{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:11:00Z","timestamp":1772136660206,"version":"3.50.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Comput Sci"],"DOI":"10.1038\/s43588-025-00880-z","type":"journal-article","created":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T09:04:15Z","timestamp":1759482255000},"page":"998-1009","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Proteoform search from protein database with top-down mass spectra"],"prefix":"10.1038","volume":"5","author":[{"given":"Kunyi","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baozhen","family":"Shan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2157-2775","authenticated-orcid":false,"given":"Ming","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4344-8791","authenticated-orcid":false,"given":"Lusheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,3]]},"reference":[{"key":"880_CR1","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1038\/s43586-024-00318-2","volume":"4","author":"DS Roberts","year":"2024","unstructured":"Roberts, D. S. et al. Top-down proteomics. Nat. Rev. Methods Primers 4, 38 (2024).","journal-title":"Nat. Rev. Methods Primers"},{"key":"880_CR2","doi-asserted-by":"publisher","first-page":"1800361","DOI":"10.1002\/pmic.201800361","volume":"19","author":"LV Schaffer","year":"2019","unstructured":"Schaffer, L. V. et al. Identification and quantification of proteoforms by mass spectrometry. Proteomics 19, 1800361 (2019).","journal-title":"Proteomics"},{"key":"880_CR3","doi-asserted-by":"publisher","first-page":"aaf7329","DOI":"10.1126\/scisignal.aaf7329","volume":"9","author":"SC Larsen","year":"2016","unstructured":"Larsen, S. C. et al. Proteome-wide analysis of arginine monomethylation reveals widespread occurrence in human cells. Sci. Signal. 9, aaf7329 (2016).","journal-title":"Sci. Signal."},{"key":"880_CR4","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1074\/mcp.M800099-MCP200","volume":"8","author":"NM Karabacak","year":"2009","unstructured":"Karabacak, N. M. et al. Sensitive and specific identification of wild type and variant proteins from 8 to 669 kDa using top-down mass spectrometry. Mol Cell Proteomics 8, 846\u201356 (2009).","journal-title":"Mol Cell Proteomics"},{"key":"880_CR5","doi-asserted-by":"publisher","first-page":"W701","DOI":"10.1093\/nar\/gkm371","volume":"35","author":"L Zamdborg","year":"2007","unstructured":"Zamdborg, L. et al. Prosight PTM 2.0: improved protein identification and characterization for top down mass spectrometry. Nucleic Acids Res. 35, W701\u2013W706 (2007).","journal-title":"Nucleic Acids Res."},{"key":"880_CR6","doi-asserted-by":"publisher","first-page":"M111","DOI":"10.1074\/mcp.M111.008524","volume":"11","author":"X Liu","year":"2012","unstructured":"Liu, X. et al. Protein identification using top-down spectra. Mol. Cell. Proteom. 11, M111\u2013008524 (2012).","journal-title":"Mol. Cell. Proteom."},{"key":"880_CR7","doi-asserted-by":"publisher","first-page":"5830","DOI":"10.1021\/pr400849y","volume":"12","author":"X Liu","year":"2013","unstructured":"Liu, X. et al. Identification of ultramodified proteins using top-down tandem mass spectra. J. Proteome Res. 12, 5830\u20135838 (2013).","journal-title":"J. Proteome Res."},{"key":"880_CR8","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1093\/bioinformatics\/btw806","volume":"33","author":"Q Kou","year":"2017","unstructured":"Kou, Q. et al. A mass graph-based approach for the identification of modified proteoforms using top-down tandem mass spectra. Bioinformatics 33, 1309\u20131316 (2017).","journal-title":"Bioinformatics"},{"key":"880_CR9","doi-asserted-by":"publisher","first-page":"3495","DOI":"10.1093\/bioinformatics\/btw398","volume":"32","author":"Q Kou","year":"2016","unstructured":"Kou, Q., Xun, L. & Liu, X. TopPIC: a software tool for top-down mass spectrometry-based proteoform identification and characterization. Bioinformatics 32, 3495\u20133497 (2016).","journal-title":"Bioinformatics"},{"key":"880_CR10","doi-asserted-by":"publisher","first-page":"bbab599","DOI":"10.1093\/bib\/bbab599","volume":"23","author":"Z Zhan","year":"2022","unstructured":"Zhan, Z. & Wang, L. Proteoform identification based on top-down tandem mass spectra with peak error corrections. Brief. Bioinformatics 23, bbab599 (2022).","journal-title":"Brief. Bioinformatics"},{"key":"880_CR11","doi-asserted-by":"publisher","first-page":"btae149","DOI":"10.1093\/bioinformatics\/btae149","volume":"40","author":"Z Zhan","year":"2024","unstructured":"Zhan, Z. & Wang, L. Fast peak error correction algorithms for proteoform identification using top-down tandem mass spectra. Bioinformatics 40, btae149 (2024).","journal-title":"Bioinformatics"},{"key":"880_CR12","doi-asserted-by":"publisher","first-page":"D609","DOI":"10.1093\/nar\/gkae1010","volume":"53","author":"UniProt Consortium.","year":"2025","unstructured":"UniProt Consortium. Uniprot: the universal protein knowledgebase in 2025. Nucleic Acids Res. 53, D609\u2013D617 (2025).","journal-title":"Nucleic Acids Res."