{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T19:55:47Z","timestamp":1768334147737,"version":"3.49.0"},"reference-count":32,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T00:00:00Z","timestamp":1766707200000},"content-version":"vor","delay-in-days":3,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-18-RHUS-0013"],"award-info":[{"award-number":["ANR-18-RHUS-0013"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Sequence variability can be extremely high, particularly in bacteria due to the rapid accumulation of mutations linked to their high replication rate and environmental selection pressure, which often favors diversifying selection. For most species, there are no automated, computationally efficient tools available for constructing a nonredundant database covering the allelic variability of target proteins.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We have thus developed Bacterial Peptide Sequence Selection, a Nextflow pipeline to define a minimal list of peptide sequences for detecting all variants of a protein of interest.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>All the code and containers used are freely available on Gitlab from https:\/\/gitbio.ens-lyon.fr\/ciri\/stapath\/bpss or on Zenodo (10.5281\/zenodo.16894981) under GPLv3 open-source license and DockerHub platform from https:\/\/hub.docker.com\/u\/stapath.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf677","type":"journal-article","created":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T12:47:57Z","timestamp":1766234877000},"source":"Crossref","is-referenced-by-count":0,"title":["BPSS: a Nextflow pipeline for Bacterial Peptide Sequence Selection to detect protein diversity"],"prefix":"10.1093","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3687-8646","authenticated-orcid":false,"given":"Sylv\u00e8re","family":"Bastien","sequence":"first","affiliation":[{"name":"CIRI, Center for Integrative Research in Infectious Diseases and Immunology, Universit\u00e9 de Lyon, Inserm U1111, Universit\u00e9 Claude Bernard Lyon 1, CNRS UMR5308, ENS de Lyon , Lyon, 69007,","place":["France"]},{"name":"Institut des Agents Infectieux, Centre National de R\u00e9f\u00e9rence des Staphylocoques, Hospices Civils de Lyon , Lyon, 69004,","place":["France"]}]},{"given":"Pauline","family":"Fran\u00e7ois","sequence":"additional","affiliation":[{"name":"CIRI, Center for Integrative Research in Infectious Diseases and Immunology, Universit\u00e9 de Lyon, Inserm U1111, Universit\u00e9 Claude Bernard Lyon 1, CNRS UMR5308, ENS de Lyon , Lyon, 69007,","place":["France"]},{"name":"Institut des Agents Infectieux, Centre National de R\u00e9f\u00e9rence des Staphylocoques, Hospices Civils de Lyon , Lyon, 69004,","place":["France"]}]},{"given":"Sara","family":"Moussadeq","sequence":"additional","affiliation":[{"name":"CIRI, Center for Integrative Research in Infectious Diseases and Immunology, Universit\u00e9 de Lyon, Inserm U1111, Universit\u00e9 Claude Bernard Lyon 1, CNRS UMR5308, ENS de Lyon , Lyon, 69007,","place":["France"]},{"name":"Institut des Agents Infectieux, Centre National de R\u00e9f\u00e9rence des Staphylocoques, Hospices Civils de Lyon , Lyon, 69004,","place":["France"]}]},{"given":"J\u00e9r\u00f4me","family":"Lemoine","sequence":"additional","affiliation":[{"name":"Universit\u00e9 de Lyon, CNRS, Universit\u00e9 Claude Bernard Lyon 1, Institut des Sciences Analytiques, UMR 5280 , Villeurbanne, 69100,","place":["France"]}]},{"given":"Karen","family":"Moreau","sequence":"additional","affiliation":[{"name":"CIRI, Center for Integrative Research in Infectious Diseases and Immunology, Universit\u00e9 de Lyon, Inserm U1111, Universit\u00e9 Claude Bernard Lyon 1, CNRS UMR5308, ENS de Lyon , Lyon, 69007,","place":["France"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9412-7106","authenticated-orcid":false,"given":"Fran\u00e7ois","family":"Vandenesch","sequence":"additional","affiliation":[{"name":"CIRI, Center for Integrative Research in Infectious Diseases and Immunology, Universit\u00e9 de Lyon, Inserm U1111, Universit\u00e9 Claude Bernard Lyon 1, CNRS UMR5308, ENS de Lyon , Lyon, 69007,","place":["France"]},{"name":"Institut des Agents Infectieux, Centre National de R\u00e9f\u00e9rence des