{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T15:27:56Z","timestamp":1773242876455,"version":"3.50.1"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Motivation: The problem of ab initio protein folding is one of the most difficult in modern computational biology. The prediction of residue contacts within a protein provides a more tractable immediate step. Recently introduced maximum entropy-based correlated mutation measures (CMMs), such as direct information, have been successful in predicting residue contacts. However, most correlated mutation studies focus on proteins that have large good-quality multiple sequence alignments (MSA) because the power of correlated mutation analysis falls as the size of the MSA decreases. However, even with small autogenerated MSAs, maximum entropy-based CMMs contain information. To make use of this information, in this article, we focus not on general residue contacts but contacts between residues in \u03b2-sheets. The strong constraints and prior knowledge associated with \u03b2-contacts are ideally suited for prediction using a method that incorporates an often noisy CMM.<\/jats:p>\n               <jats:p>Results: Using contrastive divergence, a statistical machine learning technique, we have calculated a maximum entropy-based CMM. We have integrated this measure with a new probabilistic model for \u03b2-contact prediction, which is used to predict both residue- and strand-level contacts. Using our model on a standard non-redundant dataset, we significantly outperform a 2D recurrent neural network architecture, achieving a 5% improvement in true positives at the 5% false-positive rate at the residue level. At the strand level, our approach is competitive with the state-of-the-art single methods achieving precision of 61.0% and recall of 55.4%, while not requiring residue solvent accessibility as an input.<\/jats:p>\n               <jats:p>Availability: \u00a0http:\/\/www2.warwick.ac.uk\/fac\/sci\/systemsbiology\/research\/software\/<\/jats:p>\n               <jats:p>Contact: \u00a0D.L.Wild@warwick.ac.uk<\/jats:p>\n               <jats:p>Supplementary information: \u00a0Supplementary data are available at Bioinformatics online.<\/jats:p>","DOI":"10.1093\/bioinformatics\/btt005","type":"journal-article","created":{"date-parts":[[2013,1,12]],"date-time":"2013-01-12T01:24:22Z","timestamp":1357953862000},"page":"580-587","source":"Crossref","is-referenced-by-count":20,"title":["Predicting protein \u03b2-sheet contacts using a maximum entropy-based correlated mutation measure"],"prefix":"10.1093","volume":"29","author":[{"given":"Nikolas S.","family":"Burkoff","sequence":"first","affiliation":[{"name":"Systems Biology Centre, Senate House, University of Warwick, Coventry, CV4 7AL, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Csilla","family":"V\u00e1rnai","sequence":"additional","affiliation":[{"name":"Systems Biology Centre, Senate House, University of Warwick, Coventry, CV4 7AL, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David L.","family":"Wild","sequence":"additional","affiliation":[{"name":"Systems Biology Centre, Senate House, University of Warwick, Coventry, CV4 7AL, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2013,1,10]]},"reference":[{"key":"2023051607331903700_btt005-B1","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","article-title":"Gapped BLAST and PSI-BLAST: a new generation of protein database search proteins","volume":"25","author":"Altschul","year":"1997","journal-title":"Nucleic Acids Res."},{"key":"2023051607331903700_btt005-B2","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1002\/prot.22168","article-title":"Optimal data collection for correlated mutation analysis","volume":"74","author":"Ashkenazy","year":"2009","journal-title":"Proteins"},{"key":"2023051607331903700_btt005-B3","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1109\/TCBB.2008.140","article-title":"Bayesian models and algorithms for protein \u03b2-sheet prediction","volume":"8","author":"Aydin","year":"2011","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinformatics"},{"key":"2023051607331903700_btt005-B4","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.1002\/prot.22934","article-title":"Learning generative models for protein fold families","volume":"79","author":"Balakrishnan","year":"2011","journal-title":"Proteins"},{"key":"2023051607331903700_btt005-B5","doi-asserted-by":"crossref","first-page":"e1000633","DOI":"10.1371\/journal.pcbi.1000633","article-title":"Disentangling direct from indirect co-evolution of residues in protein alignments","volume":"6","author":"Burger","year":"2010","journal-title":"PLoS Comput. Biol."},{"key":"2023051607331903700_btt005-B6","doi-asserted-by":"crossref","first-page":"878","DOI":"10.1016\/j.bpj.2011.12.053","article-title":"Exploring the energy landscapes of protein folding simulations with bayesian computation","volume":"102","author":"Burkoff","year":"2012","journal-title":"Biophysical. J."