{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T01:15:59Z","timestamp":1752282959350},"reference-count":25,"publisher":"Oxford University Press (OUP)","issue":"22","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,11,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Motivation: Effective computational methods for peptide-protein binding prediction can greatly help clinical peptide vaccine search and design. However, previous computational methods fail to capture key nonlinear high-order dependencies between different amino acid positions. As a result, they often produce low-quality rankings of strong binding peptides. To solve this problem, we propose nonlinear high-order machine learning methods including high-order neural networks (HONNs) with possible deep extensions and high-order kernel support vector machines to predict major histocompatibility complex-peptide binding.<\/jats:p>\n               <jats:p>Results: The proposed high-order methods improve quality of binding predictions over other prediction methods. With the proposed methods, a significant gain of up to 25\u201340% is observed on the benchmark and reference peptide datasets and tasks. In addition, for the first time, our experiments show that pre-training with high-order semi-restricted Boltzmann machines significantly improves the performance of feed-forward HONNs. Moreover, our experiments show that the proposed shallow HONN outperform the popular pre-trained deep neural network on most tasks, which demonstrates the effectiveness of modelling high-order feature interactions for predicting major histocompatibility complex-peptide binding.<\/jats:p>\n               <jats:p>Availability and implementation: There is no associated distributable software.<\/jats:p>\n               <jats:p>Contact: \u00a0renqiang@nec-labs.com or mark.gerstein@yale.edu<\/jats:p>\n               <jats:p>Supplementary information: Supplementary data are available at Bioinformatics online.<\/jats:p>","DOI":"10.1093\/bioinformatics\/btv371","type":"journal-article","created":{"date-parts":[[2015,7,24]],"date-time":"2015-07-24T00:53:42Z","timestamp":1437699222000},"page":"3600-3607","source":"Crossref","is-referenced-by-count":30,"title":["High-order neural networks and kernel methods for peptide-MHC binding prediction"],"prefix":"10.1093","volume":"31","author":[{"given":"Pavel P.","family":"Kuksa","sequence":"first","affiliation":[{"name":"1 Institute for Biomedical Informatics,"},{"name":"2 Department of Pathology and Laboratory Medicine, University of Pennsylvania School of Medicine, Philadelphia, PA 19104, USA,"},{"name":"3 Department of Machine Learning, NEC Laboratories America, Princeton, NJ 08540, USA,"}]},{"given":"Martin Renqiang","family":"Min","sequence":"additional","affiliation":[{"name":"3 Department of Machine Learning, NEC Laboratories America, Princeton, NJ 08540, USA,"}]},{"given":"Rishabh","family":"Dugar","sequence":"additional","affiliation":[{"name":"3 Department of Machine Learning, NEC Laboratories America, Princeton, NJ 08540, USA,"}]},{"given":"Mark","family":"Gerstein","sequence":"additional","affiliation":[{"name":"4 Program of Computational Biology and Bioinformatics and"},{"name":"5 Department of Molecular Biophysics and Biochemistry and"},{"name":"6 Department of Computer Science, Yale University, New Haven, CT 06511, USA"}]}],"member":"286","published-online":{"date-parts":[[2015,7,23]]},"reference":[{"key":"2023020202420514000_btv371-B1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000006","article-title":"Learning deep architectures for ai","volume":"2","author":"Bengio","year":"2009","journal-title":"Found. Trends Mach. Learn."},{"key":"2023020202420514000_btv371-B2","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1046\/j.1440-1711.2002.01088.x","article-title":"Prediction of promiscuous peptides that bind HLA class I molecules","volume":"80","author":"Brusic","year":"2002","journal-title":"Immunol. Cell Biol."},{"key":"2023020202420514000_btv371-B3","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1034\/j.1399-0039.2003.00112.x","article-title":"Sensitive quantitative predictions of peptide-MHC binding by a \u2018Query by Committee\u2019 artificial neural network approach","volume":"62","author":"Buus","year":"2003","journal-title":"Tissue Antigens"},{"key":"2023020202420514000_btv371-B4","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1002\/eji.200535424","article-title":"Crystal structure of HLA-A*2402 complexed with a telomerase peptide","volume":"36","author":"Cole","year":"2006","journal-title":"Eur. J. Immunol."},{"key":"2023020202420514000_btv371-B5","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1186\/1471-2105-14-82","article-title":"Learning a peptide-protein binding affinity predictor with kernel ridge regression","volume":"14","author":"Giguere","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"2023020202420514000_btv371-B6","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.jim.2013.10.003","article-title":"MHC-NP: Predicting peptides naturally processed by the MHC","volume":"400401","author":"Gigure","year":"2013","journal-title":"J. Immunol. Methods"},{"key":"2023020202420514000_btv371-B7","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1162\/089976602760128018","article-title":"Training products of experts by minimizing contrastive divergence","volume":"14","author":"Hinton","year":"2002","journal-title":"Neural Comput."},{"key":"2023020202420514000_btv371-B8","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","article-title":"A fast learning algorithm for deep belief nets","volume":"18","author":"Hinton","year":"2006","journal-title":"Neural Comput."