zhejiang,China;School of Biological and Chemical Engineering,Jiaxing University,Jianxing 314001,Zhejiang,China;Jiaxing Synbiolab Biotech Co.Ltd.,Jiaxing 314001,Zhejiang,China)

机构地区：[1]浙江理工大学生命科学与医药学院,浙江杭州310018 [2]嘉兴学院生物与化学工程学院,浙江嘉兴314001 [3]嘉兴欣贝莱生物科技有限公司,浙江嘉兴314001

出　　处：《生物工程学报》2024年第7期2070-2086,共17页Chinese Journal of Biotechnology

基　　金：国家自然科学基金(32172708)。

摘　　要：蛋白质与配体的结合在生命过程中发挥重要作用,计算蛋白质-配体结合亲和力(protein-ligand binding affinity, PLBA)有助于解析蛋白质功能、筛选与蛋白靶点结合的药物以及进行酶的改造等。近年来,人工智能(artificial intelligence,AI)发展迅速,因其特征提取能力强、算法准确度高、计算速度快等优势,已广泛应用于PLBA预测。本文介绍了AI预测的建立过程、相关资源、应用场景以及面临的挑战和潜在解决办法,为相关研究提供借鉴。The binding of proteins and ligands is a crucial aspect of life processes.The calculation of the protein-ligand binding affinity(PLBA)offers valuable insights into protein function,drug screening targets protein receptors,and enzyme modifications.In recent years,artificial intelligence(AI)has experienced rapid advancements,becoming widely used in PLBA prediction.This is attributed to its robust feature extraction ability,superior algorithm accuracy,and speedy calculations.Our paper aims to provide a comprehensive overview of AI predication process,associated resources,application scenarios,challenges,and potential solutions,serving as a valuable reference for the relevant research endeavors.

关 键 词：人工智能 蛋白质-配体结合亲和力 药物研发 酶工程 

分 类 号：Q503[生物学—生物化学] TP18[自动化与计算机技术—控制理论与控制工程]