{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T10:12:10Z","timestamp":1774260730404,"version":"3.50.1"},"reference-count":37,"publisher":"Oxford University Press (OUP)","issue":"18","license":[{"start":{"date-parts":[[2016,10,2]],"date-time":"2016-10-02T00:00:00Z","timestamp":1475366400000},"content-version":"vor","delay-in-days":2220,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/2.0\/uk\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,9,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Motivation: Protein\u2013protein interactions (PPIs) are critical for virtually every biological function. Recently, researchers suggested to use supervised learning for the task of classifying pairs of proteins as interacting or not. However, its performance is largely restricted by the availability of truly interacting proteins (labeled). Meanwhile, there exists a considerable amount of protein pairs where an association appears between two partners, but not enough experimental evidence to support it as a direct interaction (partially labeled).<\/jats:p>\n               <jats:p>Results: We propose a semi-supervised multi-task framework for predicting PPIs from not only labeled, but also partially labeled reference sets. The basic idea is to perform multi-task learning on a supervised classification task and a semi-supervised auxiliary task. The supervised classifier trains a multi-layer perceptron network for PPI predictions from labeled examples. The semi-supervised auxiliary task shares network layers of the supervised classifier and trains with partially labeled examples. Semi-supervision could be utilized in multiple ways. We tried three approaches in this article, (i) classification (to distinguish partial positives with negatives); (ii) ranking (to rate partial positive more likely than negatives); (iii) embedding (to make data clusters get similar labels). We applied this framework to improve the identification of interacting pairs between HIV-1 and human proteins. Our method improved upon the state-of-the-art method for this task indicating the benefits of semi-supervised multi-task learning using auxiliary information.<\/jats:p>\n               <jats:p>Availability: \u00a0http:\/\/www.cs.cmu.edu\/\u223cqyj\/HIVsemi<\/jats:p>\n               <jats:p>Contact: \u00a0qyj@cs.cmu.edu<\/jats:p>","DOI":"10.1093\/bioinformatics\/btq394","type":"journal-article","created":{"date-parts":[[2010,9,7]],"date-time":"2010-09-07T17:41:46Z","timestamp":1283881306000},"page":"i645-i652","source":"Crossref","is-referenced-by-count":108,"title":["Semi-supervised multi-task learning for predicting interactions between HIV-1 and human proteins"],"prefix":"10.1093","volume":"26","author":[{"given":"Yanjun","family":"Qi","sequence":"first","affiliation":[{"name":"1 NEC Labs America, 4 Independence Way, Princeton, NJ 08540, 2School of Computer Science, Carnegie Mellon University, PA 15213 and 3Google Research NY, 75 Ninth Avenue, New York, NY 10011, USA"}]},{"given":"Oznur","family":"Tastan","sequence":"additional","affiliation":[{"name":"1 NEC Labs America, 4 Independence Way, Princeton, NJ 08540, 2School of Computer Science, Carnegie Mellon University, PA 15213 and 3Google Research NY, 75 Ninth Avenue, New York, NY 10011, USA"}]},{"given":"Jaime G.","family":"Carbonell","sequence":"additional","affiliation":[{"name":"1 NEC Labs America, 4 Independence Way, Princeton, NJ 08540, 2School of Computer Science, Carnegie Mellon University, PA 15213 and 3Google Research NY, 75 Ninth Avenue, New York, NY 10011, USA"}]},{"given":"Judith","family":"Klein-Seetharaman","sequence":"additional","affiliation":[{"name":"1 NEC Labs America, 4 Independence Way, Princeton, NJ 08540, 2School of Computer Science, Carnegie Mellon University, PA 15213 and 3Google Research NY, 75 Ninth Avenue, New York, NY 10011, USA"}]},{"given":"Jason","family":"Weston","sequence":"additional","affiliation":[{"name":"1 NEC Labs America, 4 Independence Way, Princeton, NJ 08540, 2School of Computer Science, Carnegie Mellon University, PA 15213 and 3Google Research NY, 75 Ninth Avenue, New York, NY 10011, USA"}]}],"member":"286","published-online":{"date-parts":[[2010,9,4]]},"reference":[{"key":"2023012508274065500_B1","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":"2023012508274065500_B2","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1126\/science.1152725","article-title":"Identification of host proteins required for hiv infection through a functional genomic screen","volume":"319","author":"Brass","year":"2008","journal-title":"Science"},{"key":"2023012508274065500_B3","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"2023012508274065500_B4","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Mach. Learn."