{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T13:55:58Z","timestamp":1781618158790,"version":"3.54.5"},"reference-count":53,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2020,2,25]],"date-time":"2020-02-25T00:00:00Z","timestamp":1582588800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000060","name":"National Institute of Allergy and Infectious Diseases","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000060","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000060","name":"NIAID","doi-asserted-by":"publisher","award":["1R01AI081062"],"award-info":[{"award-number":["1R01AI081062"]}],"id":[{"id":"10.13039\/100000060","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Reverse vaccinology (RV) is a milestone in rational vaccine design, and machine learning (ML) has been applied to enhance the accuracy of RV prediction. However, ML-based RV still faces challenges in prediction accuracy and program accessibility.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>This study presents Vaxign-ML, a supervised ML classification to predict bacterial protective antigens (BPAgs). To identify the best ML method with optimized conditions, five ML methods were tested with biological and physiochemical features extracted from well-defined training data. Nested 5-fold cross-validation and leave-one-pathogen-out validation were used to ensure unbiased performance assessment and the capability to predict vaccine candidates against a new emerging pathogen. The best performing model (eXtreme Gradient Boosting) was compared to three publicly available programs (Vaxign, VaxiJen, and Antigenic), one SVM-based method, and one epitope-based method using a high-quality benchmark dataset. Vaxign-ML showed superior performance in predicting BPAgs. Vaxign-ML is hosted in a publicly accessible web server and a standalone version is also available.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Vaxign-ML website at http:\/\/www.violinet.org\/vaxign\/vaxign-ml, Docker standalone Vaxign-ML available at https:\/\/hub.docker.com\/r\/e4ong1031\/vaxign-ml and source code is available at https:\/\/github.com\/VIOLINet\/Vaxign-ML-docker.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaa119","type":"journal-article","created":{"date-parts":[[2020,2,18]],"date-time":"2020-02-18T20:13:28Z","timestamp":1582056808000},"page":"3185-3191","source":"Crossref","is-referenced-by-count":153,"title":["Vaxign-ML: supervised machine learning reverse vaccinology model for improved prediction of bacterial protective antigens"],"prefix":"10.1093","volume":"36","author":[{"given":"Edison","family":"Ong","sequence":"first","affiliation":[{"name":"Department of Computational Medicine and Bioinformatics , University of Michigan Medical School, Ann Arbor, MI 48109, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haihe","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Pathogenobiology , Daqing Branch of Harbin Medical University, Daqing 163319, China"},{"name":"Unit for Laboratory Animal Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei U","family":"Wong","sequence":"additional","affiliation":[{"name":"Unit for Laboratory Animal Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meenakshi","family":"Seetharaman","sequence":"additional","affiliation":[{"name":"College of Literature , Science, and the Arts, University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ninotchka","family":"Valdez","sequence":"additional","affiliation":[{"name":"College of Literature , Science, and the Arts, University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqun","family":"He","sequence":"additional","affiliation":[{"name":"Unit for Laboratory Animal Medicine"},{"name":"Department of Microbiology and Immunology"},{"name":"Center of Computational Medicine and Bioinformatics , University of Michigan Medical School, Ann Arbor, MI 48109, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,2,25]]},"reference":[{"key":"2023013112031932800_btaa119-B1","doi-asserted-by":"crossref","first-page":"8156","DOI":"10.1016\/j.vaccine.2011.07.142","article-title":"Improving reverse vaccinology with a machine learning approach","volume":"29","author":"Bowman","year":"2011","journal-title":"Vaccine"},{"key":"2023013112031932800_btaa119-B2","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique Nitesh","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res"},{"key":"2023013112031932800_btaa119-B3","first-page":"13","author":"Chen","year":"2016"},{"key":"2023013112031932800_btaa119-B4","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1006\/bbrc.2000.3815","article-title":"Prediction of protein subcellular locations by incorporating quasi-sequence-order effect","volume":"278","author":"Chou","year":"2000","journal-title":"Biochem. Biophys. Res. Commun"},{"key":"2023013112031932800_btaa119-B5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fimmu.2019.00113","article-title":"Comparison of open-source reverse vaccinology programs for bacterial vaccine antigen discovery","volume":"10","author":"Dalsass","year":"2019","journal-title":"Front. Immunol"},{"key":"2023013112031932800_btaa119-B6","doi-asserted-by":"crossref","first-page":"W502","DOI":"10.1093\/nar\/gkz452","article-title":"IEDB-AR: immune epitope database\u2014analysis resource in 2019","volume":"47","author":"Dhanda","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023013112031932800_btaa119-B7","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1142\/S0219720005001004","article-title":"Minimum redundancy feature selection from microarray gene expression data","volume":"3","author":"Ding","year":"2003","journal-title":"J. Bioinform. Comput. Biol."