},{"key":"2023051607331903700_btt005-B7","doi-asserted-by":"crossref","first-page":"i75","DOI":"10.1093\/bioinformatics\/bti1004","article-title":"Three-stage prediction of protein \u03b2-sheets by neural networks, alignments and graph algorithms","volume":"21","author":"Cheng","year":"2005","journal-title":"Bioinformatics"},{"key":"2023051607331903700_btt005-B8","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/TCBB.2006.17","article-title":"Bayesian segmental models with multiple sequence alignment profiles for protein secondary structure and contact map prediction","volume":"3","author":"Chu","year":"2006","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinformatics"},{"key":"2023051607331903700_btt005-B9","doi-asserted-by":"crossref","first-page":"1565","DOI":"10.1093\/bioinformatics\/bth128","article-title":"A perturbation-based method for calculating explicit likelihood of evolutionary co-variance in multiple sequence alignments","volume":"20","author":"Dekker","year":"2004","journal-title":"Bioinformatics"},{"key":"2023051607331903700_btt005-B10","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1186\/1471-2105-11-283","article-title":"Optimal contact definition for reconstruction of contact maps","volume":"11","author":"Duarte","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2023051607331903700_btt005-B11","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1093\/bioinformatics\/btm604","article-title":"Mutual information without the influence of phylogeny or entropy dramatically improves residue contact prediction","volume":"24","author":"Dunn","year":"2008","journal-title":"Bioinformatics"},{"key":"2023051607331903700_btt005-B12","doi-asserted-by":"crossref","first-page":"1792","DOI":"10.1093\/nar\/gkh340","article-title":"MUSCLE: multiple sequence alignment with high accuracy and high throughput","volume":"32","author":"Edgar","year":"2004","journal-title":"Nucl. Acids Res."},{"key":"2023051607331903700_btt005-B13","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1002\/prot.340180402","article-title":"Correlated mutations and residue contacts in proteins","volume":"18","author":"Gobel","year":"1994","journal-title":"Proteins"},{"key":"2023051607331903700_btt005-B14","first-page":"1","article-title":"Products of experts","volume-title":"Proceedings of the Ninth International Conference on Artificial Neural Networks","author":"Hinton","year":"1999"},{"key":"2023051607331903700_btt005-B15","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1162\/089976602760128018","article-title":"Training products of experts by minimizing contrastive divergence","volume":"14","author":"Hinton","year":"2002","journal-title":"Neural Comput."},{"key":"2023051607331903700_btt005-B16","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1016\/j.cell.2012.04.012","article-title":"Three-dimensional structures of membrane proteins from genomic sequencing","volume":"149","author":"Hopf","year":"2012","journal-title":"Cell"},{"key":"2023051607331903700_btt005-B17","first-page":"336","article-title":"Use of \u03b2-strand interaction pseudo potentials in protein structure and modelling","volume-title":"Proceedings of the 27th Hawaii Int\u2019l Conf. System Sciences","author":"Hubbard","year":"1994"},{"key":"2023051607331903700_btt005-B18","volume-title":"Probability Theory: The Logic of Science","author":"Jaynes","year":"2007"},{"key":"2023051607331903700_btt005-B19","doi-asserted-by":"crossref","first-page":"2577","DOI":"10.1002\/bip.360221211","article-title":"Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features","volume":"22","author":"Kabsch","year":"1983","journal-title":"Biopolymers"},{"key":"2023051607331903700_btt005-B20","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1126\/science.281.5374.253","article-title":"Design of a 20-amino acid, three-stranded \u03b2-sheet protein","volume":"281","author":"Kortemme","year":"1998","journal-title":"Science"},{"key":"2023051607331903700_btt005-B21","doi-asserted-by":"crossref","first-page":"2506","DOI":"10.1093\/bioinformatics\/btp455","article-title":"A new method for revealing correlated mutations under the structural and functional constraints in proteins","volume":"25","author":"Lee","year":"2009","journal-title":"Bioinformatics"},{"key":"2023051607331903700_btt005-B22","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","article-title":"Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences","volume":"22","author":"Li","year":"2006","journal-title":"Bioinformatics"},{"key":"2023051607331903700_btt005-B23","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1093\/bioinformatics\/17.3.282","article-title":"Clustering of highly homologous sequences to reduce the size of large protein database","volume":"17","author":"Li","year":"2001","journal-title":"Bioinformatics"},{"key":"2023051607331903700_btt005-B24","doi-asserted-by":"crossref","first-page":"2326","DOI":"10.1093\/bioinformatics\/btp421","article-title":"Prediction of protein \u03b2-residue contacts by Markov logic networks with grounding-specific weights","volume":"25","author":"Lippi","year":"2009","journal-title":"Bioinformatics"},{"key":"2023051607331903700_btt005-B25","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1006\/jmbi.2000.4364","article-title":"Contributions of residue pairing to beta-sheet formation: conservation and covariation of amino acid residue pairs on antiparallel beta-strands","volume":"305","author":"Mandel-Gutfreund","year":"2001","journal-title":"J. Mol. Biol."},{"key":"2023051607331903700_btt005-B26","doi-asserted-by":"crossref","first-page":"e28766","DOI":"10.1371\/journal.pone.0028766","article-title":"Protein 3D structure computed from evolutionary sequence variation","volume":"6","author":"Marks","year":"2011","journal-title":"PLoS One"},{"key":"2023051607331903700_btt005-B27","doi-asserted-by":"crossref","first-page":"29200","DOI":"10.1074\/jbc.M004734200","article-title":"Modulating protein folding rates in vivo and in vitro by side chain interactions between the parallel beta strands of green flluorescent protein","volume":"275","author":"Merkel","year":"2000","journal-title":"J. Biol. Chem."