},{"key":"2023012508274065500_B5","volume-title":"Semi-Supervised Learning (Adaptive Computation and Machine Learning).","author":"Chapelle","year":"2006"},{"key":"2023012508274065500_B6","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1038\/nmeth.1284","article-title":"Literature-curated protein interaction datasets","volume":"6","author":"Cusick","year":"2008","journal-title":"Nat. Methods"},{"key":"2023012508274065500_B7","doi-asserted-by":"crossref","first-page":"2585","DOI":"10.1110\/ps.073228407","article-title":"Host pathogen protein interactions predicted by comparative modeling","volume":"16","author":"Davis","year":"2007","journal-title":"Protein Sci."},{"key":"2023012508274065500_B8","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/1755-8794-2-27","article-title":"Prediction of HIV-1 virus-host protein interactions using virus and host sequence motifs","volume":"2","author":"Evans","year":"2009","journal-title":"BMC Med. Genomics"},{"key":"2023012508274065500_B9","doi-asserted-by":"crossref","first-page":"D417","DOI":"10.1093\/nar\/gkn708","article-title":"Human immunodeficiency virus type 1, human protein interaction database at NCBI","volume":"37","author":"Fu","year":"2008","journal-title":"Nucleic Acids Res."},{"key":"2023012508274065500_B10","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/415141a","article-title":"Functional organization of the yeast proteome by systematic analysis of protein complexes","volume":"415","author":"Gavin","year":"2002","journal-title":"Nature"},{"key":"2023012508274065500_B11","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":"2023012508274065500_B12","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1038\/415180a","article-title":"Systematic identification of protein complexes in Saccharomyces cerevisiae by mass spectrometry","volume":"415","author":"Ho","year":"2002","journal-title":"Nature"},{"key":"2023012508274065500_B13","doi-asserted-by":"crossref","first-page":"4569","DOI":"10.1073\/pnas.061034498","article-title":"A comprehensive two-hybrid analysis to explore the yeast proteininteractome","volume":"98","author":"Ito","year":"2001","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2023012508274065500_B14","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1126\/science.1087361","article-title":"A bayesian networks approach for predicting protein-protein interactions from genomic data","volume":"302","author":"Jansen","year":"2003","journal-title":"Science"},{"key":"2023012508274065500_B15","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.cell.2008.07.032","article-title":"Global analysis of host-pathogen interactions that regulate early-stage hiv-1 replication","volume":"135","author":"K\u00f6nig","year":"2008","journal-title":"Cell"},{"key":"2023012508274065500_B16","doi-asserted-by":"crossref","first-page":"1555","DOI":"10.1126\/science.1099511","article-title":"A probabilistic functional network of yeast genes","volume":"306","author":"Lee","year":"2004","journal-title":"Science"},{"key":"2023012508274065500_B17","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1186\/1471-2105-5-154","article-title":"Information assessment on predicting protein-protein interactions","volume":"5","author":"Lin","year":"2004","journal-title":"BMC Bioinformatics"},{"key":"2023012508274065500_B18","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1002\/rmv.570","article-title":"Cellular proteins detected in hiv-1","volume":"18","author":"Ott","year":"2008","journal-title":"Rev. Med. Virol."},{"key":"2023012508274065500_B19","first-page":"531","article-title":"Random forest similarity for protein-protein interaction prediction from multiple sources","volume":"10","author":"Qi","year":"2005","journal-title":"Proc. Pac. Symp. Biocomput."},{"key":"2023012508274065500_B20","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1038\/nbt1103","article-title":"Probabilistic model of the human protein-protein interaction network","volume":"8","author":"Rhodes","year":"2005","journal-title":"Nat. Biotechnol."},{"key":"2023012508274065500_B21","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.1038\/nature04209","article-title":"Towards a proteome-scale map of the human protein-protein interaction network","volume":"437","author":"Rual","year":"2005","journal-title":"Nature"},{"key":"2023012508274065500_B22","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1186\/1471-2105-8-239","article-title":"Probabilistic prediction and ranking of human protein-protein interactions","volume":"8","author":"Scott","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"2023012508274065500_B23","doi-asserted-by":"crossref","first-page":"e42","DOI":"10.1371\/journal.pcbi.0030042","article-title":"Deciphering protein-protein interactions. part i. experimental techniques and databases","volume":"3","author":"Shoemaker","year":"2007","journal-title":"PLoS Comput. Biol."