Predicting residue-residue contact maps by a two-layer, integrated neural-network method

被引：35
作者：
Xue, Bin [1 ,2 ]
Faraggi, Eshel [1 ,2 ]
Zhou, Yaoqi [1 ,2 ]
机构：
[1] Indiana Univ Purdue Univ, Indiana Univ, Sch Informat, Indianapolis, IN 46202 USA
[2] Indiana Univ, Sch Med, Ctr Computat Biol & Bioinformat, Indianapolis, IN 46202 USA
来源：
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS | 2009年 / 76卷 / 01期
关键词：
artificial neural networks; contact map prediction; protein structure prediction; PROTEIN SECONDARY STRUCTURE; REAL-VALUE PREDICTION; CORRELATED MUTATIONS;
D O I：
10.1002/prot.22329
中图分类号：
Q5 [生物化学]; Q7 [分子生物学];
学科分类号：
071010 ; 081704 ;
摘要：
A neural network method (SPINE-2D) is introduced to provide a sequence-based prediction of residue-residue contact maps. This method is built on the success of SPINE in predicting secondary structure, residue solvent accessibility, and backbone torsion angles via large-scale training with overfit protection and a two-layer neural network. SPINE-2D achieved a 10-fold cross-validated accuracy of 47% (+/- 2%) for top L/5 predicted contacts between two residues with sequence separation of six or more and an accuracy of 24 +/- 1% for nonlocal contacts with sequence separation of 24 residues or more. The accuracies of 23% and 26% for nonlocal contact predictions are achieved for two independent datasets of 500 proteins and 82 CASP 7 targets, respectively. A comparison with other methods indicates that SPINE-2D is among the most accurate methods for contact-map prediction. SPINE-2D is available as a webserver at http://sparks.informatics.iupui.edu.
引用
收藏
页码：176 / 183
页数：8
相关论文
共 37 条
[1]   Gapped BLAST and PSI-BLAST: a new generation of protein database search programs [J].
Altschul, SF ;
Madden, TL ;
Schaffer, AA ;
Zhang, JH ;
Zhang, Z ;
Miller, W ;
Lipman, DJ .
NUCLEIC ACIDS RESEARCH, 1997, 25 (17) :3389-3402
[2]   Contact order and ab initio protein structure prediction [J].
Bonneau, R ;
Ruczinski, I ;
Tsai, J ;
Baker, D .
PROTEIN SCIENCE, 2002, 11 (08) :1937-1944
[3]   Improved residue contact prediction using support vector machines and a large feature set [J].
Cheng, Jianlin ;
Baldi, Pierre .
BMC BIOINFORMATICS, 2007, 8 (1)
[4]   Three-stage prediction of protein β-sheets by neural networks, alignments and graph algorithms [J].
Cheng, JL ;
Baldi, P .
BIOINFORMATICS, 2005, 21 :I75-I84
[5]   Real-SPINE: An integrated system of neural networks for real-value prediction of protein structural properties [J].
Dor, Ofer ;
Zhou, Yaoqi .
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2007, 68 (01) :76-81
[6]   Achieving 80% ten-fold cross-validated accuracy for secondary structure prediction by large-scale training [J].
Dor, Ofer ;
Zhou, Yaoqi .
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2007, 66 (04) :838-845
[7]  
FARAGGI E, 2008, PROTEINS IN PRESS, DOI DOI 10.1002/PROT.22193
[8]   Progress in predicting inter-residue contacts of proteins with neural networks and correlated mutations [J].
Fariselli, P ;
Olmea, O ;
Valencia, A ;
Casadio, R .
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2001, :157-162
[9]   A neural network based predictor of residue contacts in proteins [J].
Fariselli, P ;
Casadio, R .
PROTEIN ENGINEERING, 1999, 12 (01) :15-21
[10]   CORRELATED MUTATIONS AND RESIDUE CONTACTS IN PROTEINS [J].
GOBEL, U ;
SANDER, C ;
SCHNEIDER, R ;
VALENCIA, A .
PROTEINS-STRUCTURE FUNCTION AND GENETICS, 1994, 18 (04) :309-317
1234