{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T15:22:21Z","timestamp":1764688941813},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"13","license":[{"start":{"date-parts":[[2016,10,2]],"date-time":"2016-10-02T00:00:00Z","timestamp":1475366400000},"content-version":"vor","delay-in-days":1201,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/3.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Motivation: An important aspect of infectious disease research involves understanding the differences and commonalities in the infection mechanisms underlying various diseases. Systems biology-based approaches study infectious diseases by analyzing the interactions between the host species and the pathogen organisms. This work aims to combine the knowledge from experimental studies of host\u2013pathogen interactions in several diseases to build stronger predictive models. Our approach is based on a formalism from machine learning called \u2018multitask learning\u2019, which considers the problem of building models across tasks that are related to each other. A \u2018task\u2019 in our scenario is the set of host\u2013pathogen protein interactions involved in one disease. To integrate interactions from several tasks (i.e. diseases), our method exploits the similarity in the infection process across the diseases. In particular, we use the biological hypothesis that similar pathogens target the same critical biological processes in the host, in defining a common structure across the tasks.<\/jats:p>\n               <jats:p>Results: Our current work on host\u2013pathogen protein interaction prediction focuses on human as the host, and four bacterial species as pathogens. The multitask learning technique we develop uses a task-based regularization approach. We find that the resulting optimization problem is a difference of convex (DC) functions. To optimize, we implement a Convex\u2013Concave procedure-based algorithm. We compare our integrative approach to baseline methods that build models on a single host\u2013pathogen protein interaction dataset. Our results show that our approach outperforms the baselines on the training data. We further analyze the protein interaction predictions generated by the models, and find some interesting insights.<\/jats:p>\n               <jats:p>Availability: The predictions and code are available at: http:\/\/www.cs.cmu.edu\/\u223cmkshirsa\/ismb2013_paper320.html<\/jats:p>\n               <jats:p>Contact: \u00a0j.klein-seetharaman@warwick.ac.uk<\/jats:p>\n               <jats:p>Supplementary information: \u00a0Supplementary data are available at Bioinformatics online.<\/jats:p>","DOI":"10.1093\/bioinformatics\/btt245","type":"journal-article","created":{"date-parts":[[2013,6,27]],"date-time":"2013-06-27T05:33:26Z","timestamp":1372311206000},"page":"i217-i226","source":"Crossref","is-referenced-by-count":75,"title":["Multitask learning for host\u2013pathogen protein interactions"],"prefix":"10.1093","volume":"29","author":[{"given":"Meghana","family":"Kshirsagar","sequence":"first","affiliation":[]},{"given":"Jaime","family":"Carbonell","sequence":"additional","affiliation":[]},{"given":"Judith","family":"Klein-Seetharaman","sequence":"additional","affiliation":[]}],"member":"286","published-online":{"date-parts":[[2013,6,19]]},"reference":[{"key":"2023062614270766400_btt245-B1","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1038\/75556","article-title":"Gene ontology: tool for the unification of biology","volume":"25","author":"Ashburner","year":"2000","journal-title":"Nat. Genet."},{"key":"2023062614270766400_btt245-B2","doi-asserted-by":"crossref","first-page":"D1005","DOI":"10.1093\/nar\/gkq1184","article-title":"NCBI GEO: archive for functional genomics data sets\u201410 years on","volume":"39","author":"Barrett","year":"2011","journal-title":"Nucleic Acids Res."},{"key":"2023062614270766400_btt245-B3","doi-asserted-by":"crossref","first-page":"4394","DOI":"10.1093\/bioinformatics\/bti721","article-title":"Prediction of protein-protein interactions using random decision forest framework","volume":"21","author":"Chen","year":"2005","journal-title":"Bioinformatics"},{"key":"2023062614270766400_btt245-B4","doi-asserted-by":"crossref","first-page":"e34240","DOI":"10.1371\/journal.pone.0034240","article-title":"Associations between HIV and human pathways revealed by protein-protein interactions and correlated gene expression profiles","volume":"7","author":"Chen","year":"2012","journal-title":"PLoS One"},{"key":"2023062614270766400_btt245-B5","doi-asserted-by":"crossref","first-page":"D647","DOI":"10.1093\/nar\/gkn799","article-title":"Pig\u2013the pathogen interaction gateway","volume":"37","author":"Driscoll","year":"2009","journal-title":"Nucleic Acids Res."