Predicting MHC-II binding affinity using multiple instance regression EL-Manzalawy, Yasser Dobbs, Drena Honavar, Vasant Dobbs, Drena
dc.contributor.department Computer Science
dc.contributor.department Genetics, Development and Cell Biology
dc.contributor.department Bioinformatics and Computational Biology 2018-02-18T05:08:11.000 2020-06-30T04:01:10Z 2020-06-30T04:01:10Z Sat Jan 01 00:00:00 UTC 2011 2011-01-01
dc.description.abstract <p>Reliably predicting the ability of antigen peptides to bind to major histocompatibility complex class II (MHC-II) molecules is an essential step in developing new vaccines. Uncovering the amino acid sequence correlates of the binding affinity of MHC-II binding peptides is important for understanding pathogenesis and immune response. The task of predicting MHC-II binding peptides is complicated by the significant variability in their length. Most existing computational methods for predicting MHC-II binding peptides focus on identifying a nine amino acids core region in each binding peptide. We formulate the problems of qualitatively and quantitatively predicting flexible length MHC-II peptides as multiple instance learning and multiple instance regression problems, respectively. Based on this formulation, we introduce MHCMIR, a novel method for predicting MHC-II binding affinity using multiple instance regression. We present results of experiments using several benchmark datasets that show that MHCMIR is competitive with the state-of-the-art methods for predicting MHC-II binding peptides. An online web server that implements the MHCMIR method for MHC-II binding affinity prediction is freely accessible at</p>
dc.description.comments <p>This article is from <em>IEEE/ACM Transactions on Computational Biology and Bioinformatics </em>8 (2011): 1067, doi: <a href="" target="_blank">10.1109/TCBB.2010.94</a>. Posted with permission.</p>
dc.format.mimetype application/pdf
dc.identifier archive/
dc.identifier.articleid 1121
dc.identifier.contextkey 9776951
dc.identifier.s3bucket isulib-bepress-aws-west
dc.identifier.submissionpath gdcb_las_pubs/118
dc.language.iso en
dc.source.bitstream archive/|||Fri Jan 14 18:58:37 UTC 2022
dc.source.uri 10.1109/TCBB.2010.94
dc.subject.disciplines Bioinformatics
dc.subject.disciplines Cell and Developmental Biology
dc.subject.disciplines Computational Biology
dc.subject.disciplines Genetics and Genomics
dc.subject.disciplines Molecular Genetics
dc.subject.keywords MHC-II peptide prediction
dc.subject.keywords multiple instance learning
dc.subject.keywords multiple instance regression
dc.title Predicting MHC-II binding affinity using multiple instance regression
dc.type article
dc.type.genre article
dspace.entity.type Publication
relation.isAuthorOfPublication 7e096c4f-9007-41e4-9414-989c3ea9bc88
relation.isOrgUnitOfPublication f7be4eb9-d1d0-4081-859b-b15cee251456
relation.isOrgUnitOfPublication 9e603b30-6443-4b8e-aff5-57de4a7e4cb2
relation.isOrgUnitOfPublication c331f825-0643-499a-9eeb-592c7b43b1f5
Original bundle
Now showing 1 - 1 of 1
531.08 KB
Adobe Portable Document Format