{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T04:10:56Z","timestamp":1772165456885,"version":"3.50.1"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,7,2]],"date-time":"2020-07-02T00:00:00Z","timestamp":1593648000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,7,2]],"date-time":"2020-07-02T00:00:00Z","timestamp":1593648000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Immunotherapy is a promising route towards personalized cancer treatment. A key algorithmic challenge in this process is to decide if a given peptide (neoepitope) binds with the major histocompatibility complex (MHC). This is an active area of research and there are many MHC binding prediction algorithms that can predict the MHC binding affinity for a given peptide to a high degree of accuracy. However, most of the state-of-the-art approaches make use of complicated training and model selection procedures, are restricted to peptides of a certain length and\/or rely on heuristics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      We put forward\n                      <jats:italic>USMPep<\/jats:italic>\n                      , a simple recurrent neural network that reaches state-of-the-art approaches on MHC class I binding prediction with a single, generic architecture and even a single set of hyperparameters both on IEDB benchmark datasets and on the very recent HPV dataset. Moreover, the algorithm is competitive for a single model trained from scratch, while ensembling multiple regressors and language model pretraining can still slightly improve the performance. The direct application of the approach to MHC class II binding prediction shows a solid performance despite of limited training data.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We demonstrate that competitive performance in MHC binding affinity prediction can be reached with a standard architecture and training procedure without relying on any heuristics.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12859-020-03631-1","type":"journal-article","created":{"date-parts":[[2020,7,2]],"date-time":"2020-07-02T04:31:03Z","timestamp":1593664263000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["USMPep: universal sequence models for major histocompatibility complex binding affinity prediction"],"prefix":"10.1186","volume":"21","author":[{"given":"Johanna","family":"Vielhaben","sequence":"first","affiliation":[]},{"given":"Markus","family":"Wenzel","sequence":"additional","affiliation":[]},{"given":"Wojciech","family":"Samek","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4447-0162","authenticated-orcid":false,"given":"Nils","family":"Strodthoff","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,7,2]]},"reference":[{"key":"3631_CR1","doi-asserted-by":"publisher","unstructured":"Scheetz L, Park KS, Li Q, Lowenstein PR, Castro MG, Schwendeman A, Moon JJ. Engineering patient-specific cancer immunotherapies. Nat Biomed Eng. 2019. https:\/\/doi.org\/10.1038\/s41551-019-0436-x.","DOI":"10.1038\/s41551-019-0436-x"},{"issue":"6382","key":"3631_CR2","doi-asserted-by":"publisher","first-page":"1355","DOI":"10.1126\/science.aar7112","volume":"359","author":"U Sahin","year":"2018","unstructured":"Sahin U, T\u00fcreci \u00d6. Personalized vaccines for cancer immunotherapy. Science. 2018; 359(6382):1355\u201360. https:\/\/doi.org\/10.1126\/science.aar7112.","journal-title":"Science"},{"issue":"6230","key":"3631_CR3","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1126\/science.aaa4971","volume":"348","author":"TN Schumacher","year":"2015","unstructured":"Schumacher TN, Schreiber RD. Neoantigens in cancer immunotherapy. Science. 2015; 348(6230):69\u201374. https:\/\/doi.org\/10.1126\/science.aaa4971.","journal-title":"Science"},{"issue":"3","key":"3631_CR4","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1038\/nri.2017.131","volume":"18","author":"Z Hu","year":"2018","unstructured":"Hu Z, Ott PA, Wu CJ. Towards personalized, tumour-specific, therapeutic vaccines for cancer. Nat Rev Immunol. 2018; 18(3):168. https:\/\/doi.org\/10.1038\/nri.2017.131.","journal-title":"Nat Rev Immunol"},{"issue":"11","key":"3631_CR5","doi-asserted-by":"publisher","first-page":"1006457","DOI":"10.1371\/journal.pcbi.1006457","volume":"14","author":"W Zhao","year":"2018","unstructured":"Zhao W, Sher X. Systematically benchmarking peptide-MHC binding predictors: From synthetic to naturally processed epitopes. PLOS Comput Biol. 2018; 14(11):1006457. https:\/\/doi.org\/10.1371\/journal.pcbi.1006457.","journal-title":"PLOS Comput Biol"},{"key":"3631_CR6","doi-asserted-by":"publisher","unstructured":"Mei S, Li F, Leier A, Marquez-Lago TT, Giam K, Croft NP, Akutsu T, Smith AI, Li J, Rossjohn J, Purcell AW, Song J. A comprehensive review and performance evaluation of bioinformatics tools for HLA class I peptide-binding prediction. Brief Bioinformatics. 