{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T20:17:39Z","timestamp":1792181859700,"version":"4.4.0"},"reference-count":34,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T00:00:00Z","timestamp":1709078400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Korean Ministry of Science and ICT","award":["No. 2021M3H9A2030520 and RS-2023-00263899"],"award-info":[{"award-number":["No. 2021M3H9A2030520 and RS-2023-00263899"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>\n                    In proteomics, a crucial aspect is to identify peptide sequences. De novo sequencing methods have been widely employed to identify peptide sequences, and numerous tools have been proposed over the past two decades. Recently, deep learning approaches have been introduced for de novo sequencing. Previous methods focused on encoding tandem mass spectra and predicting peptide sequences from the first amino acid onwards. However, when predicting peptides using tandem mass spectra, the peptide sequence can be predicted not only from the first amino acid but also from the last amino acid due to the coexistence of\n                    <jats:italic>b<\/jats:italic>\n                    -ion (or\n                    <jats:italic>a<\/jats:italic>\n                    - or\n                    <jats:italic>c<\/jats:italic>\n                    -ion) and\n                    <jats:italic>y<\/jats:italic>\n                    -ion (or\n                    <jats:italic>x<\/jats:italic>\n                    - or\n                    <jats:italic>z<\/jats:italic>\n                    -ion) fragments in the tandem mass spectra. Therefore, it is essential to predict peptide sequences bidirectionally. Our approach, called NovoB, utilizes a Transformer model to predict peptide sequences bidirectionally, starting with both the first and last amino acids. In comparison to Casanovo, our method achieved an improvement of the average peptide-level accuracy rate of approximately 9.8% across all species.\n                  <\/jats:p>","DOI":"10.1371\/journal.pcbi.1011892","type":"journal-article","created":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T13:23:01Z","timestamp":1709126581000},"page":"e1011892","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":27,"title":["Bidirectional de novo peptide sequencing using a transformer model"],"prefix":"10.1371","volume":"20","author":[{"given":"Sangjeong","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6785-7760","authenticated-orcid":true,"given":"Hyunwoo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,2,28]]},"reference":[{"issue":"9","key":"pcbi.1011892.ref001","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1038\/nrm1468","article-title":"The ABC\u2019s (and XYZ\u2019s) of peptide sequencing","volume":"5","author":"H Steen","year":"2004","journal-title":"Nature reviews Molecular cell biology"},{"issue":"3\u20134","key":"pcbi.1011892.ref002","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1089\/106652799318300","article-title":"A De novo peptide sequencing via tandem mass spectrometry","volume":"6","author":"V Dan\u010d\u00edk","year":"1999","journal-title":"Journal of computational biology"},{"issue":"20","key":"pcbi.1011892.ref003","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1002\/rcm.1196","article-title":"PEAKS: powerful software for peptide de novo sequencing by tandem mass spectrometry","volume":"17","author":"B Ma","year":"2003","journal-title":"Rapid communications in mass spectrometry"},{"issue":"5","key":"pcbi.1011892.ref004","doi-asserted-by":"crossref","first-page":"2713","DOI":"10.1021\/pr100182k","article-title":"pNovo: de novo peptide sequencing and identification using HCD spectra","volume":"9","author":"H Chi","year":"2010","journal-title":"Journal of proteome research"},{"issue":"1","key":"pcbi.1011892.ref005","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1002\/pmic.201200439","article-title":"Comet: an open-source MS\/MS sequence database search tool","volume":"13","author":"J K Eng","year":"2013","journal-title":"Proteomics"},{"issue":"1","key":"pcbi.1011892.ref006","doi-asserted-by":"crossref","first-page":"5277","DOI":"10.1038\/ncomms6277","article-title":"MS-GF+ makes progress towards a universal database search tool for proteomics","volume":"5","author":"S Kim","year":"2014","journal-title":"Nature