摘要
宿主与病原体之间的蛋白质-蛋白质互作(Host-pathogen protein-protein interaction,HP-PPI)是病原体感染宿主的关键分子事件,准确识别HP-PPI对于理解宿主的免疫防御机制、病原体的致病机制,以及研发抗感染药物都具有重要意义。近年来,蛋白质互作实验技术的发展及其在宿主与病原体互作研究中的应用,积累了大量的HPPPI数据,于是人工智能技术逐渐在HP-PPI预测研究领域中脱颖而出。本文综述了人工智能方法在HP-PPI预测研究领域中的应用,首先介绍了基于人工智能方法识别HP-PPI的任务流程,总结了收录HP-PPI数据的常用数据库;然后重点对机器学习和深度学习两大类人工智能方法在HP-PPI预测研究领域中的应用进行分类归纳,介绍了部分经典算法模型的基本原理、特征选择和模型评估结果等;最后,分析了人工智能方法预测HP-PPI面临的问题及挑战,以期为宿主与病原体互作研究领域的科研人员提供思路和参考。
Host-pathogen protein-protein interaction(HP-PPI)is a key molecular event in host during infection by pathogens.Elucidation of HP-PPI is crucial for understanding the immune defense mechanism of the host,the mechanism of pathogenesis,and development of anti-infection drugs.In recent years,the development of PPI detection methods and their application in host-pathogen interaction studies have accumulated a large amount of HP-PPI data,which help the artificial intelligence(AI)emerge as outstanding techniques in the research field of HP-PPI prediction.This paper reviews the application of AI techniques in HP-PPI prediction.Firstly,the workflow of AI-aided identification of HP-PPI is outlined,and the commonly used databases containing HP-PPI data are summarized.Subsequently,we focus on the application of two major categories of AI methods,namely machine learning and deep learning,in the research field of HP-PPI prediction,and present the fundamentals of several classical algorithmic models,feature selection methods and model evaluation results.Finally,the problems and challenges faced by AI-aided HP-PPI prediction were discussed in detail to provide insights for researchers in studying host-pathogen interactions.
作者
任碧燕
刘璐
舒坤贤
曾垂省
代劲
刘川
李娜
REN Biyan;LIU Lu;SHU Kunxian;ZENG Chuisheng;DAI Jin;LIU Chuan;LI Na(Chongqing Key Laboratory of Big Data for Bio Intelligence,School of Life Health Information Science and Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;School of Software Engineering,Chongqing University of Posts and Telecommunications,Chongqing400065,China)
出处
《病毒学报》
CAS
CSCD
北大核心
2024年第5期1121-1136,共16页
Chinese Journal of Virology
基金
重庆市教委科学技术研究项目(项目号:KJQN202300616),题目:面向宿主与病原菌互作的机器学习关键技术研究。
作者简介
任碧燕(1995-),女,从事机器学习与深度学习应用研究,Email:s220502009@stu.cqupt.edu.cn;通信作者:刘川(1986-),男,讲师,从事人工智能与多组学数据挖掘,Email:liuchuan@cqupt.edu.cn;通信作者:李娜(1987-),女,讲师,从事人工智能与植物抗病分子生物学研究,Email:lina@cqupt.edu.cn。
