蛋白质与蛋白质相互作用预测模型综述  

A survey of models for protein-protein interactions prediction

作　　者：钱冰 马宝山[1] 刘玉 QIAN Bing;MA Bao-shan;LIU Yu(School of Information Science and Technology,Dalian Maritime University,Dalian 116026,China)

机构地区：[1]大连海事大学信息科学技术学院,辽宁大连116026

出　　处：《广州大学学报（自然科学版）》2023年第1期25-32,共8页Journal of Guangzhou University:Natural Science Edition

基　　金：大连市科技创新基金资助项目(2020JJ27SN066)。

摘　　要：蛋白质作为生命活动的物质基础,通过彼此之间的相互作用来参与生物信号传递、能量和物质代谢及细胞周期调控等,因此,预测蛋白质与蛋白质相互作用(PPIs)有助于从系统角度理解生命过程,同时为细胞机制的研究奠定重要基础。目前,高通量测序技术的进步使研究人员获取了海量的蛋白质相互作用数据。面对大量具有潜在可用性的PPIs数据,国内外研究人员提出了多种PPIs预测模型。文章综述了现有的基于计算的PPIs预测方法,并进行分类,讨论了其各自优缺点。最后对PPIs预测方法进行总结和展望,提出了未来可以深入研究的方向。As the material basis of life activities,proteins participate in biological signal transmission,energy and substance metabolism and cell cycle regulation through their interactions with each other.Therefore,predicting protein-protein interactions(PPIs)helps to understand life processes from a systemic perspective,and provides an important foundation for the study of cellular mechanisms.At present,advances in high-throughput sequencing technologies have enabled researchers to acquire massive amounts of proteomics data.Faced with the large amount of potentially available data,researchers have proposed various computational models for PPIs prediction.In this paper,we review the existing computational methods for PPIs prediction,classify them,and discuss their respective advantages and disadvantages.Finally,we conclude with a summary of the methods for predicting PPIs,and suggest directions that can be studied in depth in the future.

关 键 词：蛋白质相互作用 预测方法 计算模型 

分 类 号：TP3-05[自动化与计算机技术—计算机科学与技术] TP391