{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T23:23:02Z","timestamp":1773271382586,"version":"3.50.1"},"reference-count":28,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2016,10,2]],"date-time":"2016-10-02T00:00:00Z","timestamp":1475366400000},"content-version":"vor","delay-in-days":2876,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/2.0\/uk\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,1,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Motivation: An important problem in systems biology is reconstructing complete networks of interactions between biological objects by extrapolating from a few known interactions as examples. While there are many computational techniques proposed for this network reconstruction task, their accuracy is consistently limited by the small number of high-confidence examples, and the uneven distribution of these examples across the potential interaction space, with some objects having many known interactions and others few.<\/jats:p>\n               <jats:p>Results: To address this issue, we propose two computational methods based on the concept of training set expansion. They work particularly effectively in conjunction with kernel approaches, which are a popular class of approaches for fusing together many disparate types of features. Both our methods are based on semi-supervised learning and involve augmenting the limited number of gold-standard training instances with carefully chosen and highly confident auxiliary examples. The first method, prediction propagation, propagates highly confident predictions of one local model to another as the auxiliary examples, thus learning from information-rich regions of the training network to help predict the information-poor regions. The second method, kernel initialization, takes the most similar and most dissimilar objects of each object in a global kernel as the auxiliary examples. Using several sets of experimentally verified protein\u2013protein interactions from yeast, we show that training set expansion gives a measurable performance gain over a number of representative, state-of-the-art network reconstruction methods, and it can correctly identify some interactions that are ranked low by other methods due to the lack of training examples of the involved proteins.<\/jats:p>\n               <jats:p>Contact: \u00a0mark.gerstein@yale.edu<\/jats:p>\n               <jats:p>Availability: The datasets and additional materials can be found at http:\/\/networks.gersteinlab.org\/tse.<\/jats:p>","DOI":"10.1093\/bioinformatics\/btn602","type":"journal-article","created":{"date-parts":[[2008,11,18]],"date-time":"2008-11-18T01:13:50Z","timestamp":1226970830000},"page":"243-250","source":"Crossref","is-referenced-by-count":23,"title":["Training set expansion: an approach to improving the reconstruction of biological networks from limited and uneven reliable interactions"],"prefix":"10.1093","volume":"25","author":[{"given":"Kevin Y.","family":"Yip","sequence":"first","affiliation":[{"name":"1 Department of Computer Science, Yale University, 51 Prospect Street, New Haven, CT 06511, 2Program in Computational Biology and Bioinformatics, Yale University and 3Department of Molecular Biophysics and Biochemistry, Yale University, 266 Whitney Avenue, New Haven, CT 06520, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Gerstein","sequence":"additional","affiliation":[{"name":"1 Department of Computer Science, Yale University, 51 Prospect Street, New Haven, CT 06511, 2Program in Computational Biology and Bioinformatics, Yale University and 3Department of Molecular Biophysics and Biochemistry, Yale University, 266 Whitney Avenue, New Haven, CT 06520, USA"},{"name":"1 Department of Computer Science, Yale University, 51 Prospect Street, New Haven, CT 06511, 2Program in Computational Biology and Bioinformatics, Yale University and 3Department of Molecular Biophysics and Biochemistry, Yale University, 266 Whitney Avenue, New Haven, CT 06520, USA"},{"name":"1 Department of Computer Science, Yale University, 51 Prospect Street, New Haven, CT 06511, 2Program in Computational Biology and Bioinformatics, Yale University and 3Department of Molecular Biophysics and Biochemistry, Yale University, 266 Whitney Avenue, New Haven, CT 06520, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2008,11,17]]},"reference":[{"key":"2023013110004469700_B1","first-page":"821","article-title":"Theoretical foundations of the potential function method in pattern recognition learning.","volume":"25","author":"Aizerman","year":"1964","journal-title":"Automat. Rem. Contr."},{"key":"2023013110004469700_B2","doi-asserted-by":"crossref","first-page":"i38","DOI":"10.1093\/bioinformatics\/bti1016","article-title":"Kernel methods for predicting protein-protein interactions.","volume":"21","author":"Ben-Hur","year":"2005","journal-title":"Bioinformatics"},{"key":"2023013110004469700_B3","doi-asserted-by":"crossref","first-page":"i57","DOI":"10.1093\/bioinformatics\/btm204","article-title":"Supervised reconstruction of biological networks with local models.","volume":"23","author":"Bleakley","year":"2007","journal-title":"Bioinformatics"},{"key":"2023013110004469700_B4","doi-asserted-by":"crossref","DOI":"10.1145\/279943.279962","article-title":"Combining labeled and unlabeled data with co-training.","volume-title":"The Eleventh Annual Workshop on Computational Learning Theory.","author":"Blum","year":"1998"},{"key":"2023013110004469700_B5","unstructured":"Chang\n              C-C\n            \n            \u00a0LinC-J\n          LIBSVM: a library for support vector machine.