COMSAT: Residue contact prediction of transmembrane proteins based on support vector machines and mixed integer linear programming

doi:10.1002/prot.24979

	COMSAT: Residue contact prediction of transmembrane proteins based on support vector machines and mixed integer linear programming
	Zhang, Huiling 1; Huang, Qingsheng 1; Bei, Zhendong 2; Wei, Yanjie 1; Floudas, Christodoulos A.3,4
	2016-03-01
发表期刊	PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS
ISSN	0887-3585
卷号	84 期号:3 页码:332-348
摘要	In this article, we present COMSAT, a hybrid framework for residue contact prediction of transmembrane (TM) proteins, integrating a support vector machine (SVM) method and a mixed integer linear programming (MILP) method. COMSAT consists of two modules: COMSAT_SVM which is trained mainly on position-specific scoring matrix features, and COMSAT_MILP which is an ab initio method based on optimization models. Contacts predicted by the SVM model are ranked by SVM confidence scores, and a threshold is trained to improve the reliability of the predicted contacts. For TM proteins with no contacts above the threshold, COMSAT_MILP is used. The proposed hybrid contact prediction scheme was tested on two independent TM protein sets based on the contact definition of 14 angstrom between C alpha-C alpha atoms. First, using a rigorous leave-one-protein-out cross validation on the training set of 90 TM proteins, an accuracy of 66.8%, a coverage of 12.3%, a specificity of 99.3% and a Matthews' correlation coefficient (MCC) of 0.184 were obtained for residue pairs that are at least six amino acids apart. Second, when tested on a test set of 87 TM proteins, the proposed method showed a prediction accuracy of 64.5%, a coverage of 5.3%, a specificity of 99.4% and a MCC of 0.106. COMSAT shows satisfactory results when compared with 12 other state-of-the-art predictors, and is more robust in terms of prediction accuracy as the length and complexity of TM protein increase.
关键词	protein structure prediction hybrid framework machine learning ab initio prediction MILP
DOI	10.1002/prot.24979
收录类别	SCI
语种	英语
资助项目	National Science Foundation of China[11204342] ; Shenzhen Peacock Plan[KQCX20130628112914299] ; Science Technology and Innovation Committee of Shenzhen Municipality[JCYJ20120615140912201] ; National High Technology Research and Development Program of China[2015AA020109]
WOS研究方向	Biochemistry & Molecular Biology ; Biophysics
WOS类目	Biochemistry & Molecular Biology ; Biophysics
WOS记录号	WOS:000373352100004
出版者	WILEY-BLACKWELL
引用统计	被引频次：17[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/8444
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wei, Yanjie; Floudas, Christodoulos A.
作者单位	1.Chinese Acad Sci, Shenzhen Inst Adv Technol, Ctr High Performance Comp, Shenzhen 518055, Peoples R China 2.Chinese Acad Sci, Shenzhen Inst Adv Technol, Ctr Cloud Comp, Shenzhen 518055, Peoples R China 3.Texas A&M Univ, Dept Chem Engn, College Stn, TX 77843 USA 4.Texas A&M Univ, Texas A&M Energy Inst, College Stn, TX 77843 USA
推荐引用方式 GB/T 7714	Zhang, Huiling,Huang, Qingsheng,Bei, Zhendong,et al. COMSAT: Residue contact prediction of transmembrane proteins based on support vector machines and mixed integer linear programming[J]. PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS,2016,84(3):332-348.
APA	Zhang, Huiling,Huang, Qingsheng,Bei, Zhendong,Wei, Yanjie,&Floudas, Christodoulos A..(2016).COMSAT: Residue contact prediction of transmembrane proteins based on support vector machines and mixed integer linear programming.PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS,84(3),332-348.
MLA	Zhang, Huiling,et al."COMSAT: Residue contact prediction of transmembrane proteins based on support vector machines and mixed integer linear programming".PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS 84.3(2016):332-348.