},{"key":"2023013112031932800_btaa119-B8","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/1471-2105-8-4","article-title":"VaxiJen: a server for prediction of protective antigens, tumour antigens and subunit vaccines","volume":"8","author":"Doytchinova","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"2023013112031932800_btaa119-B9","doi-asserted-by":"crossref","first-page":"8700","DOI":"10.1073\/pnas.92.19.8700","article-title":"Prediction of protein folding class using global description of amino acid sequence","volume":"92","author":"Dubchak","year":"1995","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023013112031932800_btaa119-B10","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1023\/A:1007091128394","article-title":"Prediction of membrane protein types based on the hydrophobic index of amino acids","volume":"19","author":"Feng","year":"2000","journal-title":"J. Protein Chem"},{"key":"2023013112031932800_btaa119-B11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fimmu.2017.00278","article-title":"The immune epitope database and analysis resource in epitope discovery and synthetic vaccine design","volume":"8","author":"Fleri","year":"2017","journal-title":"Front. Immunol"},{"key":"2023013112031932800_btaa119-B12","doi-asserted-by":"crossref","first-page":"S1","DOI":"10.1186\/1745-7580-6-S2-S1","article-title":"Computer aided selection of candidate vaccine antigens","volume":"6","author":"Flower","year":"2010","journal-title":"Immunome Res"},{"key":"2023013112031932800_btaa119-B13","first-page":"608","article-title":"Use of serogroup B meningococcal vaccines in persons aged &gt;\/=10 years at increased risk for serogroup B meningococcal disease: recommendations of the advisory committee on immunization practices, 2015","volume":"64","author":"Folaranmi","year":"2015","journal-title":"Morb. Mortal. Wkly. Rep"},{"key":"2023013112031932800_btaa119-B0167572","doi-asserted-by":"crossref","first-page":"488","DOI":"10.1073\/pnas.1422923112","article-title":"Controlled analysis of nanoparticle charge on mucosal and systemic antibody responses following pulmonary immunization","volume":"112","author":"Fromen","year":"2015","journal-title":"Proc. Natl. Acad. Sci."},{"key":"2023013112031932800_btaa119-B14","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1186\/1471-2105-14-315","article-title":"A novel strategy for classifying the output from an in silico vaccine discovery pipeline for eukaryotic pathogens using machine learning algorithms","volume":"14","author":"Goodswen","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"2023013112031932800_btaa119-B15","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1007\/s00251-011-0513-0","article-title":"Functional classification of class II human leukocyte antigen (HLA) molecules reveals seven different supertypes and a surprising degree of repertoire sharing across supertypes","volume":"63","author":"Greenbaum","year":"2011","journal-title":"Immunogenetics"},{"key":"2023013112031932800_btaa119-B16","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1016\/j.it.2008.06.001","article-title":"Are bacterial vaccine antigens T-cell epitope depleted?","volume":"29","author":"Halling-Brown","year":"2008","journal-title":"Trends Immunol"},{"key":"2023013112031932800_btaa119-B17","doi-asserted-by":"crossref","first-page":"2699","DOI":"10.1016\/j.molimm.2009.05.027","article-title":"Proteins accessible to immune surveillance show significant T-cell epitope depletion: implications for vaccine design","volume":"46","author":"Halling-Brown","year":"2009","journal-title":"Mol. Immunol"},{"key":"2023013112031932800_btaa119-B18","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.provac.2012.04.002","article-title":"Bioinformatics analysis of bacterial protective antigens in manually curated Protegen database","volume":"6","author":"He","year":"2012","journal-title":"Procedia Vaccinol"},{"key":"2023013112031932800_btaa119-B19","first-page":"1","article-title":"Vaxign: the first web-based vaccine design program for reverse vaccinology and applications for vaccine development","volume":"2010","author":"He","year":"2010","journal-title":"J. Biomed. Biotechnol"},{"key":"2023013112031932800_btaa119-B0841086","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-36950-8","article-title":"Web-based display of protein surface and pH-dependent properties for assessing the developability of