{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T04:51:19Z","timestamp":1761540679847},"reference-count":15,"publisher":"Oxford University Press (OUP)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Motivation: Short well-defined domains known as peptide recognition modules (PRMs) regulate many important protein\u2013protein interactions involved in the formation of macromolecular complexes and biochemical pathways. Since high-throughput experiments like yeast two-hybrid and phage display are expensive and intrinsically noisy, it would be desirable to more specifically target or partially bypass them with complementary in silico approaches. In the present paper, we present a probabilistic discriminative approach to predicting PRM-mediated protein\u2013protein interactions from sequence data. The model is motivated by the discriminative model of Segal and Sharan as an alternative to the generative approach of Reiss and Schwikowski. In our evaluation, we focus on predicting the interaction network. As proposed by Williams, we overcome the problem of susceptibility to over-fitting by adopting a Bayesian a posteriori approach based on a Laplacian prior in parameter space.<\/jats:p>\n               <jats:p>Results: The proposed method was tested on two datasets of protein\u2013protein interactions involving 28 SH3 domain proteins in Saccharmomyces cerevisiae, where the datasets were obtained with different experimental techniques. The predictions were evaluated with out-of-sample receiver operator characteristic (ROC) curves. In both cases, Laplacian regularization turned out to be crucial for achieving a reasonable generalization performance. The Laplacian-regularized discriminative model outperformed the generative model of Reiss and Schwikowski in terms of the area under the ROC curve on both datasets. The performance was further improved with a hybrid approach, in which our model was initialized with the motifs obtained with the method of Reiss and Schwikowski.<\/jats:p>\n               <jats:p>Availability: Software and supplementary material is available from<\/jats:p>\n               <jats:p>Contact: \u00a0wlehrach@ed.ac.uk<\/jats:p>","DOI":"10.1093\/bioinformatics\/bti804","type":"journal-article","created":{"date-parts":[[2006,1,6]],"date-time":"2006-01-06T01:39:12Z","timestamp":1136511552000},"page":"532-540","source":"Crossref","is-referenced-by-count":18,"title":["A regularized discriminative model for the prediction of protein\u2013peptide interactions"],"prefix":"10.1093","volume":"22","author":[{"given":"Wolfgang P.","family":"Lehrach","sequence":"first","affiliation":[{"name":"University of Edinburgh 1 \u00a0 1 \u00a0 \u00a0 Edinburgh EH1 2QL, UK"},{"name":"Biomathematics and Statistics Scotland 2 \u00a0 2 \u00a0 \u00a0 Edinburgh EH9 3JZ, UK"}]},{"given":"Dirk","family":"Husmeier","sequence":"additional","affiliation":[{"name":"Biomathematics and Statistics Scotland 2 \u00a0 2 \u00a0 \u00a0 Edinburgh EH9 3JZ, UK"}]},{"given":"Christopher K. I.","family":"Williams","sequence":"additional","affiliation":[{"name":"University of Edinburgh 1 \u00a0 1 \u00a0 \u00a0 Edinburgh EH1 2QL, UK"}]}],"member":"286","published-online":{"date-parts":[[2006,1,5]]},"reference":[{"key":"2023012408522597800_b1","doi-asserted-by":"crossref","first-page":"1540","DOI":"10.1101\/gr.153002","article-title":"Inferring domain\u2013domain interactions from protein\u2013protein interactions","volume":"12","author":"Deng","year":"2002","journal-title":"Genome Res."},{"key":"2023012408522597800_b2","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1126\/science.8211139","article-title":"Detecting subtle sequence signals: a Gibbs sampling strategy for multiple alignment","volume":"262","author":"Lawrence","year":"1993","journal-title":"Science"},{"key":"2023012408522597800_b3","doi-asserted-by":"crossref","first-page":"1156","DOI":"10.1080\/01621459.1995.10476622","article-title":"Bayesian models for multiple local sequence alignment and Gibbs sampling strategies.","volume":"90","author":"Liu","year":"1995","journal-title":"J. Am. Stat. Assoc."},{"key":"2023012408522597800_b4","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1162\/neco.1992.4.3.415","article-title":"Bayesian interpolation","volume":"4","author":"MacKay","year":"1992","journal-title":"Neural Comput."},{"key":"2023012408522597800_b5","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.1162\/089976699300016331","article-title":"Comparsion of approximate methods for handling hyperparameters","volume":"11","author":"MacKay","year":"1999","journal-title":"Neural Comput."},{"key":"2023012408522597800_b6","volume-title":"NETLAB: Algorithms for Pattern Recognition","author":"Nabney","year":"2002"},{"key":"2023012408522597800_b7","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0745-0","volume-title":"Bayesian Learning for Neural Networks, Vol. 118, of Lecture Notes in Statistics","author":"Neal","year":"1996"},{"key":"2023012408522597800_b8","doi-asserted-by":"crossref","first-page":"2075","DOI":"10.1126\/science.278.5346.2075","article-title":"Signaling through scaffold, anchoring, and adaptor proteins","volume":"278","author":"Pawson","year":"1997","journal-title":"Science"},{"key":"2023012408522597800_b9","doi-asserted-by":"crossref","first-page":"i274","DOI":"10.1093\/bioinformatics\/bth922","article-title":"Predicting protein\u2013peptide interactions via a network-based motif sampler","volume":"20","author":"Reiss","year":"2004","journal-title":"Bioinformatics"},{"key":"2023012408522597800_b10","first-page":"263","article-title":"From Promoter Sequence to Expression: A Probabilistic Framework","author":"Segal","year":"2002"},{"key":"2023012408522597800_b11","first-page":"822","article-title":"A discriminative model for identifying spatial cis-regulatory modules","author":"Segal","year":"2004"},{"key":"2023012408522597800_b12","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1016\/S0092-8674(00)00203-8","article-title":"New wrinkles for an old domain","volume":"103","author":"Sudol","year":"2000","journal-title":"Cell"},{"key":"2023012408522597800_b13","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1126\/science.1064987","article-title":"A combined experimental and computational strategy to define protein interaction networks for peptide recognition modules","volume":"295","author":"Tong","year":"2002","journal-title":"Science"},{"key":"2023012408522597800_b14","doi-asserted-by":"crossref","DOI":"10.4324\/9780203507391","volume-title":"Principles of Proteomics","author":"Twyman","year":"2004"},{"key":"2023012408522597800_b15","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1162\/neco.1995.7.1.117","article-title":"Bayesian regularization and pruning using a Laplace prior","volume":"7","author":"Williams","year":"1995","journal-title":"Neural Comput."}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/22\/5\/532\/48838855\/bioinformatics_22_5_532.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/22\/5\/532\/48838855\/bioinformatics_22_5_532.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T09:29:29Z","timestamp":1674552569000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/22\/5\/532\/205219"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,1,5]]},"references-count":15,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2006,3,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bti804","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2006,3,1]]},"published":{"date-parts":[[2006,1,5]]}}}