\n          2008\n          (last accessed date on October 2008)\n          Available at http:\/\/www.csie.ntu.edu.tw\/~cjlin\/papers\/libsvm.pdf"},{"key":"2023013110004469700_B6","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/9780262033589.001.0001","volume-title":"Semi-Supervised Learning.","author":"Chapelle","year":"2006"},{"key":"2023013110004469700_B7","doi-asserted-by":"crossref","first-page":"4241","DOI":"10.1091\/mbc.11.12.4241","article-title":"Genomic expression programs in the response of yeast cells to environmental changes.","volume":"11","author":"Gasch","year":"2000","journal-title":"Mol. Biol. Cell"},{"key":"2023013110004469700_B8","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1038\/nature04532","article-title":"Proteome survey reveals modularity of the yeast cell machinery.","volume":"440","author":"Gavin","year":"2006","journal-title":"Nature"},{"key":"2023013110004469700_B9","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1038\/nature00935","article-title":"Functional profiling of the Saccharomyces cerevisiae genome.","volume":"418","author":"Giaever","year":"2002","journal-title":"Nature"},{"key":"2023013110004469700_B10","doi-asserted-by":"crossref","first-page":"e214","DOI":"10.1371\/journal.pcbi.0030214","article-title":"Where have all the interactions gone? Estimating the coverage of two-hybrid protein interaction maps.","volume":"3","author":"Huang","year":"2007","journal-title":"PLoS Comput. Biol"},{"key":"2023013110004469700_B11","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1038\/nature02026","article-title":"Global analysis of protein localization in budding yeast.","volume":"425","author":"Huh","year":"2003","journal-title":"Nature"},{"key":"2023013110004469700_B12","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1073\/pnas.97.3.1143","article-title":"Toward a protein-protein interaction map of the budding yeast: A comprehensive system to examine two-hybrid interactions in all possible combinations between the yeast proteins.","volume":"97","author":"Ito","year":"2000","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2023013110004469700_B13","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1038\/nature04670","article-title":"Global landscape of protein complexes in the yeast Saccharomyces cerevisiae.","volume":"440","author":"Krogan","year":"2006","journal-title":"Nature"},{"key":"2023013110004469700_B14","doi-asserted-by":"crossref","first-page":"2626","DOI":"10.1093\/bioinformatics\/bth294","article-title":"A statistical framework for genomic data fusion.","volume":"20","author":"Lanckriet","year":"2004","journal-title":"Bioinformatics"},{"key":"2023013110004469700_B15","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1098\/rsta.1909.0016","article-title":"Functions of positive and negative type, and their connection with the theory of integral equations.","volume":"209","author":"Mercer","year":"1909","journal-title":"Philos. Trans. R. Soc. Lond."},{"key":"2023013110004469700_B16","doi-asserted-by":"crossref","first-page":"2322","DOI":"10.1093\/bioinformatics\/btm332","article-title":"Context-sensitive data integration and prediction of biological networks.","volume":"23","author":"Myers","year":"2007","journal-title":"Bioinformatics"},{"key":"2023013110004469700_B17","doi-asserted-by":"crossref","first-page":"e1000054","DOI":"10.1371\/journal.pcbi.1000054","article-title":"Predicting co-complexed protein pairs from heterogeneous data.","volume":"4","author":"Qiu","year":"2008","journal-title":"PLoS Comput. Biol"},{"key":"2023013110004469700_B18","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4057.001.0001","volume-title":"Kernel Methods in Computational Biology.","author":"Sch\u00f6lkopf","year":"2004"},{"key":"2023013110004469700_B19","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1023\/B:STCO.0000035301.49549.88","article-title":"A tutorial on support vector regression.","volume":"14","author":"Smola","year":"2004","journal-title":"Stat. Comput."},{"key":"2023013110004469700_B20","doi-asserted-by":"crossref","first-page":"3273","DOI":"10.1091\/mbc.9.12.3273","article-title":"Comprehensive identification of cell cycle-regulated genes of the yeast Saccharomyces cerevisiae by microarray hybridization.","volume":"9","author":"Spellman","year":"1998","journal-title":"Mol. Biol. Cell"},{"key":"2023013110004469700_B21","doi-asserted-by":"crossref","first-page":"D535","DOI":"10.1093\/nar\/gkj109","article-title":"BioGRID: a general repository for interaction datasets.","volume":"34","author":"Stark","year":"2006","journal-title":"Nucleic Acids Res."},{"key":"2023013110004469700_B22","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1126\/science.278.5338.631","article-title":"A genomic perspective on protein families.","volume":"278","author":"Tatusov","year":"1997","journal-title":"Science"},{"key":"2023013110004469700_B23","first-page":"67","article-title":"The algorithm for kernel matrix completion with auxiliary data.","volume":"4","author":"Tsuda","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"2023013110004469700_B24","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1038\/35001009","article-title":"A comprehensive analysis of protein-protein interactions in Saccharomyces cerevisiae.","volume":"403","author":"Uetz","year":"2000","journal-title":"Nature"},{"key":"2023013110004469700_B25","first-page":"1433","article-title":"Supervised graph inference.","volume-title":"Advances in Neural Information Processing Systems 17.","author":"Vert","year":"2005"},{"key":"2023013110004469700_B26","doi-asserted-by":"crossref","first-page":"i363","DOI":"10.1093\/bioinformatics\/bth910","article-title":"Protein network inference from multiple genomic data: a supervised approach.","volume":"20","author":"Yamanishi","year":"2004","journal-title":"Bioinformatics"},{"key":"2023013110004469700_B27","doi-asserted-by":"crossref","first-page":"i468","DOI":"10.1093\/bioinformatics\/bti1012","article-title":"Supervised enzyme network inference from the integration of genomic data and chemical information.","volume":"21","author":"Yamanishi","year":"2005","journal-title":"Bioinformatics"},{"key":"2023013110004469700_B28","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1126\/science.1158684","article-title":"High-quality binary protein interaction map of the yeast interactome network.","volume":"322","author":"Yu","year":"2008","journal-title":"Science"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/25\/2\/243\/48983145\/bioinformatics_25_2_243.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/25\/2\/243\/48983145\/bioinformatics_25_2_243.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T18:44:04Z","timestamp":1675190644000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/25\/2\/243\/218869"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,11,17]]},"references-count":28,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2009,1,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btn602","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2009,1,15]]},"published":{"date-parts":[[2008,11,17]]}}}