2019. https:\/\/doi.org\/10.1093\/bib\/bbz051.","DOI":"10.1093\/bib\/bbz051"},{"issue":"1","key":"3631_CR7","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1186\/1471-2105-10-394","volume":"10","author":"Y Kim","year":"2009","unstructured":"Kim Y, Sidney J, Pinilla C, Sette A, Peters B. Derivation of an amino acid similarity matrix for peptide:MHC binding and its application as a Bayesian prior. BMC Bioinformatics. 2009; 10(1):394. https:\/\/doi.org\/10.1186\/1471-2105-10-394.","journal-title":"BMC Bioinformatics"},{"issue":"7","key":"3631_CR8","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1038\/nbt1215","volume":"24","author":"M Moutaftsi","year":"2006","unstructured":"Moutaftsi M, Peters B, Pasquetto V, Tscharke DC, Sidney J, Bui H-H, Grey H, Sette A. A consensus epitope prediction approach identifies the breadth of murine TCD8+-cell responses to vaccinia virus. Nat Biotechnol. 2006; 24(7):817\u20139. https:\/\/doi.org\/10.1038\/nbt1215.","journal-title":"Nat Biotechnol"},{"issue":"4","key":"3631_CR9","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1093\/bioinformatics\/btv639","volume":"32","author":"M Andreatta","year":"2015","unstructured":"Andreatta M, Nielsen M. Gapped sequence alignment using artificial neural networks: application to the MHC class I system. Bioinformatics. 2015; 32(4):511\u20137. https:\/\/doi.org\/10.1093\/bioinformatics\/btv639.","journal-title":"Bioinformatics"},{"issue":"9","key":"3631_CR10","doi-asserted-by":"publisher","first-page":"3360","DOI":"10.4049\/jimmunol.1700893","volume":"199","author":"V Jurtz","year":"2017","unstructured":"Jurtz V, Paul S, Andreatta M, Marcatili P, Peters B, Nielsen M. NetMHCpan-4.0: Improved Peptide\u2013MHC Class I Interaction Predictions Integrating Eluted Ligand and Peptide Binding Affinity Data. J Immunol. 2017; 199(9):3360\u20138. https:\/\/doi.org\/10.4049\/jimmunol.1700893.","journal-title":"J Immunol"},{"issue":"1","key":"3631_CR11","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.cels.2018.05.014","volume":"7","author":"TJ O\u2019Donnell","year":"2018","unstructured":"O\u2019Donnell TJ, Rubinsteyn A, Bonsack M, Riemer AB, Laserson U, Hammerbacher J. MHCflurry: Open-Source Class I MHC Binding Affinity Prediction. Cell Syst. 2018; 7(1):129\u20131324. https:\/\/doi.org\/10.1016\/j.cels.2018.05.014.","journal-title":"Cell Syst"},{"issue":"5","key":"3631_CR12","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1158\/2326-6066.CIR-18-0584","volume":"7","author":"M Bonsack","year":"2019","unstructured":"Bonsack M, Hoppe S, Winter J, Tichy D, Zeller C, K\u00fcpper MD, Schitter EC, Blatnik R, Riemer AB. Performance Evaluation of MHC Class-I Binding Prediction Tools Based on an Experimentally Validated MHC\u2013Peptide Binding Data Set. Cancer Immunol Res. 2019; 7(5):719\u201336. https:\/\/doi.org\/10.1158\/2326-6066.cir-18-0584.","journal-title":"Cancer Immunol Res"},{"key":"3631_CR13","doi-asserted-by":"publisher","unstructured":"Bhattacharya R, Sivakumar A, Tokheim C, Guthrie VB, Anagnostou V, Velculescu VE, Karchin R. Evaluation of machine learning methods to predict peptide binding to MHC Class I proteins. bioRxiv. 2017. https:\/\/doi.org\/10.1101\/154757.","DOI":"10.1101\/154757"},{"key":"3631_CR14","doi-asserted-by":"publisher","unstructured":"Phloyphisut P, Pornputtapong N, Sriswasdi S, Chuangsuwanich E. MHCSeqNet: a deep neural network model for universal MHC binding prediction. BMC Bioinformatics. 2019; 20(1). https:\/\/doi.org\/10.1186\/s12859-019-2892-4.","DOI":"10.1186\/s12859-019-2892-4"},{"issue":"8","key":"3631_CR15","doi-asserted-by":"publisher","first-page":"2401","DOI":"10.1093\/bioinformatics\/btaa003","volume":"36","author":"N Strodthoff","year":"2020","unstructured":"Strodthoff N, Wagner P, Wenzel M, Samek W. UDSMProt: universal deep sequence models for protein classification. Bioinformatics. 2020; 36(8):2401\u20139. https:\/\/doi.org\/10.1093\/bioinformatics\/btaa003.","journal-title":"Bioinformatics"},{"key":"3631_CR16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"J Howard","year":"2018","unstructured":"Howard J, Ruder S. Universal language model fine-tuning for text classification. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Melbourne: Association for Computational Linguistics: 2018. p. 328\u2013339. https:\/\/doi.org\/10.18653\/v1\/P18-1031."},{"key":"3631_CR17","unstructured":"Merity S, Keskar NS, Socher R. Regularizing and optimizing LSTM language models. arXiv preprint arXiv:1708.02182. 2017."