},{"key":"2023062614270766400_btt245-B6","doi-asserted-by":"crossref","first-page":"i159","DOI":"10.1093\/bioinformatics\/btm208","article-title":"Computational prediction of host-pathogen protein-protein interactions","volume":"23","author":"Dyer","year":"2007","journal-title":"Bioinformatics"},{"key":"2023062614270766400_btt245-B7","doi-asserted-by":"crossref","first-page":"e32","DOI":"10.1371\/journal.ppat.0040032","article-title":"The landscape of human proteins interacting with viruses and other pathogens","volume":"4","author":"Dyer","year":"2008","journal-title":"PLoS Pathog."},{"key":"2023062614270766400_btt245-B8","doi-asserted-by":"crossref","first-page":"e12089","DOI":"10.1371\/journal.pone.0012089","article-title":"The human-bacterial pathogen protein interaction networks of Bacillus anthracis, Francisella tularensis, and Yersinia pestis","volume":"5","author":"Dyer","year":"2010","journal-title":"PLoS One"},{"key":"2023062614270766400_btt245-B9","doi-asserted-by":"crossref","DOI":"10.1145\/1014052.1014067","article-title":"Regularized multi-task learning","volume-title":"SIGKDD","author":"Evgeniou","year":"2004"},{"key":"2023062614270766400_btt245-B10","first-page":"1871","article-title":"Liblinear: a library for large linear classification","volume":"9","author":"Fan","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"2023062614270766400_btt245-B11","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1186\/1471-2105-11-56","article-title":"Biana: a software framework for compiling biological interactions and analyzing networks","volume":"11","author":"Garcia","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2023062614270766400_btt245-B12","doi-asserted-by":"crossref","first-page":"e1001128","DOI":"10.1371\/journal.ppat.1001128","article-title":"Pathogenic bacteria target NEDD8-conjugated cullins to hijack host-cell signaling pathways","volume":"6","author":"Jubelin","year":"2010","journal-title":"PLoS Pathog."},{"key":"2023062614270766400_btt245-B13","doi-asserted-by":"crossref","first-page":"i466","DOI":"10.1093\/bioinformatics\/bts375","article-title":"Techniques to cope with missing data in host-pathogen protein interaction prediction","volume":"28","author":"Kshirsagar","year":"2012","journal-title":"Bioinformatics"},{"key":"2023062614270766400_btt245-B14","doi-asserted-by":"crossref","first-page":"S16","DOI":"10.1186\/1471-2105-11-S6-S16","article-title":"HPIDB\u2013a unified resource for host-pathogen interactions","volume":"11","author":"Kumar","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2023062614270766400_btt245-B15","doi-asserted-by":"crossref","first-page":"D619","DOI":"10.1093\/nar\/gkn863","article-title":"Reactome knowledgebase of human biological pathways and processes","volume":"37","author":"Matthews","year":"2009","journal-title":"Nucleic Acids Res."},{"key":"2023062614270766400_btt245-B16","doi-asserted-by":"crossref","first-page":"596","DOI":"10.1126\/science.1203659","article-title":"Independently evolved virulence effectors converge onto hubs in a plant immune system network","volume":"333","author":"Mukhtar","year":"2011","journal-title":"Science"},{"key":"2023062614270766400_btt245-B17","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1002\/prot.20865","article-title":"Evaluation of different biological data and computational classification methods for use in protein interaction prediction","volume":"63","author":"Qi","year":"2006","journal-title":"Proteins"},{"key":"2023062614270766400_btt245-B18","doi-asserted-by":"crossref","first-page":"5243","DOI":"10.1002\/pmic.200900259","article-title":"Systematic prediction of human membrane receptor interactions","volume":"23","author":"Qi","year":"2009","journal-title":"Proteomics"},{"key":"2023062614270766400_btt245-B19","doi-asserted-by":"crossref","first-page":"i645","DOI":"10.1093\/bioinformatics\/btq394","article-title":"Semi-supervised multi-task learning for predicting interactions between HIV-1 and human proteins","volume":"26","author":"Qi","year":"2010","journal-title":"Bioinformatics"},{"key":"2023062614270766400_btt245-B20","doi-asserted-by":"crossref","first-page":"D674","DOI":"10.1093\/nar\/gkn653","article-title":"PID: the pathway interaction database","volume":"37","author":"Schaefer","year":"2009","journal-title":"Nucleic Acids Res."