},{"key":"2023020202420514000_btv371-B9","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1098\/rstb.2009.0200","article-title":"Learning to represent visual input","volume":"365","author":"Hinton","year":"2010","journal-title":"Philos. Trans. R. Soc. B Biol. Sci."},{"key":"2023020202420514000_btv371-B10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00251-008-0341-z","article-title":"NetMHCpan, a method for MHC class I binding prediction beyond humans","volume":"61","author":"Hoof","year":"2009","journal-title":"Immunogenetics"},{"key":"2023020202420514000_btv371-B11","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1186\/1471-2105-15-241","article-title":"Dataset size and composition impact the reliability of performance benchmarks for peptide-MHC binding predictions","volume":"15","author":"Kim","year":"2014","journal-title":"BMC Bioinformatics"},{"key":"2023020202420514000_btv371-B12","first-page":"283","article-title":"In silico prediction of peptide-MHC binding affinity using SVRMHC","volume-title":"Immunoinformatics, Volume 409 of Methods in Molecular Biology","author":"Liu","year":"2007"},{"key":"2023020202420514000_btv371-B13","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.jim.2010.10.011","article-title":"Prediction of epitopes using neural network based methods","volume":"374","author":"Lundegaard","year":"2011","journal-title":"J. Immunol. Methods"},{"key":"2023020202420514000_btv371-B15","first-page":"791","article-title":"Deep supervised t-distributed embedding","volume-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel, June 21\u201324, 2010","author":"Min","year":"2010"},{"key":"2023020202420514000_btv371-B16","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1110\/ps.0239403","article-title":"Reliable prediction of T-cell epitopes using neural networks with novel sequence representations","volume":"12","author":"Nielsen","year":"2003","journal-title":"Protein Sci."},{"key":"2023020202420514000_btv371-B17","doi-asserted-by":"crossref","first-page":"1388","DOI":"10.1093\/bioinformatics\/bth100","article-title":"Improved prediction of MHC class I and class II epitopes using a novel Gibbs sampling approach","volume":"20","author":"Nielsen","year":"2004","journal-title":"Bioinformatics"},{"key":"2023020202420514000_btv371-B18","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1186\/1471-2105-6-132","article-title":"Generating quantitative models describing the sequence specificity of biological processes with the stabilized matrix method","volume":"6","author":"Peters","year":"2005","journal-title":"BMC Bioinformatics"},{"key":"2023020202420514000_btv371-B19","doi-asserted-by":"crossref","first-page":"2206","DOI":"10.1109\/TPAMI.2013.29","article-title":"Modeling natural images using gated MRFs","volume":"35","author":"Ranzato","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2023020202420514000_btv371-B20","first-page":"185","article-title":"Prediction of peptide-MHC binding using profiles","volume-title":"Immunoinformatics, Volume 409 of Methods in Molecular Biology","author":"Reche","year":"2007"},{"key":"2023020202420514000_btv371-B21","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1016\/S0198-8859(02)00432-9","article-title":"Prediction of MHC class I binding peptides using profile motifs","volume":"63","author":"Reche","year":"2002","journal-title":"Hum. Immunol."},{"key":"2023020202420514000_btv371-B22","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1186\/1471-2105-7-501","article-title":"Predicting class II MHC-peptide binding: a kernel based approach using similarity scores","volume":"7","author":"Salomon","year":"2006","journal-title":"BMC Bioinformatics"},{"key":"2023020202420514000_btv371-B23","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1186\/1471-2105-12-446","article-title":"POPISK: T-cell reactivity prediction using support vector machines and string kernels","volume":"12","author":"Tung","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2023020202420514000_btv371-B24","doi-asserted-by":"crossref","first-page":"D854","DOI":"10.1093\/nar\/gkp1004","article-title":"The immune epitope database 2.0","volume":"38","author":"Vita","year":"2010","journal-title":"Nucleic Acids Res."},{"issue":"Web Server Issue","key":"2023020202420514000_btv371-B25","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1093\/nar\/gki452","article-title":"MULTIPRED: a computational system for prediction of promiscuous HLA binding peptides","volume":"33","author":"Zhang","year":"2005","journal-title":"Nucleic Acids Res."},{"key":"2023020202420514000_btv371-B26","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1093\/bioinformatics\/btn579","article-title":"Pan-specific MHC class I predictors: a benchmark of HLA class I pan-specific prediction methods","volume":"25","author":"Zhang","year":"2009","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/31\/22\/3600\/49036320\/bioinformatics_31_22_3600.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/31\/22\/3600\/49036320\/bioinformatics_31_22_3600.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T03:57:21Z","timestamp":1675310241000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/31\/22\/3600\/240035"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,23]]},"references-count":25,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2015,11,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btv371","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2015,11,15]]},"published":{"date-parts":[[2015,7,23]]}}}