biotherapeutics","volume":"9","author":"Hebditch","year":"2019","journal-title":"Sci. Rep"},{"key":"2023013112031932800_btaa119-B20","doi-asserted-by":"crossref","first-page":"312","DOI":"10.3390\/ijms18020312","article-title":"Enhancing the biological relevance of machine learning classifiers for reverse vaccinology","volume":"18","author":"Heinson","year":"2017","journal-title":"Int. J. Mol. Sci"},{"key":"2023013112031932800_btaa119-B21","first-page":"1","article-title":"Computational identification and characterization of a promiscuous T-cell epitope on the extracellular protein 85B of Mycobacterium spp. for peptide-based subunit vaccine design","volume":"2017","author":"Hossain","year":"2017","journal-title":"Biomed. Res. Int"},{"key":"2023013112031932800_btaa119-B22","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1186\/1471-2105-14-211","article-title":"Jenner-predict server: prediction of protein vaccine candidates (PVCs) in bacteria based on host-pathogen interactions","volume":"14","author":"Jaiswal","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"2023013112031932800_btaa119-B23","doi-asserted-by":"crossref","first-page":"4990","DOI":"10.1128\/iai.62.11.4990-4996.1994","article-title":"Vaccination with Brucella abortus rough mutant RB51 protects BALB\/c mice against virulent strains of Brucella abortus, Brucella melitensis, and Brucella ovis","volume":"62","author":"Jimenez de Bagues","year":"1994","journal-title":"Infect. Immun"},{"key":"2023013112031932800_btaa119-B24","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1006\/jmbi.2000.4315","article-title":"Predicting transmembrane protein topology with a hidden Markov model: application to complete genomes","volume":"305","author":"Krogh","year":"2001","journal-title":"J. Mol. Biol"},{"key":"2023013112031932800_btaa119-B25","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1023\/A:1010967008838","article-title":"Accurate prediction of protein secondary structural content","volume":"20","author":"Lin","year":"2001","journal-title":"Protein J"},{"key":"2023013112031932800_btaa119-B26","doi-asserted-by":"crossref","first-page":"2936","DOI":"10.1093\/bioinformatics\/btq551","article-title":"High-throughput prediction of protein antigenicity using protein microarray data","volume":"26","author":"Magnan","year":"2010","journal-title":"Bioinformatics"},{"key":"2023013112031932800_btaa119-B27","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1002\/cfg.319","article-title":"Analysis of known bacterial protein vaccine antigens reveals biased physical properties and amino acid composition","volume":"4","author":"Mayers","year":"2003","journal-title":"Comp. Funct. Genomics"},{"key":"2023013112031932800_btaa119-B28","doi-asserted-by":"crossref","first-page":"2312","DOI":"10.1080\/21645515.2015.1061159","article-title":"iVAX: an integrated toolkit for the selection and optimization of antigens and the design of epitope-driven vaccines","volume":"11","author":"Moise","year":"2015","journal-title":"Hum. Vaccin. Immunother"},{"key":"2023013112031932800_btaa119-B29","doi-asserted-by":"crossref","first-page":"148","DOI":"10.5539\/gjhs.v10n7p148","article-title":"Prediction of Epitopes in the Proteome of Helicobacter pylori","volume":"10","author":"Navarro-Quiroz","year":"2018","journal-title":"Glob. J. Health Sci"},{"key":"2023013112031932800_btaa119-B0429490","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.mimet.2012.04.001","article-title":"An in silico chimeric multi subunit vaccine targeting virulence factors of enterotoxigenic Escherichia coli (ETEC) with its bacterial inbuilt adjuvant","volume":"90","author":"Nazarian","year":"2012","journal-title":"J Microbiol Methods"},{"key":"2023013112031932800_btaa119-B30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fimmu.2017.01382","article-title":"Identification of new features from known bacterial protective vaccine antigens enhances rational vaccine design","volume":"8","author":"Ong","year":"2017","journal-title":"Front. Immunol"},{"key":"2023013112031932800_btaa119-B31","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1186\/1471-2105-8-300","article-title":"Efficacy of different protein descriptors in predicting protein functional families","volume":"8","author":"Ong","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"2023013112031932800_btaa119-B0088297","doi-asserted-by":"crossref","DOI":"10.1098\/rsob.120139","article-title":"T-cell epitope vaccine design by immunoinformatics","volume":"3","author":"Patronov","year":"2013","journal-title":"Open Biol"},{"key":"2023013112031932800_btaa119-B32","author":"Pearson","year":"2013"},{"key":"2023013112031932800_btaa119-B33","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2012"},{"key":"2023013112031932800_btaa119-B34","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1038\/nmeth.1701","article-title":"SignalP 4.0: discriminating signal peptides from transmembrane regions","volume":"8","author":"Petersen","year":"2011","journal-title":"Nat. Methods"},{"key":"2023013112031932800_btaa119-B35","doi-asserted-by":"crossref","first-page":"1816","DOI":"10.1126\/science.287.5459.1816","article-title":"Identification