},{"key":"2023062614270766400_btt245-B21","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1002\/prca.201100083","article-title":"The current salmonella-host interactome","volume":"6","author":"Schleker","year":"2012","journal-title":"Proteomics Clin. Appl."},{"key":"2023062614270766400_btt245-B22","doi-asserted-by":"crossref","DOI":"10.21236\/ADA486804","article-title":"Relational learning via collective matrix factorization","volume-title":"KDD","author":"Singh","year":"2008"},{"key":"2023062614270766400_btt245-B23","first-page":"403","article-title":"Struct2net: integrating structure into protein-protein interaction prediction","author":"Singh","year":"2006","journal-title":"Pac. Symp. Biocomput."},{"key":"2023062614270766400_btt245-B24","first-page":"516","article-title":"Prediction of interactions between HIV-1 and human proteins by information integration","author":"Tastan","year":"2009","journal-title":"Pac. Symp. Biocomput."},{"key":"2023062614270766400_btt245-B25","first-page":"46","article-title":"Infection strategies of bacterial and viral pathogens through pathogen-host protein\u2013protein interactions","volume":"3","author":"Tekir","year":"2012","journal-title":"Front. Microbiol."},{"key":"2023062614270766400_btt245-B26","doi-asserted-by":"crossref","first-page":"D214","DOI":"10.1093\/nar\/gkq1020","article-title":"Ongoing and future developments at the universal protein resource","volume":"39","author":"UniProt Consortium","year":"2011","journal-title":"Nucleic. Acids Res."},{"key":"2023062614270766400_btt245-B27","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1186\/1471-2105-8-391","article-title":"Analysis on multi-domain cooperation for predicting protein-protein interactions","volume":"8","author":"Wang","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"2023062614270766400_btt245-B28","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-12683-3_34","article-title":"Leveraging sequence classification by taxonomy-based multitask learning","volume-title":"RECOMB","author":"Widmer","year":"2010"},{"key":"2023062614270766400_btt245-B29","doi-asserted-by":"crossref","first-page":"D572","DOI":"10.1093\/nar\/gkm858","article-title":"Phi-base update: additions to the pathogen host interaction database","volume":"36","author":"Winnenburg","year":"2008","journal-title":"Nucleic Acids Res."},{"key":"2023062614270766400_btt245-B30","doi-asserted-by":"crossref","first-page":"2137","DOI":"10.1093\/nar\/gkl219","article-title":"Prediction of yeast protein-protein interaction network: insights from the gene ontology and annotations","volume":"34","author":"Wu","year":"2006","journal-title":"Nucleic Acids Res."},{"key":"2023062614270766400_btt245-B31","doi-asserted-by":"crossref","first-page":"257","DOI":"10.5626\/JCSE.2011.5.3.257","article-title":"A survey of transfer and multitask learning in bioinformatics","volume":"5","author":"Xu","year":"2011","journal-title":"J. Comput. Sci. Eng."},{"key":"2023062614270766400_btt245-B32","author":"Xu","year":"2010"},{"key":"2023062614270766400_btt245-B33","doi-asserted-by":"crossref","DOI":"10.1145\/1553374.1553523","article-title":"Learning structural SVMS with latent variables","volume-title":"International Conference on Machine Learning","author":"Yu","year":"2009"},{"key":"2023062614270766400_btt245-B34","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1162\/08997660360581958","article-title":"The concave-convex procedure","volume":"15","author":"Yuille","year":"2003","journal-title":"Neural Comput."}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/29\/13\/i217\/50702862\/bioinformatics_29_13_i217.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/29\/13\/i217\/50702862\/bioinformatics_29_13_i217.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T15:27:06Z","timestamp":1687793226000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/29\/13\/i217\/199627"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,6,19]]},"references-count":34,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2013,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btt245","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2013,7]]},"published":{"date-parts":[[2013,6,19]]}}}