},{"key":"3631_CR18","unstructured":"Smith LN. A disciplined approach to neural network hyper-parameters: Part 1 - learning rate, batch size, momentum, and weight decay. arXiv preprint arXiv:1803.09820. 2018."},{"issue":"1","key":"3631_CR19","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1186\/1471-2105-15-241","volume":"15","author":"Y Kim","year":"2014","unstructured":"Kim Y, Sidney J, Buus S, Sette A, Nielsen M, Peters B. Dataset size and composition impact the reliability of performance benchmarks for peptide-MHC binding predictions. BMC Bioinformatics. 2014; 15(1):241. https:\/\/doi.org\/10.1186\/1471-2105-15-241.","journal-title":"BMC Bioinformatics"},{"issue":"D1","key":"3631_CR20","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1093\/nar\/gky1006","volume":"47","author":"R Vita","year":"2018","unstructured":"Vita R, Mahajan S, Overton JA, Dhanda SK, Martini S, Cantrell JR, Wheeler DK, Sette A, Peters B. The Immune Epitope Database (IEDB): 2018 update. Nucleic Acids Res. 2018; 47(D1):339\u201343. doi:10.1093\/nar\/gky1006.","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"3631_CR21","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1186\/1471-2105-11-568","volume":"11","author":"P Wang","year":"2010","unstructured":"Wang P, Sidney J, Kim Y, Sette A, Lund O, Nielsen M, Peters B. Peptide binding predictions for HLA DR, DP and DQ molecules. BMC Bioinformatics. 2010; 11(1):568. https:\/\/doi.org\/10.1186\/1471-2105-11-568.","journal-title":"BMC Bioinformatics"},{"issue":"12","key":"3631_CR22","doi-asserted-by":"publisher","first-page":"5831","DOI":"10.4049\/jimmunol.1302101","volume":"191","author":"S Paul","year":"2013","unstructured":"Paul S, Weiskopf D, Angelo MA, Sidney J, Peters B, Sette A. HLA Class I Alleles Are Associated with Peptide-Binding Repertoires of Different Size, Affinity, and Immunogenicity. J Immunol. 2013; 191(12):5831\u20139. https:\/\/doi.org\/10.4049\/jimmunol.1302101.","journal-title":"J Immunol"},{"issue":"2","key":"3631_CR23","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1093\/bib\/bbw108","volume":"19","author":"J Chen","year":"2016","unstructured":"Chen J, Guo M, Wang X, Liu B. A comprehensive review and comparison of different computational methods for protein remote homology detection. Brief Bioinformatics. 2016; 19(2):231\u201344. https:\/\/doi.org\/10.1093\/bib\/bbw108.","journal-title":"Brief Bioinformatics"},{"issue":"8","key":"3631_CR24","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1038\/nbt.3300","volume":"33","author":"B Alipanahi","year":"2015","unstructured":"Alipanahi B, Delong A, Weirauch MT, Frey BJ. Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat Biotechnol. 2015; 33(8):831\u20138. https:\/\/doi.org\/10.1038\/nbt.3300.","journal-title":"Nat Biotechnol"},{"key":"3631_CR25","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to Information Retrieval","author":"CD Manning","year":"2008","unstructured":"Manning CD, Raghavan P, Schutze H. Introduction to Information Retrieval. New York: Cambridge University Press; 2008. https:\/\/doi.org\/10.1017\/cbo9780511809071."},{"issue":"1","key":"3631_CR26","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s00251-005-0781-7","volume":"57","author":"M Nielsen","year":"2005","unstructured":"Nielsen M, Lundegaard C, Lund O, Ke\u015fmir C. The role of the proteasome in generating cytotoxic T-cell epitopes: insights obtained from improved predictions of proteasomal cleavage. Immunogenetics. 2005; 57(1):33\u201341. https:\/\/doi.org\/10.1007\/s00251-005-0781-7.","journal-title":"Immunogenetics"},{"key":"3631_CR27","unstructured":"Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer A. Automatic differentiation in PyTorch. In: 31st Conference on Neural Information Processing Systems (NIPS) Workshop Autodiff: 2017."},{"key":"3631_CR28","unstructured":"Howard J, et al.fast.ai. GitHub. 2018. https:\/\/github.com\/fastai\/fastai. Accessed 26 Apr 2019."}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-020-03631-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-020-03631-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-020-03631-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T19:14:36Z","timestamp":1625166876000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-020-03631-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,2]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["3631"],"URL":"https:\/\/doi.org\/10.1186\/s12859-020-03631-1","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/816546","asserted-by":"object"}]},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,2]]},"assertion":[{"value":"14 November 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"279"}}