of vaccine candidates against serogroup B meningococcus by whole-genome sequencing","volume":"287","author":"Pizza","year":"2000","journal-title":"Science (80-)"},{"key":"2023013112031932800_btaa119-B36","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.artmed.2018.12.010","article-title":"Antigenic: an improved prediction model of protective antigens","volume":"94","author":"Rahman","year":"2019","journal-title":"Artif. Intell. Med"},{"key":"2023013112031932800_btaa119-B37","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1016\/S1369-5274(00)00119-3","article-title":"Reverse vaccinology","volume":"3","author":"Rappuoli","year":"2000","journal-title":"Curr. Opin. Microbiol"},{"key":"2023013112031932800_btaa119-B38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-017-1540-0","article-title":"VacSol: a high throughput in silico pipeline to predict potential therapeutic targets in prokaryotic pathogens using subtractive reverse vaccinology","volume":"18","author":"Rizwan","year":"2017","journal-title":"BMC Bioinformatics"},{"key":"2023013112031932800_btaa119-B39","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1093\/bioinformatics\/bti028","article-title":"SPAAN: a software program for prediction of adhesins and adhesin-like proteins using neural networks","volume":"21","author":"Sachdeva","year":"2005","journal-title":"Bioinformatics"},{"key":"2023013112031932800_btaa119-B40","doi-asserted-by":"crossref","first-page":"158","DOI":"10.3389\/fmicb.2016.00158","article-title":"Immunoprotective efficacy of Acinetobacter baumannii outer membrane protein, FilF, predicted in silico as a potential vaccine candidate","volume":"7","author":"Singh","year":"2016","journal-title":"Front. Microbiol"},{"key":"2023013112031932800_btaa119-B41","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1002\/ajpa.20250","article-title":"Population structure inferred by local spatial autocorrelation: an example from an Amerindian tribal population","volume":"129","author":"Sokal","year":"2006","journal-title":"Am. J. Phys. Anthropol"},{"key":"2023013112031932800_btaa119-B42","article-title":"The universal protein resource (UniProt)","volume":"36","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2023013112031932800_btaa119-B43","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1179\/2047773214Y.0000000162","article-title":"Bexsero H chronicle","volume":"108","author":"Vernikos","year":"2014","journal-title":"Pathog. Glob. Health"},{"key":"2023013112031932800_btaa119-B44","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1186\/1472-6750-6-35","article-title":"NERVE: new enhanced reverse vaccinology environment","volume":"6","author":"Vivona","year":"2006","journal-title":"BMC Biotechnol"},{"key":"2023013112031932800_btaa119-B45","doi-asserted-by":"crossref","first-page":"E2046","DOI":"10.1073\/pnas.1305227110","article-title":"Comprehensive analysis of dengue virus-specific responses supports an HLA-linked protective role for CD8+ T cells","volume":"110","author":"Weiskopf","year":"2013","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023013112031932800_btaa119-B46","volume-title":"MDG 6: Combat HIV\/AIDS, Malaria and Other Diseases","year":"2014"},{"key":"2023013112031932800_btaa119-B47","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1093\/nar\/gkq944","article-title":"Protegen: a web-based protective antigen database and analysis system","volume":"39","author":"Yang","year":"2011","journal-title":"Nucleic Acids Res"},{"key":"2023013112031932800_btaa119-B48","doi-asserted-by":"crossref","first-page":"1608","DOI":"10.1093\/bioinformatics\/btq249","article-title":"PSORTb 3.0: improved protein subcellular localization prediction with refined localization subcategories and predictive capabilities for all prokaryotes","volume":"26","author":"Yu","year":"2010","journal-title":"Bioinformatics"},{"key":"2023013112031932800_btaa119-B58166625","doi-asserted-by":"crossref","first-page":"2463","DOI":"10.1021\/acsbiomaterials.8b00511","article-title":"Peptide amphiphile micelle vaccine size and charge influence the host antibody response","volume":"4","author":"Zhang","year":"2018","journal-title":"ACS Biomater. Sci. Eng.,"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa119\/32962535\/btaa119.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/10\/3185\/48990592\/bioinformatics_36_10_3185.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/10\/3185\/48990592\/bioinformatics_36_10_3185.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T21:16:10Z","timestamp":1675199770000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/10\/3185\/5756199"}},"subtitle":[],"editor":[{"given":"Jinbo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2020,2,25]]},"references-count":53,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2020,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa119","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,5,15]]},"published":{"date-parts":[[2020,2,25]]}}}