{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T17:12:08Z","timestamp":1773162728515,"version":"3.50.1"},"reference-count":24,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T00:00:00Z","timestamp":1696809600000},"content-version":"vor","delay-in-days":8,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Center for Basic Machine Learning Research in Life Science","award":["NNF20OC0062606"],"award-info":[{"award-number":["NNF20OC0062606"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Peptides are ubiquitous throughout life and involved in a wide range of biological processes, ranging from neural signaling in higher organisms to antimicrobial peptides in bacteria. Many peptides are generated post-translationally by cleavage of precursor proteins and can thus not be detected directly from genomics data, as the specificities of the responsible proteases are often not completely understood.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We present DeepPeptide, a deep learning model that predicts cleaved peptides directly from the amino acid sequence. DeepPeptide shows both improved precision and recall for peptide detection compared to previous methodology. We show that the model is capable of identifying peptides in underannotated proteomes.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>DeepPeptide is available online at ku.biolib.com\/DeepPeptide.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad616","type":"journal-article","created":{"date-parts":[[2023,10,6]],"date-time":"2023-10-06T20:19:59Z","timestamp":1696623599000},"source":"Crossref","is-referenced-by-count":11,"title":["DeepPeptide predicts cleaved peptides in proteins using conditional random fields"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1275-8065","authenticated-orcid":false,"given":"Felix","family":"Teufel","sequence":"first","affiliation":[{"name":"Department of Biology, University of Copenhagen , Ole Maal\u00f8es Vej 5 , Copenhagen 2200, Denmark"},{"name":"Digital Science & Innovation, Novo Nordisk A\/S , Novo Nordisk Park , M\u00e5l\u00f8v 2760, Denmark"}]},{"given":"Jan Christian","family":"Refsgaard","sequence":"additional","affiliation":[{"name":"Digital Science & Innovation, Novo Nordisk A\/S , Novo Nordisk Park , M\u00e5l\u00f8v 2760, Denmark"}]},{"given":"Christian Toft","family":"Madsen","sequence":"additional","affiliation":[{"name":"Global Translation, Novo Nordisk A\/S , Novo Nordisk Park , M\u00e5l\u00f8v 2760, Denmark"}]},{"given":"Carsten","family":"Stahlhut","sequence":"additional","affiliation":[{"name":"Digital Science & Innovation, Novo Nordisk A\/S , Novo Nordisk Park , M\u00e5l\u00f8v 2760, Denmark"}]},{"given":"Mads","family":"Gr\u00f8nborg","sequence":"additional","affiliation":[{"name":"Global Translation, Novo Nordisk A\/S , Novo Nordisk Park , M\u00e5l\u00f8v 2760, Denmark"}]},{"given":"Ole","family":"Winther","sequence":"additional","affiliation":[{"name":"Department of Biology, University of Copenhagen , Ole Maal\u00f8es Vej 5 , Copenhagen 2200, Denmark"},{"name":"Department of Applied Mathematics and Computer Science, Technical University of Denmark , Lyngby 2800, Denmark"}]},{"given":"Dennis","family":"Madsen","sequence":"additional","affiliation":[{"name":"Digital Science & Innovation, Novo Nordisk A\/S , Novo Nordisk Park , M\u00e5l\u00f8v 2760, Denmark"}]}],"member":"286","published-online":{"date-parts":[[2023,10,9]]},"reference":[{"key":"2023101908040827800_btad616-B1","doi-asserted-by":"crossref","first-page":"1445","DOI":"10.3390\/ijms23031445","article-title":"Bioactive peptides: synthesis, sources, applications, and proposed mechanisms of action","volume":"23","author":"Akbarian","year":"2022","journal-title":"Int J Mol Sci"},{"key":"2023101908040827800_btad616-B2","first-page":"2623","author":"Akiba","year":"2019"},{"key":"2023101908040827800_btad616-B3","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1038\/s41587-019-0036-z","article-title":"SignalP 5.0 improves signal peptide predictions using deep neural networks","volume":"37","author":"Almagro Armenteros","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2023101908040827800_btad616-B4","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1038\/nmeth.3830","article-title":"Standardized benchmarking in the quest for orthologs","volume":"13","author":"Altenhoff","year":"2016","journal-title":"Nat Methods"},{"key":"2023101908040827800_btad616-B5","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-97886-9","volume-title":"Peptide Chemistry;1-9","author":"Bodanszky","year":"1988"},{"key":"2023101908040827800_btad616-B6","doi-asserted-by":"crossref","first-page":"e202100534","DOI":"10.1002\/cbic.202100534","article-title":"The small open reading frame-encoded peptides: advances in methodologies and functional studies","volume":"23","author":"Chen","year":"2022","journal-title":"Chembiochem"},{"key":"2023101908040827800_btad616-B7","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1016\/j.cell.2019.10.010","article-title":"Discovery