«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

33

期数:

2023年03期

页码:

1-8

栏目:

综述

出版日期:

2023-03-10

文章信息/Info

Title:

Review of Sequence-based Protein Dihedral Angle Prediction Research

文章编号:

1673-629X(2023)03-0001-08

作者:

郑美丽¹ ; 朱 琪¹ ; 张步忠¹; 2

1. 安庆师范大学 计算机与信息学院,安徽 安庆 246013;

2. 苏州大学 江苏省计算机信息处理技术重点实验室,江苏 苏州 215006

Author(s):

ZHENG Mei-li1 ; ZHU Qi1 ; ZHANG Bu-zhong1; 2

1. School of Computer and Information,Anqing Normal University,Anqing 246013,China;

2. Jiangsu Provincial Key Laboratory for Computer Information Processing Technology,Soochow University,Suzhou 215006,China

关键词:

骨架二面角; 机器学习; 深度学习; 序列表征; 蛋白质结构

Keywords:

backbone dihedral angle; machine learning; deep learning; sequence characterization; protein structure

分类号:

TP181

DOI:

10. 3969 / j. issn. 1673-629X. 2023. 03. 001

摘要:

蛋白质结构决定功能,蛋白质主链上 N-C 键和 C-C 键形成的二面角 (渍,鬃) 对蛋白质三维结构和空间构象起着重要作用。 从蛋白质一级序列出发,预测骨架二面角可以加速对低能结构构象空间的有效采样,大大推进三维结构预测,可作为生物实验的有效快速辅助手段。 随着蛋白质生物样本数据增多和计算性能提升,近年来,深度学习方法广泛应用到蛋白质二面角预测。 介绍了蛋白质残基的主要特征表示、计算方法对二面角预测处理、评价标准和常用数据集等;对近几年来的基于深度学习模型诸多研究工作进行系统归纳与整理,从网络结构设计、输入特征表示、模型泛化性能等方面进行总结,并对比分析各算法特点及存在的问题。 在此基础上,对其未来研究发展方向与应用前景进行了展望。

Abstract:

Protein structure determines function,and the dihedral angles formed by N-C and C-C bonds in the protein backbone play animportant role in protein three-dimensional structure and spatial conformation. Starting from the protein primary sequence,prediction ofbackbone dihedral angle can accelerate the effective sampling of low-energy structural conformational space and greatly advance the 3Dstructure prediction,which can be used as an effective and rapid aid for biological experiments. With more protein biological samples andimproved computational performance, deep learning methods have been widely applied to protein dihedral angle prediction in recentyears.? To deeply understand this work,what are detailed introduced are feature representations of protein residues,computational methodsfor dihedral angle processing, evaluation metrics and common datasets. And the recent research progress based on deep learning isrigorously reviewed in terms of network structure design, input feature representation, model generalization performance, etc. Theeffectiveness and shortcoming of each algorithm are also compared and analyzed. Upon above analysis,the future research field and appli鄄cation prospect are presented.

常用功能

更新日期/Last Update: 2023-03-10