PSICOV: precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignments

被引:566
作者
Jones, David T. [1 ]
Buchan, Daniel W. A. [1 ]
Cozzetto, Domenico [1 ]
Pontil, Massimiliano [2 ]
机构
[1] UCL, Dept Comp Sci, Bioinformat Grp, London WC1E 6BT, England
[2] UCL, Dept Comp Sci, Ctr Computat Stat & Machine Learning, London WC1E 6BT, England
基金
英国生物技术与生命科学研究理事会; 英国工程与自然科学研究理事会;
关键词
RESIDUE CONTACTS; CORRELATED MUTATIONS; PROTEIN; IDENTIFICATION; INFORMATION; PHYLOGENY; SELECTION; FAMILIES; IMPROVES; NUMBER;
D O I
10.1093/bioinformatics/btr638
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
Results: PSICOV displays a mean precision substantially better than the best performing normalized mutual information approach and Bayesian networks. For 118 out of 150 targets, the L/5 (i.e. top-L/5 predictions for a protein of length L) precision for long-range contacts (sequence separation > 23) was >= 0.5, which represents an improvement sufficient to be of significant benefit in protein structure prediction or model quality assessment.
引用
收藏
页码:184 / 190
页数:7
相关论文
共 42 条
[1]   Reducing phylogenetic bias in correlated mutation analysis [J].
Ashkenazy, Haim ;
Kliger, Yossef .
PROTEIN ENGINEERING DESIGN & SELECTION, 2010, 23 (05) :321-326
[2]  
Banerjee O, 2008, J MACH LEARN RES, V9, P485
[3]   The Protein Data Bank [J].
Berman, HM ;
Westbrook, J ;
Feng, Z ;
Gilliland, G ;
Bhat, TN ;
Weissig, H ;
Shindyalov, IN ;
Bourne, PE .
NUCLEIC ACIDS RESEARCH, 2000, 28 (01) :235-242
[4]  
Bühlmann P, 2011, SPRINGER SER STAT, P1, DOI 10.1007/978-3-642-20192-9
[5]   Disentangling Direct from Indirect Co-Evolution of Residues in Protein Alignments [J].
Burger, Lukas ;
van Nimwegen, Erik .
PLOS COMPUTATIONAL BIOLOGY, 2010, 6 (01)
[6]   Is There an Optimal Substitution Matrix for Contact Prediction with Correlated Mutations? [J].
Di Lena, Pietro ;
Fariselli, Piero ;
Margara, Luciano ;
Vassura, Marco ;
Casadio, Rita .
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, 2011, 8 (04) :1017-1028
[7]   Mutual information without the influence of phylogeny or entropy dramatically improves residue contact prediction [J].
Dunn, S. D. ;
Wahl, L. M. ;
Gloor, G. B. .
BIOINFORMATICS, 2008, 24 (03) :333-340
[8]   Assessment of domain boundary predictions and the prediction of intramolecular contacts in CASP8 [J].
Ezkurdia, Iakes ;
Grana, Osvaldo ;
Izarzugaza, Jose M. G. ;
Tress, Michael L. .
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2009, 77 :196-209
[9]   Prediction of contact maps with neural networks and correlated mutations [J].
Fariselli, P ;
Olmea, O ;
Valencia, A ;
Casadio, R .
PROTEIN ENGINEERING, 2001, 14 (11) :835-843
[10]   The Pfam protein families database [J].
Finn, Robert D. ;
Mistry, Jaina ;
Tate, John ;
Coggill, Penny ;
Heger, Andreas ;
Pollington, Joanne E. ;
Gavin, O. Luke ;
Gunasekaran, Prasad ;
Ceric, Goran ;
Forslund, Kristoffer ;
Holm, Liisa ;
Sonnhammer, Erik L. L. ;
Eddy, Sean R. ;
Bateman, Alex .
NUCLEIC ACIDS RESEARCH, 2010, 38 :D211-D222