of human signaling systems: pairing peptides to G protein-coupled receptors","volume":"179","author":"Foster","year":"2019","journal-title":"Cell"},{"key":"2023101908040827800_btad616-B8","author":"Hallgren","year":"2022"},{"key":"2023101908040827800_btad616-B9","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1021\/acs.chemrev.7b00120","article-title":"Proteolytic cleavage\u2014mechanisms, function, and \u201comic\u201d approaches for a near-ubiquitous posttranslational modification","volume":"118","author":"Klein","year":"2018","journal-title":"Chem Rev"},{"key":"2023101908040827800_btad616-B10","first-page":"282","author":"Lafferty","year":"2001"},{"key":"2023101908040827800_btad616-B11","doi-asserted-by":"crossref","first-page":"W449","DOI":"10.1093\/nar\/gkw329","article-title":"PEP-FOLD3: faster de novo structure prediction for linear peptides in solution and in complex","volume":"44","author":"Lamiable","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023101908040827800_btad616-B12","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"2023101908040827800_btad616-B13","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1038\/s41587-022-01226-0","article-title":"Identification of antimicrobial peptides from the human gut microbiome using deep learning","volume":"40","author":"Ma","year":"2022","journal-title":"Nat Biotechnol"},{"key":"2023101908040827800_btad616-B14","doi-asserted-by":"crossref","first-page":"6235","DOI":"10.1038\/s41467-022-34031-z","article-title":"Combining mass spectrometry and machine learning to discover bioactive peptides","volume":"13","author":"Madsen","year":"2022","journal-title":"Nat Commun"},{"key":"2023101908040827800_btad616-B15","doi-asserted-by":"crossref","first-page":"1120","DOI":"10.1093\/bioinformatics\/btt103","article-title":"PeptideLocator: prediction of bioactive peptides in protein sequences","volume":"29","author":"Mooney","year":"2013","journal-title":"Bioinformatics"},{"key":"2023101908040827800_btad616-B16","doi-asserted-by":"crossref","first-page":"12826","DOI":"10.1016\/S0021-9258(18)51561-1","article-title":"Complete sequences of glucagon-like peptide-1 from human and pig small intestine","volume":"264","author":"Orskov","year":"1989","journal-title":"J Biol Chem"},{"key":"2023101908040827800_btad616-B17","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118; e2016239118","author":"Rives","year":"2021","journal-title":"Proc Natl Acad Sci USA"},{"key":"2023101908040827800_btad616-B18","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1152\/physrev.00013.2014","article-title":"Physiology of proglucagon peptides: role of glucagon and GLP-1 in health and disease","volume":"95","author":"Sandoval","year":"2015","journal-title":"Physiol Rev"},{"key":"2023101908040827800_btad616-B19","doi-asserted-by":"crossref","first-page":"D344","DOI":"10.1093\/nar\/gks1067","article-title":"New and continuing developments at PROSITE","volume":"41","author":"Sigrist","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2023101908040827800_btad616-B20","author":"Teufel","year":"2023"},{"key":"2023101908040827800_btad616-B21","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1038\/s41587-021-01156-3","article-title":"SignalP 6.0 predicts all five types of signal peptides using protein language models","volume":"40","author":"Teufel","year":"2022","journal-title":"Nat Biotechnol"},{"key":"2023101908040827800_btad616-B22","doi-asserted-by":"crossref","first-page":"D480","DOI":"10.1093\/nar\/gkaa1100","article-title":"UniProt: the universal protein knowledgebase in 2021","volume":"49","author":"The UniProt Consortium","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2023101908040827800_btad616-B23","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1109\/TIT.1967.1054010","article-title":"Error bounds for convolutional codes and an asymptotically optimum decoding algorithm","volume":"13","author":"Viterbi","year":"1967","journal-title":"IEEE Trans Inform Theory"},{"key":"2023101908040827800_btad616-B24","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1038\/s41392-022-00904-4","article-title":"Therapeutic peptides: current applications and future directions","volume":"7","author":"Wang","year":"2022","journal-title":"Signal Transduct Target Ther"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad616\/51960023\/btad616.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/10\/btad616\/52241432\/btad616.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/10\/btad616\/52241432\/btad616.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,19]],"date-time":"2023-10-19T12:20:18Z","timestamp":1697718018000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad616\/7301438"}},"subtitle":[],"editor":[{"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":24,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad616","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,10,1]]},"published":{"date-parts":[[2023,10,1]]},"article-number":"btad616"}}