{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T13:27:57Z","timestamp":1773235677813,"version":"3.50.1"},"reference-count":24,"publisher":"Oxford University Press (OUP)","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,4,15]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Motivation: Prediction of protein\u2013protein interaction has become an important part of systems biology in reverse engineering the biological networks for better understanding the molecular biology of the cell. Although significant progress has been made in terms of prediction accuracy, most computational methods only predict whether two proteins interact but not their interacting residues\u2014the information that can be very valuable for understanding the interaction mechanisms and designing modulation of the interaction. In this work, we developed a computational method to predict the interacting residue pairs\u2014contact matrix for interacting protein domains, whose rows and columns correspond to the residues in the two interacting domains respectively and whose values (1 or 0) indicate whether the corresponding residues (do or do not) interact.<\/jats:p><jats:p>Results: Our method is based on supervised learning using support vector machines. For each domain involved in a given domain\u2013domain interaction (DDI), an interaction profile hidden Markov model (ipHMM) is first built for the domain family, and then each residue position for a member domain sequence is represented as a 20-dimension vector of Fisher scores, characterizing how similar it is as compared with the family profile at that position. Each element of the contact matrix for a sequence pair is now represented by a feature vector from concatenating the vectors of the two corresponding residues, and the task is to predict the element value (1 or 0) from the feature vector. A support vector machine is trained for a given DDI, using either a consensus contact matrix or contact matrices for individual sequence pairs, and is tested by leave-one-out cross validation. The performance averaged over a set of 115 DDIs collected from the 3 DID database shows significant improvement (sensitivity up to 85%, and specificity up to 85%), as compared with a multiple sequence alignment-based method (sensitivity 57%, and specificity 78%) previously reported in the literature.<\/jats:p><jats:p>Contact: \u00a0lliao@cis.udel.edu or wuc@cis.udel.edu<\/jats:p><jats:p>Supplementary information: \u00a0Supplementary data are available at Bioinformatics online.<\/jats:p>","DOI":"10.1093\/bioinformatics\/btt076","type":"journal-article","created":{"date-parts":[[2013,2,16]],"date-time":"2013-02-16T05:36:01Z","timestamp":1360992961000},"page":"1018-1025","source":"Crossref","is-referenced-by-count":16,"title":["Prediction of contact matrix for protein\u2013protein interaction"],"prefix":"10.1093","volume":"29","author":[{"given":"Alvaro J.","family":"Gonz\u00e1lez","sequence":"first","affiliation":[{"name":"Department of Computer and Information Sciences, University of Delaware, Newark, DE 19716, USA"}]},{"given":"Li","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Sciences, University of Delaware, Newark, DE 19716, USA"}]},{"given":"Cathy H.","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Sciences, University of Delaware, Newark, DE 19716, USA"}]}],"member":"286","published-online":{"date-parts":[[2013,2,15]]},"reference":[{"key":"2023012810304404800_btt076-B1","doi-asserted-by":"crossref","first-page":"5896","DOI":"10.1073\/pnas.092147999","article-title":"Interrogating protein interaction networks through structural biology","volume":"99","author":"Aloy","year":"2002","journal-title":"Proc. Natl Acad. Sci. U S A"},{"key":"2023012810304404800_btt076-B2","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The protein data bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res."},{"key":"2023012810304404800_btt076-B3","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1006\/jmbi.2000.3670","article-title":"SH3-SPOT: an algorithm to predict preferred ligands to different members of the SH3 gene family","volume":"298","author":"Brannetti","year":"2000","journal-title":"J. Mol. Biol."},{"key":"2023012810304404800_btt076-B4","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1038\/256705a0","article-title":"Principles of protein-protein recognition","volume":"256","author":"Chothia","year":"1975","journal-title":"Nature"},{"key":"2023012810304404800_btt076-B5","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1093\/bioinformatics\/14.9.755","article-title":"Profile hidden Markov models","volume":"14","author":"Eddy","year":"1998","journal-title":"Bioinformatics"},{"key":"2023012810304404800_btt076-B6","doi-asserted-by":"crossref","first-page":"2333","DOI":"10.1093\/bioinformatics\/btl403","article-title":"A novel structure-based encoding for machine-learning applied to the inference of SH3 domain specificity","volume":"22","author":"Ferraro","year":"2006","journal-title":"Bioinformatics"},{"key":"2023012810304404800_btt076-B7","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1093\/bioinformatics\/bti011","article-title":"iPfam: visualization of protein-protein interactions in PDB at domain and amino acid resolutions","volume":"21","author":"Finn","year":"2005","journal-title":"Bioinformatics"},{"key":"2023012810304404800_btt076-B8","doi-asserted-by":"crossref","first-page":"D211","DOI":"10.1093\/nar\/gkp985","article-title":"The