communications"},{"issue":"12","key":"pcbi.1011892.ref007","doi-asserted-by":"crossref","first-page":"2301","DOI":"10.1038\/nprot.2016.136","article-title":"The MaxQuant computational platform for mass spectrometry-based shotgun proteomics","volume":"11","author":"S Tyanova","year":"2016","journal-title":"Nature protocols"},{"issue":"4","key":"pcbi.1011892.ref008","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1021\/ac048788h","article-title":"PepNovo: de novo peptide sequencing via probabilistic network modeling","volume":"77","author":"A Frank","year":"2005","journal-title":"Analytical chemistry"},{"issue":"11","key":"pcbi.1011892.ref009","doi-asserted-by":"crossref","first-page":"1885","DOI":"10.1007\/s13361-015-1204-0","article-title":"Novor: real-time peptide de novo sequencing software","volume":"26","author":"B Ma","year":"2015","journal-title":"Journal of the American Society for Mass Spectrometry"},{"issue":"31","key":"pcbi.1011892.ref010","doi-asserted-by":"crossref","first-page":"8247","DOI":"10.1073\/pnas.1705691114","article-title":"De novo peptide sequencing by deep learning","volume":"114","author":"NH Tran","year":"2017","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"8","key":"pcbi.1011892.ref011","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural computation"},{"key":"pcbi.1011892.ref012","doi-asserted-by":"crossref","unstructured":"Cho K, van Merrienboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv 2014;1406.1078.","DOI":"10.3115\/v1\/D14-1179"},{"issue":"5","key":"pcbi.1011892.ref013","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1038\/s42256-021-00304-3","article-title":"Computationally instrument-resolution-independent de novo peptide sequencing for high-resolution devices","volume":"3","author":"Qiao Ru","year":"2021","journal-title":"Nature Machine Intelligence"},{"key":"pcbi.1011892.ref014","doi-asserted-by":"crossref","unstructured":"Yilmaz M, Fondrie W, Bittremieux W, Oh S, Noble W S De novo mass spectrometry peptide sequencing with a transformer model. In: International Conference on Machine Learning. PMLR 2022;25514\u201325522.","DOI":"10.1101\/2022.02.07.479481"},{"key":"pcbi.1011892.ref015","first-page":"2023","article-title":"De novo peptide sequencing with InstaNovo: Accurate, database-free peptide identification for large scale proteomics experiments","author":"K Eloff","year":"2023","journal-title":"bioRxiv"},{"key":"pcbi.1011892.ref016","article-title":"Attention is all you need","volume":"30","author":"A Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"pcbi.1011892.ref017","first-page":"2023","article-title":"BiATNovo: A Self-Attention based Bidirectional Peptide Sequencing Method","author":"S Wu","year":"2023","journal-title":"bioRxiv"},{"key":"pcbi.1011892.ref018","article-title":"Mitigating the missing fragmentation problem in de novo peptide sequencing with a two stage graph-based deep learning model","author":"Z Mao","year":"2023","journal-title":"Nature Machine Intelligence"},{"key":"pcbi.1011892.ref019","unstructured":"Hamilton W L, Ying R, Leskovec J Representation learning on graphs: Methods and applications. arXiv preprint arXiv 2017;1709.05584."},{"key":"pcbi.1011892.ref020","doi-asserted-by":"crossref","first-page":"103234","DOI":"10.1016\/j.artint.2020.103234","article-title":"Synchronous bidirectional inference for neural sequence generation","volume":"281","author":"J Zhang","year":"2020","journal-title":"Artificial Intelligence"},{"key":"pcbi.1011892.ref021","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1162\/tacl_a_00256","article-title":"Synchronous bidirectional neural machine translation","volume":"7","author":"L Zhou","year":"2019","journal-title":"Transactions of the Association for Computational Linguistics"},{"issue":"12","key":"pcbi.1011892.ref022","doi-asserted-by":"crossref","first-page":"4208","DOI":"10.1021\/acs.jproteome.6b00211","article-title":"Label-free proteomic reveals that cowpea severe mosaic virus transiently suppresses the host leaf protein accumulation during the compatible interaction with cowpea (Vigna unguiculata [L.] Walp.)","volume":"15","author":"AL Paiva","year":"2016","journal-title":"Journal of Proteome Research"},{"issue":"3","key":"pcbi.1011892.ref023","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1074\/mcp.M116.063867","article-title":"Impact of cystinosin glycosylation on protein stability by differential dynamic stable isotope labeling by amino acids in cell culture (SILAC)","volume":"16","author":"N Nevo","year":"2017","journal-title":"Molecular & Cellular Proteomics"},{"issue":"10","key":"pcbi.1011892.ref024","doi-asserted-by":"crossref","first-page":"3773","DOI":"10.1021\/acs.jproteome.6b00569","article-title":"Combination of bottom-up 2D-LC-MS and semi-top-down GelFree-LC-MS enhances coverage of proteome and low molecular weight short open reading frame encoded peptides of the archaeon Methanosarcina mazei","volume":"15","author":"L Cassidy","year":"2016","journal-title":"Journal of proteome research"},{"issue":"2","key":"pcbi.1011892.ref025","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1101\/gr.215293.116","article-title":"Large-scale reduction of the Bacillus subtilis genome: consequences for the transcriptional network, resource allocation, and metabolism","volume":"27","author":"R Reu\u00df D","year":"2017","journal-title":"Genome research"},{"issue":"1","key":"pcbi.1011892.ref026","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/nmicrobiol.2016.195","article-title":"Chemosynthetic symbionts of marine invertebrate animals are capable of nitrogen fixation","volume":"2","author":"JM Petersen","year":"2016","journal-title":"Nature microbiology"},{"issue":"1\u20132","key":"pcbi.1011892.ref027","doi-asserted-by":"crossref","first-page":"1600406","DOI":"10.1002\/pmic.201600406","article-title":"In-depth characterization of the tomato fruit pericarp proteome","volume":"17","author":"CI Mata","year":"2017","journal-title":"Proteomics"},{"issue":"2","key":"pcbi.1011892.ref028","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1021\/acs.jproteome.6b00647","article-title":"Quantitative global proteomics of yeast PBP1 deletion mutants and their stress responses identifies glucose metabolism, mitochondrial, and stress granule changes","volume":"16","author":"G Seidel","year":"2017","journal-title":"Journal of proteome research"},{"issue":"8","key":"pcbi.1011892.ref029","doi-asserted-by":"crossref","first-page":"2841","DOI":"10.1021\/acs.jproteome.6b00423","article-title":"Proteome analysis of the hemolymph, mushroom body, and antenna provides novel insight into honeybee resistance against varroa infestation","volume":"15","author":"H Hu","year":"2016","journal-title":"Journal of proteome research"},{"issue":"1","key":"pcbi.1011892.ref030","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1021\/acs.jproteome.6b00596","article-title":"Proteomic and bioinformatic characterization of extracellular vesicles released from human macrophages upon influenza A virus infection","volume":"16","author":"W Cypryk","year":"2017","journal-title":"Journal of Proteome Research"},{"issue":"6","key":"pcbi.1011892.ref031","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1038\/s41592-018-0003-5","article-title":"BoxCar acquisition method enables single-shot proteomics at a depth of 10,000 proteins in 100 minutes","volume":"15","author":"F Meier","year":"2018","journal-title":"Nature methods"},{"issue":"6","key":"pcbi.1011892.ref032","doi-asserted-by":"crossref","first-page":"2065","DOI":"10.3390\/ijms21062065","article-title":"The beta subunit of nascent polypeptide associated complex plays a role in flowers and Siliques development of Arabidopsis Thaliana","volume":"21","author":"J F\u00edla","year":"2020","journal-title":"International Journal of Molecular Sciences"},{"issue":"5","key":"pcbi.1011892.ref033","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1038\/s42255-020-0200-2","article-title":"NFYB-1 regulates mitochondrial function and longevity via lysosomal prosaposin","volume":"2","author":"R G Tharyan","year":"2020","journal-title":"Nature Metabolism"},{"issue":"8","key":"pcbi.1011892.ref034","doi-asserted-by":"crossref","first-page":"2120","DOI":"10.1021\/acsinfecdis.0c00196","article-title":"Predictive signatures of 19 antibiotic-induced Escherichia coli proteomes","volume":"6","author":"Y Yu","year":"2020","journal-title":"ACS Infectious Diseases"}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T13:23:20Z","timestamp":1709126600000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011892"}},"subtitle":[],"editor":[{"given":"Wout","family":"Bittremieux","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,2,28]]},"references-count":34,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,2,28]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1011892","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,28]]}}}