},{"key":"2023012508274065500_B24","doi-asserted-by":"crossref","first-page":"e43","DOI":"10.1371\/journal.pcbi.0030043","article-title":"Deciphering protein-protein interactions. part ii. computational methods to predict protein and domain interaction partners","volume":"3","author":"Shoemaker","year":"2007","journal-title":"PLoS Comput. Biol."},{"key":"2023012508274065500_B25","doi-asserted-by":"crossref","first-page":"830","DOI":"10.1016\/j.cell.2005.08.029","article-title":"A human protein-protein interaction network: a resource for annotating the proteome","volume":"122","author":"Stelzl","year":"2005","journal-title":"Cell"},{"key":"2023012508274065500_B26","first-page":"516","article-title":"Prediction of interactions between HIV-1 and human proteins by information integration","volume":"14","author":"Tastan","year":"2009","journal-title":"Pac. Symp. Biocomput."},{"key":"2023012508274065500_B27","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1016\/j.mib.2004.08.001","article-title":"HIV-host interactions: vital to the virus and key to its inhibition","volume":"7","author":"Trkola","year":"2004","journal-title":"Curr. Opin. Microbiol."},{"key":"2023012508274065500_B28","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":"2023012508274065500_B29","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1038\/nature750","article-title":"Comparative assessment of large-scale data sets of protein-protein interactions","volume":"417","author":"von Mering","year":"2002","journal-title":"Nature"},{"key":"2023012508274065500_B30","doi-asserted-by":"crossref","first-page":"R192.1","DOI":"10.1186\/gb-2007-8-9-r192","article-title":"InSite: a computational method for identifying protein-protein interaction binding sites on a proteome-wide scale","volume":"8","author":"Wang","year":"2007","journal-title":"Genome Biol."},{"key":"2023012508274065500_B31","doi-asserted-by":"crossref","first-page":"1168","DOI":"10.1145\/1390156.1390303","article-title":"Deep learning via semi-supervised embedding","volume-title":"ICML '08: Proceedings of the 25th International Conference on Machine Learning.","author":"Weston","year":"2008"},{"key":"2023012508274065500_B32","doi-asserted-by":"crossref","first-page":"363","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":"2023012508274065500_B33","doi-asserted-by":"crossref","first-page":"19463","DOI":"10.1074\/jbc.M109.010033","article-title":"A genome-wide short hairpin rna screening of jurkat T-cells for human proteins contributing to productive HIV-1 replication","volume":"284","author":"Yeung","year":"2009","journal-title":"J. Biol. Chem."},{"key":"2023012508274065500_B34","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1093\/bioinformatics\/btn602","article-title":"Training set expansion: an approach to improving the reconstruction of biological networks from limited and uneven reliable interactions","volume":"25","author":"Yip","year":"2009","journal-title":"Bioinformatics"},{"key":"2023012508274065500_B35","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"},{"key":"2023012508274065500_B36","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1186\/1471-2105-5-38","article-title":"Predicting co-complexed protein pairs using genomic and proteomic data integration","volume":"5","author":"Zhang","year":"2004","journal-title":"BMC Bioinformatics"},{"key":"2023012508274065500_B37","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1016\/j.chom.2008.10.004","article-title":"Genome-scale rnai screen for host factors required for hiv replication","volume":"4","author":"Zhou","year":"2008","journal-title":"Cell Host Microbe"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/26\/18\/i645\/48858607\/bioinformatics_26_18_i645.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/26\/18\/i645\/48858607\/bioinformatics_26_18_i645.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T08:28:08Z","timestamp":1674635288000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/26\/18\/i645\/207083"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,9,4]]},"references-count":37,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2010,9,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btq394","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2010,9,15]]},"published":{"date-parts":[[2010,9,4]]}}}