Pfam protein families database","volume":"38","author":"Finn","year":"2010","journal-title":"Nucleic Acids Res. (Database Issue)"},{"key":"2023012810304404800_btt076-B9","doi-asserted-by":"crossref","first-page":"2851","DOI":"10.1093\/bioinformatics\/btl486","article-title":"Modeling interaction sites in protein domains with interaction profile hidden Markov models","volume":"22","author":"Friedrich","year":"2006","journal-title":"Bioinformatics"},{"key":"2023012810304404800_btt076-B10","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-00727-9_23","article-title":"Constrained Fisher scores derived from interaction profile hidden Markov models improve protein to protein interaction prediction","volume-title":"Proceedings of the First International Conference on Bioinformatics and Computational Biology (BICoB)","author":"Gonz\u00e1lez","year":"2009"},{"key":"2023012810304404800_btt076-B11","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1186\/1471-2105-11-537","article-title":"Predicting domain-domain interaction based on domain profiles with feature selection and support vector machines","volume":"11","author":"Gonz\u00e1lez","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2023012810304404800_btt076-B12","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1089\/10665270050081405","article-title":"A discriminative framework for detecting remote protein homologies","volume":"7","author":"Jaakkola","year":"1999","journal-title":"J. Computat. Biol"},{"key":"2023012810304404800_btt076-B13","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1073\/pnas.93.1.13","article-title":"Principles of protein-protein interactions","volume":"93","author":"Jones","year":"1996","journal-title":"Proc. Natl Acad. Sci. U S A"},{"key":"2023012810304404800_btt076-B14","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1109\/ICMLA.2005.24","article-title":"Discriminating transmembrane proteins from signal peptides using SVM-Fisher approach","volume-title":"The Proceedings of the Fourth International Conference on Machine Learning and Applications (ICMLA\u201905)","author":"Kahsay","year":"2005"},{"key":"2023012810304404800_btt076-B15","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1016\/S0969-2126(98)00044-6","article-title":"Morphology of protein-protein interfaces","volume":"6","author":"Larsen","year":"1998","journal-title":"Structure"},{"key":"2023012810304404800_btt076-B16","first-page":"745","article-title":"Protein sequence alignments: a strategy for the hierarchical analysis of residue conservation","volume":"9","author":"Livingstone","year":"1993","journal-title":"Comput. Appl. Biosci."},{"key":"2023012810304404800_btt076-B17","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":"2023012810304404800_btt076-B18","doi-asserted-by":"crossref","first-page":"9867","DOI":"10.1073\/pnas.0600220103","article-title":"Long-range cooperative binding effects in a T cell receptor variable domain","volume":"103","author":"Moza","year":"2006","journal-title":"Proc. Natl Acad. Sci. U S A"},{"key":"2023012810304404800_btt076-B19","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.1093\/embo-reports\/kvf221","article-title":"Arf, arl, arp and sar proteins: a family of gtp-binding proteins with a structural device for \u2018front-back\u2019 communication","volume":"3","author":"Pasqualato","year":"2002","journal-title":"EMBO Rep."},{"key":"2023012810304404800_btt076-B20","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","article-title":"A tutorial on hidden Markov models and selected applications in speech recognition","volume":"77","author":"Rabiner","year":"1989","journal-title":"Proc. IEEE"},{"key":"2023012810304404800_btt076-B21","doi-asserted-by":"crossref","first-page":"D656","DOI":"10.1093\/nar\/gkm761","article-title":"DOMINE: a database of protein domain interactions","volume":"36","author":"Raghavacharil","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2023012810304404800_btt076-B22","doi-asserted-by":"crossref","first-page":"D718","DOI":"10.1093\/nar\/gkq962","article-title":"3DID: identification and classification of domain-based interactions of known three-dimensional structure","volume":"39","author":"Stein","year":"2010","journal-title":"Nucleic Acids Res"},{"key":"2023012810304404800_btt076-B23","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1093\/bib\/bbp001","article-title":"A survey of available tools and web servers for analysis of protein-protein interactions and interfaces","volume":"10","author":"Tuncbag","year":"2009","journal-title":"Brief. Bioinform."},{"key":"2023012810304404800_btt076-B24","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":"2009","journal-title":"PNAS"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/29\/8\/1018\/48901374\/bioinformatics_29_8_1018.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/29\/8\/1018\/48901374\/bioinformatics_29_8_1018.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T21:28:45Z","timestamp":1745962125000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/29\/8\/1018\/227505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,2,15]]},"references-count":24,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2013,4,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btt076","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2013,4,15]]},"published":{"date-parts":[[2013,2,15]]}}}