},{"key":"2023051607331903700_btt005-B28","doi-asserted-by":"crossref","first-page":"E1293","DOI":"10.1073\/pnas.1111471108","article-title":"Direct-coupling analysis of residue coevolution captures native contacts across many protein families","volume":"108","author":"Morcos","year":"2011","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2023051607331903700_btt005-B29","doi-asserted-by":"crossref","first-page":"S25","DOI":"10.1016\/S1359-0278(97)00060-6","article-title":"Improving contact prediction by the combination of correlated mutations and other sources of sequence information","volume":"2","author":"Olmea","year":"1997","journal-title":"Fold. Des."},{"key":"2023051607331903700_btt005-B30","first-page":"185","article-title":"Flexible sequence similarity searching with the FASTA3 program package","volume":"132","author":"Pearson","year":"2000","journal-title":"Methods Mol. Biol."},{"key":"2023051607331903700_btt005-B31","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1186\/1751-0473-3-12","article-title":"Crankite: a fast polypeptide backbone conformation sampler","volume":"3","author":"Podtelezhnikov","year":"2008","journal-title":"Source Code Biol. Med."},{"key":"2023051607331903700_btt005-B32","doi-asserted-by":"crossref","first-page":"4399","DOI":"10.1016\/j.bpj.2009.02.057","article-title":"Reconstruction and stability of secondary structure elements in the context of protein structure prediction","volume":"96","author":"Podtelezhnikov","year":"2009","journal-title":"Biophys. J."},{"key":"2023051607331903700_btt005-B33","doi-asserted-by":"crossref","first-page":"1825","DOI":"10.1002\/prot.22696","article-title":"Contact prediction for beta and alpha-beta proteins using integer linear optimization and its impact on the first principles 3D structure prediction method ASTRO-FOLD","volume":"78","author":"Rajgaria","year":"2010","journal-title":"Proteins"},{"key":"2023051607331903700_btt005-B34","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1002\/prot.10123","article-title":"Distribution of beta sheets in proteins with application to structure prediction","volume":"48","author":"Ruczinski","year":"2002","journal-title":"Proteins"},{"key":"2023051607331903700_btt005-B35","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1093\/bioinformatics\/15.6.521","article-title":"Protein analyst\u2014a distributed object environment for protein sequence and structure analysis","volume":"15","author":"Saqi","year":"1999","journal-title":"Bioinformatics"},{"key":"2023051607331903700_btt005-B36","doi-asserted-by":"crossref","first-page":"e1000584","DOI":"10.1371\/journal.pcbi.1000584","article-title":"Defining an essence of structure determining residue contacts in proteins","volume":"5","author":"Sathyapriya","year":"2009","journal-title":"PLoS Comput. Biol."},{"key":"2023051607331903700_btt005-B37","article-title":"Statistical models and monte carlo methods for protein structure prediction","author":"Schmidler","year":"2002"},{"key":"2023051607331903700_btt005-B38","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1089\/10665270050081496","article-title":"Bayesian segmentation of protein secondary structure","volume":"7","author":"Schmidler","year":"2000","journal-title":"J. Comput. Biol."},{"key":"2023051607331903700_btt005-B39","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1126\/science.270.5238.980","article-title":"Guidelines for protein design: the energetics of \u03b2 sheet side chain interactions","volume":"270","author":"Smith","year":"1995","journal-title":"Science"},{"key":"2023051607331903700_btt005-B40","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1002\/(SICI)1097-0134(199707)28:3<405::AID-PROT10>3.0.CO;2-L","article-title":"Pfam: a comprehensive database of protein families based on seed alignments","volume":"28","author":"Sonnhammer","year":"1997","journal-title":"Proteins"},{"key":"2023051607331903700_btt005-B41","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1002\/prot.10152","article-title":"Prediction of strand pairing in antiparallel and parallel beta-sheets using information theory","volume":"48","author":"Steward","year":"2002","journal-title":"Proteins Struct. Funct. Genet."},{"key":"2023051607331903700_btt005-B42","doi-asserted-by":"crossref","first-page":"10340","DOI":"10.1073\/pnas.1207864109","article-title":"Genomics-aided structure prediction","volume":"109","author":"Su\u0142kowska","year":"2012","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2023051607331903700_btt005-B43","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/S1359-0278(97)00041-2","article-title":"Recovery of protein structure from contact maps","volume":"2","author":"Vendruscolo","year":"1997","journal-title":"Fold. Des."},{"key":"2023051607331903700_btt005-B44","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1073\/pnas.0805923106","article-title":"Identification of direct residue contacts in protein-protein interaction by message passing","volume":"106","author":"Weigt","year":"2008","journal-title":"Proc. Natl Acad. Sci. USA"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/29\/5\/580\/50336183\/bioinformatics_29_5_580.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/29\/5\/580\/50336183\/bioinformatics_29_5_580.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T07:58:02Z","timestamp":1684223882000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/29\/5\/580\/249323"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,1,10]]},"references-count":44,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2013,3,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btt005","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2013,3,1]]},"published":{"date-parts":[[2013,1,10]]}}}