Staphylocoques, Hospices Civils de Lyon , Lyon, 69004,","place":["France"]}]}],"member":"286","published-online":{"date-parts":[[2025,12,23]]},"reference":[{"key":"2026011308213646300_btaf677-B1","author":"Barnier","year":"2024"},{"key":"2026011308213646300_btaf677-B2","author":"Barrett","year":"2024"},{"key":"2026011308213646300_btaf677-B3","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1186\/1471-2105-10-421","article-title":"BLAST+: architecture and applications","volume":"10","author":"Camacho","year":"2009","journal-title":"BMC Bioinformatics"},{"key":"2026011308213646300_btaf677-B4","author":"Chang","year":"2024"},{"key":"2026011308213646300_btaf677-B5","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1007\/978-3-540-35306-5_10","volume-title":"Structural Approaches to Sequence Evolution: Molecules, Networks, Populations, Biological and Medical Physics, Biomedical Engineering","author":"Charif","year":"2007"},{"key":"2026011308213646300_btaf677-B6","doi-asserted-by":"crossref","first-page":"D325","DOI":"10.1093\/nar\/gki008","article-title":"VFDB: a reference database for bacterial virulence factors","volume":"33","author":"Chen","year":"2005","journal-title":"Nucleic Acids Res"},{"key":"2026011308213646300_btaf677-B7","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1038\/nbt.3820","article-title":"Nextflow enables reproducible computational workflows","volume":"35","author":"Di Tommaso","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2026011308213646300_btaf677-B8","article-title":"ResFinder\u2014an open online resource for identification of antimicrobial resistance genes in next-generation sequencing data and prediction of phenotypes from genotypes","volume":"8","author":"Florensa","year":"2022","journal-title":"Microb Genom"},{"key":"2026011308213646300_btaf677-B9","doi-asserted-by":"crossref","first-page":"3150","DOI":"10.1093\/bioinformatics\/bts565","article-title":"CD-HIT: accelerated for clustering the next-generation sequencing data","volume":"28","author":"Fu","year":"2012","journal-title":"Bioinformatics"},{"key":"2026011308213646300_btaf677-B10","doi-asserted-by":"crossref","first-page":"124","DOI":"10.12688\/wellcomeopenres.14826.1","article-title":"Open-access bacterial population genomics: BIGSdb software, the PubMLST.org website and their applications","volume":"3","author":"Jolley","year":"2018","journal-title":"Wellcome Open Res"},{"key":"2026011308213646300_btaf677-B11","doi-asserted-by":"crossref","first-page":"D29","DOI":"10.1093\/nar\/gki098","article-title":"The EMBL nucleotide sequence database","volume":"33","author":"Kanz","year":"2005","journal-title":"Nucleic Acids Res"},{"key":"2026011308213646300_btaf677-B12","doi-asserted-by":"crossref","first-page":"lqz004","DOI":"10.1093\/nargab\/lqz004","article-title":"Rapid peptides generator: fast and efficient in silico protein digestion","volume":"2","author":"Maillet","year":"2020","journal-title":"NAR Genom Bioinform"},{"key":"2026011308213646300_btaf677-B13","doi-asserted-by":"crossref","first-page":"598","DOI":"10.1038\/s41579-024-01054-w","article-title":"ESKAPE pathogens: antimicrobial resistance, epidemiology, clinical impact and therapeutics","volume":"22","author":"Miller","year":"2024","journal-title":"Nat Rev Microbiol"},{"key":"2026011308213646300_btaf677-B14","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1186\/s13059-020-01965-w","article-title":"WhatsGNU: a tool for identifying proteomic novelty","volume":"21","author":"Moustafa","year":"2020","journal-title":"Genome Biol"},{"key":"2026011308213646300_btaf677-B15","author":"Pag\u00e8s","year":"2024"},{"key":"2026011308213646300_btaf677-B16","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1093\/bioinformatics\/bty633","article-title":"ape 5.0: an environment for modern phylogenetics and evolutionary analyses in R","volume":"35","author":"Paradis","year":"2019","journal-title":"Bioinformatics"},{"key":"2026011308213646300_btaf677-B17","doi-asserted-by":"crossref","first-page":"410","DOI":"10.3389\/fmicb.2016.00410","article-title":"Proteomics As a tool for studying bacterial virulence and antimicrobial resistance","volume":"7","author":"P\u00e9rez-Llarena","year":"2016","journal-title":"Front