CopulaNet: Learning residue co-evolution directly from multiple sequence alignment for protein structure prediction

doi:10.1038/s41467-021-22869-8

CORC > 理论物理研究所 > 中国科学院理论物理研究所 > 理论物理所科研产出 > 理论物理所1978-2010年知识产出

	CopulaNet: Learning residue co-evolution directly from multiple sequence alignment for protein structure prediction
	Ju, Fusong ; Zhu, Jianwei ; Shao, Bin ; Kong, Lupeng ; Liu, Tie-Yan ; Zheng, Wei-Mou ; Bu, Dongbo 1
刊名	NATURE COMMUNICATIONS
	2021
卷号	12 期号:1 页码:2535
关键词	CONTACTS POTENTIALS
ISSN号	2041-1723
DOI	10.1038/s41467-021-22869-8
英文摘要	Residue co-evolution has become the primary principle for estimating inter-residue distances of a protein, which are crucially important for predicting protein structure. Most existing approaches adopt an indirect strategy, i.e., inferring residue co-evolution based on some hand-crafted features, say, a covariance matrix, calculated from multiple sequence alignment (MSA) of target protein. This indirect strategy, however, cannot fully exploit the information carried by MSA. Here, we report an end-to-end deep neural network, CopulaNet, to estimate residue co-evolution directly from MSA. The key elements of CopulaNet include: (i) an encoder to model context-specific mutation for each residue; (ii) an aggregator to model residue co-evolution, and thereafter estimate inter-residue distances. Using CASP13 (the 13th Critical Assessment of Protein Structure Prediction) target proteins as representatives, we demonstrate that CopulaNet can predict protein structure with improved accuracy and efficiency. This study represents a step toward improved end-to-end prediction of inter-residue distances and protein tertiary structures. Protein structure prediction is a challenge. A new deep learning framework, CopulaNet, is a major step forward toward end-to-end prediction of inter-residue distances and protein tertiary structures with improved accuracy and efficiency.
学科主题	Science & Technology - Other Topics
语种	英语
内容类型	期刊论文
源URL	[http://ir.itp.ac.cn/handle/311006/27297]
专题	理论物理研究所_理论物理所1978-2010年知识产出
作者单位	1.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Key Lab Intelligent Informat Proc,Big Data Acad, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Microsoft Res Asia, Beijing, Peoples R China 4.Chinese Acad Sci, Inst Theoret Phys, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Ju, Fusong,Zhu, Jianwei,Shao, Bin,et al. CopulaNet: Learning residue co-evolution directly from multiple sequence alignment for protein structure prediction[J]. NATURE COMMUNICATIONS,2021,12(1):2535.
APA	Ju, Fusong.,Zhu, Jianwei.,Shao, Bin.,Kong, Lupeng.,Liu, Tie-Yan.,...&Bu, Dongbo.(2021).CopulaNet: Learning residue co-evolution directly from multiple sequence alignment for protein structure prediction.NATURE COMMUNICATIONS,12(1),2535.
MLA	Ju, Fusong,et al."CopulaNet: Learning residue co-evolution directly from multiple sequence alignment for protein structure prediction".NATURE COMMUNICATIONS 12.1(2021):2535.