{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T19:46:37Z","timestamp":1784317597230,"version":"3.55.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T00:00:00Z","timestamp":1609891200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T00:00:00Z","timestamp":1609891200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Accurate prediction of binding between class I human leukocyte antigen (HLA) and neoepitope is critical for target identification within personalized T-cell based immunotherapy. Many recent prediction tools developed upon the deep learning algorithms and mass spectrometry data have indeed showed improvement on the average predicting power for class I HLA-peptide interaction. However, their prediction performances show great variability over individual HLA alleles and peptides with different lengths, which is particularly the case for HLA-C alleles due to the limited amount of experimental data. To meet the increasing demand for attaining the most accurate HLA-peptide binding prediction for individual patient in the real-world clinical studies, more advanced deep learning framework with higher prediction accuracy for HLA-C alleles and longer peptides is highly desirable.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We present a pan-allele HLA-peptide binding prediction framework\u2014MATHLA which integrates bi-directional long short-term memory network and multiple head attention mechanism. This model achieves better prediction accuracy in both fivefold cross-validation test and independent test dataset. In addition, this model is superior over existing tools regarding to the prediction accuracy for longer ligand ranging from 11 to 15 amino acids. Moreover, our model also shows a significant improvement for HLA-C-peptide-binding prediction. By investigating multiple-head attention weight scores, we depicted possible interaction patterns between three HLA I supergroups and their cognate peptides.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Our method demonstrates the necessity of further development of deep learning algorithm in improving and interpreting HLA-peptide binding prediction in parallel to increasing the amount of high-quality HLA ligandome data.<\/jats:p><\/jats:sec>","DOI":"10.1186\/s12859-020-03946-z","type":"journal-article","created":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T19:04:06Z","timestamp":1609959846000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["MATHLA: a robust framework for HLA-peptide binding prediction integrating bidirectional LSTM and multiple head attention mechanism"],"prefix":"10.1186","volume":"22","author":[{"given":"Yilin","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunwan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youdong","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5279-0345","authenticated-orcid":false,"given":"Ji","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,1,6]]},"reference":[{"issue":"7662","key":"3946_CR1","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1038\/nature22991","volume":"547","author":"PA Ott","year":"2017","unstructured":"Ott PA, Hu Z, Keskin DB, Shukla SA, Sun J, Bozym DJ, Zhang W, Luoma A, Giobbie-Hurder A, Peter L, et al. An immunogenic personal neoantigen vaccine for patients with melanoma. Nature. 2017;547(7662):217\u201321.","journal-title":"Nature"},{"issue":"7662","key":"3946_CR2","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1038\/nature23003","volume":"547","author":"U Sahin","year":"2017","unstructured":"Sahin U, Derhovanessian E, Miller M, Kloke BP, Simon P, Lower M, Bukur V, Tadmor AD, Luxemburger U, Schrors B, et al. Personalized RNA mutanome vaccines mobilize poly-specific therapeutic immunity against cancer. Nature. 2017;547(7662):222\u20136.","journal-title":"Nature"},{"issue":"1","key":"3946_CR3","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.cels.2018.05.014","volume":"7","author":"TJ O'Donnell","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):129-132 e124.","journal-title":"Cell Syst"},{"issue":"17","key":"3946_CR4","doi-asserted-by":"publisher","first-page":"2658","DOI":"10.1093\/bioinformatics\/btx264","volume":"33","author":"YS Vang","year":"2017","unstructured":"Vang YS, Xie X. HLA class I binding prediction via convolutional neural networks. Bioinformatics. 