Microbiol"},{"key":"2026011308213646300_btaf677-B18","doi-asserted-by":"crossref","first-page":"e5261","DOI":"10.7717\/peerj.5261","article-title":"Staphylococcus aureus viewed from the perspective of 40,000+ genomes","volume":"6","author":"Petit","year":"2018","journal-title":"PeerJ"},{"key":"2026011308213646300_btaf677-B19","doi-asserted-by":"crossref","first-page":"1162617","DOI":"10.3389\/fcimb.2023.1162617","article-title":"Targeted proteomics links virulence factor expression with clinical severity in staphylococcal pneumonia","volume":"13","author":"Pivard","year":"2023","journal-title":"Front Cell Infect Microbiol"},{"key":"2026011308213646300_btaf677-B20","doi-asserted-by":"crossref","first-page":"e9490","DOI":"10.1371\/journal.pone.0009490","article-title":"FastTree 2\u2014approximately maximum-likelihood trees for large alignments","volume":"5","author":"Price","year":"2010","journal-title":"PLoS One"},{"key":"2026011308213646300_btaf677-B21","volume-title":"R: A Language and Environment for Statistical Computing R Foundation for Statistical Computing","author":"R Development Core Team","year":"2024"},{"key":"2026011308213646300_btaf677-B22","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1016\/S0168-9525(00)02024-2","article-title":"EMBOSS: the European Molecular Biology Open Software Suite","volume":"16","author":"Rice","year":"2000","journal-title":"Trends Genet"},{"key":"2026011308213646300_btaf677-B23","doi-asserted-by":"crossref","first-page":"D20","DOI":"10.1093\/nar\/gkab1112","article-title":"Database resources of the national center for biotechnology information","volume":"50","author":"Sayers","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2026011308213646300_btaf677-B24","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1038\/msb.2011.75","article-title":"Fast, scalable generation of high-quality protein multiple sequence alignments using Clustal Omega","volume":"7","author":"Sievers","year":"2011","journal-title":"Mol Syst Biol"},{"key":"2026011308213646300_btaf677-B25","author":"Sievert","year":"2020"},{"key":"2026011308213646300_btaf677-B26","doi-asserted-by":"crossref","first-page":"D806","DOI":"10.1093\/nar\/gkae1042","article-title":"PanKB: an interactive microbial pangenome knowledgebase for research, biotechnological innovation, and knowledge mining","volume":"53","author":"Sun","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026011308213646300_btaf677-B27","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1186\/1471-2105-10-329","article-title":"PLAST: parallel local alignment search tool for database comparison","volume":"10","author":"Van Nguyen","year":"2009","journal-title":"BMC Bioinformatics"},{"key":"2026011308213646300_btaf677-B28","doi-asserted-by":"crossref","first-page":"1686","DOI":"10.21105\/joss.01686","article-title":"Welcome to the tidyverse","volume":"4","author":"Wickham","year":"2019","journal-title":"JOSS"},{"key":"2026011308213646300_btaf677-B29","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24277-4","volume-title":"ggplot2: Elegant Graphics for Data Analysis","author":"Wickham","year":"2016"},{"key":"2026011308213646300_btaf677-B30","author":"Wilke","year":"2024"},{"key":"2026011308213646300_btaf677-B31","author":"Xie","year":"2024"},{"key":"2026011308213646300_btaf677-B32","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1111\/2041-210X.12628","article-title":"ggtree: An r package for visualization and annotation of phylogenetic trees with their covariates and other associateddata","volume":"8","author":"Yu","year":"2017","journal-title":"Methods Ecol Evol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf677\/66129805\/btaf677.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/1\/btaf677\/66129805\/btaf677.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/1\/btaf677\/66129805\/btaf677.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T13:21:48Z","timestamp":1768310508000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf677\/8405039"}},"subtitle":[],"editor":[{"given":"Christina","family":"Kendziorski","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,12,23]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf677","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,1]]},"published":{"date-parts":[[2025,12,23]]},"article-number":"btaf677"}}