2017;33(17):2658\u201365.","journal-title":"Bioinformatics"},{"issue":"11","key":"3946_CR5","doi-asserted-by":"publisher","first-page":"1332","DOI":"10.1038\/s41587-019-0280-2","volume":"37","author":"B Chen","year":"2019","unstructured":"Chen B, Khodadoust MS, Olsson N, Wagar LE, Fast E, Liu CL, Muftuoglu Y, Sworder BJ, Diehn M, Levy R, et al. Predicting HLA class II antigen presentation through integrated deep learning. Nat Biotechnol. 2019;37(11):1332\u201343.","journal-title":"Nat Biotechnol"},{"key":"3946_CR6","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1093\/bib\/bbz051","volume":"21","author":"S Mei","year":"2019","unstructured":"Mei S, Li F, Leier A, Marquez-Lago TT, Giam K, Croft NP, Akutsu T, Smith AI, Li J, Rossjohn J, et al. A comprehensive review and performance evaluation of bioinformatics tools for HLA class I peptide-binding prediction. Brief Bioinform. 2019;21:1119\u201335.","journal-title":"Brief Bioinform"},{"issue":"2","key":"3946_CR7","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1038\/s41587-019-0322-9","volume":"38","author":"S Sarkizova","year":"2020","unstructured":"Sarkizova S, Klaeger S, Le PM, Li LW, Oliveira G, Keshishian H, Hartigan CR, Zhang WD, Braun DA, Ligon KL, et al. A large peptidome dataset improves HLA class I epitope prediction across most of the human population. Nat Biotechnol. 2020;38(2):199.","journal-title":"Nat Biotechnol"},{"issue":"1","key":"3946_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00251-008-0341-z","volume":"61","author":"I Hoof","year":"2009","unstructured":"Hoof I, Peters B, Sidney J, Pedersen LE, Sette A, Lund O, Buus S, Nielsen M. NetMHCpan, a method for MHC class I binding prediction beyond humans. Immunogenetics. 2009;61(1):1\u201313.","journal-title":"Immunogenetics"},{"issue":"9","key":"3946_CR9","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-MHC class I interaction predictions integrating eluted ligand and peptide binding affinity data. J Immunol. 2017;199(9):3360\u20138.","journal-title":"J Immunol"},{"issue":"5","key":"3946_CR10","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, Kupper MD, Schitter EC, Blatnik R, Riemer AB. Performance evaluation of MHC class-I binding prediction tools based on an experimentally validated MHC-peptide binding data set. Cancer Immunol Res. 2019;7(5):719\u201336.","journal-title":"Cancer Immunol Res"},{"issue":"12","key":"3946_CR11","doi-asserted-by":"publisher","first-page":"3705","DOI":"10.4049\/jimmunol.1800914","volume":"201","author":"D Gfeller","year":"2018","unstructured":"Gfeller D, Guillaume P, Michaux J, Pak HS, Daniel RT, Racle J, Coukos G, Bassani-Sternberg M. The length distribution and multiple specificity of naturally presented HLA-I ligands. J Immunol. 2018;201(12):3705\u201316.","journal-title":"J Immunol"},{"issue":"1","key":"3946_CR12","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/s13073-016-0288-x","volume":"8","author":"M Nielsen","year":"2016","unstructured":"Nielsen M, Andreatta M. NetMHCpan-3.0; improved prediction of binding to MHC class I molecules integrating information from multiple receptor and peptide length datasets. Genome Med. 2016;8(1):33.","journal-title":"Genome Med"},{"issue":"D1","key":"3946_CR13","doi-asserted-by":"publisher","first-page":"D339","DOI":"10.1093\/nar\/gky1006","volume":"47","author":"R Vita","year":"2019","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. 2019;47(D1):D339\u201343.","journal-title":"Nucleic Acids Res"},{"key":"3946_CR14","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 Bioinform. 2014;15:241.","journal-title":"BMC Bioinform"},{"issue":"D1","key":"3946_CR15","doi-asserted-by":"publisher","first-page":"D1237","DOI":"10.1093\/nar\/gkx664","volume":"46","author":"W Shao","year":"2018","unstructured":"Shao W, Pedrioli PGA, Wolski W, Scurtescu C, Schmid E, Vizcaino JA, Courcelles M, Schuster H, Kowalewski D, Marino F, et al. The SysteMHC Atlas project. Nucleic Acids Res. 2018;46(D1):D1237\u201347.","journal-title":"Nucleic Acids Res"},{"issue":"2","key":"3946_CR16","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1016\/j.immuni.2017.02.007","volume":"46","author":"JG Abelin","year":"2017","unstructured":"Abelin JG, Keskin DB, Sarkizova S, Hartigan CR, Zhang W, Sidney J, Stevens J, Lane W, Zhang GL, Eisenhaure TM, et al. Mass spectrometry profiling of HLA-associated peptidomes in mono-allelic cells enables more accurate epitope prediction. Immunity. 2017;46(2):315\u201326.","journal-title":"Immunity"},{"issue":"22","key":"3946_CR17","doi-asserted-by":"publisher","first-page":"10915","DOI":"10.1073\/pnas.89.22.10915","volume":"89","author":"S Henikoff","year":"1992","unstructured":"Henikoff S, Henikoff JG. Amino-acid substitution matrices from protein blocks. Proc Natl Acad Sci USA. 1992;89(22):10915\u20139.","journal-title":"Proc Natl Acad Sci USA"},{"issue":"10","key":"3946_CR18","doi-asserted-by":"publisher","first-page":"2451","DOI":"10.1162\/089976600300015015","volume":"12","author":"FA Gers","year":"2000","unstructured":"Gers FA, Schmidhuber J, Cummins F. Learning to forget: continual prediction with LSTM. Neural Comput. 2000;12(10):2451\u201371.","journal-title":"Neural Comput"},{"key":"3946_CR19","doi-asserted-by":"publisher","first-page":"3054","DOI":"10.1109\/TSG.2020.2974347","volume":"11","author":"M Kaselimi","year":"2020","unstructured":"Kaselimi M, Doulamis N, Voulodimos A, Protopapadakis E, Doulamis A. Context aware energy disaggregation using adaptive bidirectional LSTM models. IEEE Trans Smart Grid. 2020;11:3054\u201367.","journal-title":"IEEE Trans Smart Grid"},{"key":"3946_CR20","doi-asserted-by":"crossref","unstructured":"Li J, Tu Z, Yang B, Lyu MR, Zhang T. Multi-head attention with disagreement regularization; 2018. arXiv e-prints. arXiv:1810.10183.","DOI":"10.18653\/v1\/D18-1317"},{"key":"3946_CR21","doi-asserted-by":"publisher","first-page":"46802","DOI":"10.1109\/ACCESS.2020.2977471","volume":"8","author":"F Lin","year":"2020","unstructured":"Lin F, Zhang C, Liu S, Ma H. A hierarchical structured multi-head attention network for multi-turn response generation. IEEE Access. 2020;8:46802\u201310.","journal-title":"IEEE Access"},{"issue":"6","key":"3946_CR22","doi-asserted-by":"publisher","first-page":"4247","DOI":"10.3233\/JIFS-16629","volume":"32","author":"J Niu","year":"2017","unstructured":"Niu J, Chen J, Xu Y. Twin support vector regression with Huber loss. J Intell Fuzzy Syst. 2017;32(6):4247\u201358.","journal-title":"J Intell Fuzzy Syst"},{"key":"3946_CR23","unstructured":"Liu L, Jiang H, He P, Chen W, Liu X, Gao J, Han J. On the variance of the adaptive learning rate and beyond; 2019. arXiv e-prints. arXiv:1908.03265."},{"issue":"23","key":"3946_CR24","doi-asserted-by":"publisher","first-page":"4946","DOI":"10.1093\/bioinformatics\/btz427","volume":"35","author":"Y Hu","year":"2019","unstructured":"Hu Y, Wang Z, Hu H, Wan F, Chen L, Xiong Y, Wang X, Zhao D, Huang W, Zeng J. ACME: pan-specific peptide-MHC class I binding prediction through attention-based deep neural networks. Bioinformatics. 2019;35(23):4946\u201354.","journal-title":"Bioinformatics"},{"issue":"8","key":"3946_CR25","doi-asserted-by":"publisher","first-page":"e1005725","DOI":"10.1371\/journal.pcbi.1005725","volume":"13","author":"M Bassani-Sternberg","year":"2017","unstructured":"Bassani-Sternberg M, Chong C, Guillaume P, Solleder M, Pak H, Gannon PO, Kandalaft LE, Coukos G, Gfeller D. Deciphering HLA-I motifs across HLA peptidomes improves neo-antigen predictions and identifies allostery regulating HLA specificity. PLoS Comput Biol. 2017;13(8):e1005725.","journal-title":"PLoS Comput Biol"},{"issue":"6","key":"3946_CR26","doi-asserted-by":"crossref","first-page":"2874","DOI":"10.4049\/jimmunol.152.6.2874","volume":"152","author":"Y Chen","year":"1994","unstructured":"Chen Y, Sidney J, Southwood S, Cox AL, Sakaguchi K, Henderson RA, Appella E, Hunt DF, Sette A, Engelhard VH. Naturally processed peptides longer than nine amino acid residues bind to the class I MHC molecule HLA-A2.1 with high affinity and in different conformations. J Immunol. 1994;152(6):2874\u201381.","journal-title":"J Immunol"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-020-03946-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12859-020-03946-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-020-03946-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,17]],"date-time":"2023-10-17T02:39:43Z","timestamp":1697510383000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-020-03946-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,6]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["3946"],"URL":"https:\/\/doi.org\/10.1186\/s12859-020-03946-z","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,6]]},"assertion":[{"value":"30 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 December 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2021","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 declared that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"7"}}