},{"key":"880_CR13","doi-asserted-by":"publisher","first-page":"1700306","DOI":"10.1002\/pmic.201700306","volume":"18","author":"Q Kou","year":"2018","unstructured":"Kou, Q., Wu, S. & Liu, X. Systematic evaluation of protein sequence filtering algorithms for proteoform identification using top-down mass spectrometry. Proteomics 18, 1700306 (2018).","journal-title":"Proteomics"},{"key":"880_CR14","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1038\/nbt.3267","volume":"33","author":"JM Chick","year":"2015","unstructured":"Chick, J. M. et al. A mass-tolerant database search identifies a large proportion of unassigned spectra in shotgun proteomics as modified peptides. Nat. Biotechnol. 33, 743\u2013749 (2015).","journal-title":"Nat. Biotechnol."},{"key":"880_CR15","doi-asserted-by":"publisher","first-page":"4390","DOI":"10.1021\/ac00096a002","volume":"66","author":"M Mann","year":"1994","unstructured":"Mann, M. & Wilm, M. Error-tolerant identification of peptides in sequence databases by peptide sequence tags. Anal. Chem. 66, 4390\u20134399 (1994).","journal-title":"Anal. Chem."},{"key":"880_CR16","doi-asserted-by":"crossref","unstructured":"Yang, R. et al. A spectrum graph-based protein sequence filtering algorithm for proteoform identification by top-down mass spectrometry. In 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 222\u2013229 (IEEE, 2017).","DOI":"10.1109\/BIBM.2017.8217653"},{"key":"880_CR17","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1093\/bioinformatics\/btu678","volume":"31","author":"F Deng","year":"2014","unstructured":"Deng, F., Wang, L. & Liu, X. An efficient algorithm for the blocked pattern matching problem. Bioinformatics 31, 532\u2013538 (2014).","journal-title":"Bioinformatics"},{"key":"880_CR18","doi-asserted-by":"publisher","first-page":"3082","DOI":"10.1021\/acs.analchem.5b03963","volume":"88","author":"R-X Sun","year":"2016","unstructured":"Sun, R.-X. et al. pTop 1.0: A high-accuracy and high-efficiency search engine for intact protein identification. Anal. Chem. 88, 3082\u20133090 (2016).","journal-title":"Anal. Chem."},{"key":"880_CR19","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1038\/nmeth.4388","volume":"14","author":"J Park","year":"2017","unstructured":"Park, J. et al. Informed-proteomics: open-source software package for top-down proteomics. Nat. Methods 14, 909\u2013914 (2017).","journal-title":"Nat. Methods"},{"key":"880_CR20","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1021\/acs.jproteome.2c00673","volume":"22","author":"DL Tabb","year":"2023","unstructured":"Tabb, D. L. et al. Comparing top-down proteoform identification: deconvolution, PrSM overlap, and PTM detection. J. Proteome Res. 22, 2199\u20132217 (2023).","journal-title":"J. Proteome Res."},{"key":"880_CR21","doi-asserted-by":"publisher","first-page":"1800206","DOI":"10.1002\/pmic.201800206","volume":"18","author":"MG Awan","year":"2018","unstructured":"Awan, M. G. & Saeed, F. Mass-simulator: a highly configurable simulator for generating ms\/ms datasets for benchmarking of proteomics algorithms. Proteomics 18, 1800206 (2018).","journal-title":"Proteomics"},{"key":"880_CR22","doi-asserted-by":"publisher","first-page":"2772","DOI":"10.1074\/mcp.M110.002766","volume":"9","author":"X Liu","year":"2010","unstructured":"Liu, X. et al. Deconvolution and database search of complex tandem mass spectra of intact proteins. Mol. Cell. Proteom. 9, 2772\u20132782 (2010).","journal-title":"Mol. Cell. Proteom."},{"key":"880_CR23","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1038\/s42256-024-00816-8","volume":"6","author":"A Young","year":"2024","unstructured":"Young, A., R\u00f6st, H. & Wang, B. Tandem mass spectrum prediction for small molecules using graph transformers. Nat. Mach. Intell. 6, 404\u2013416 (2024).","journal-title":"Nat. Mach. Intell."},{"key":"880_CR24","unstructured":"TopPIC Suite (TopPic, 2023)."},{"key":"880_CR25","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1038\/nbt.2377","volume":"30","author":"MC Chambers","year":"2012","unstructured":"Chambers, M. C. et al. A cross-platform toolkit for mass spectrometry and proteomics. Nat. Biotechnol. 30, 918\u2013920 (2012).","journal-title":"Nat. Biotechnol."},{"key":"880_CR26","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.cels.2020.01.003","volume":"10","author":"K Jeong","year":"2020","unstructured":"Jeong, K. et al. Flashdeconv: ultrafast, high-quality feature deconvolution for top-down proteomics. Cell Syst. 10, 213\u2013218 (2020).","journal-title":"Cell Syst."},{"key":"880_CR27","doi-asserted-by":"publisher","first-page":"3354","DOI":"10.1021\/pr8001244","volume":"7","author":"S Kim","year":"2008","unstructured":"Kim, S., Gupta, N. & Pevzner, P. A. Spectral probabilities and generating functions of tandem mass spectra: a strike against decoy databases. J. Proteome Res. 7, 3354\u20133363 (2008).","journal-title":"J. Proteome Res."},{"key":"880_CR28","doi-asserted-by":"publisher","first-page":"3388","DOI":"10.1074\/mcp.M116.058073","volume":"15","author":"EA Vorontsov","year":"2016","unstructured":"Vorontsov, E. A., Rensen, E., Prangishvili, D., Krupovic, M. & Chamot-Rooke, J. Abundant lysine methylation and N-terminal acetylation in sulfolobus islandicus revealed by bottom-up and top-down proteomics. Mol. Cell. Proteom. 15, 3388\u20133404 (2016).","journal-title":"Mol. Cell. Proteom."},{"key":"880_CR29","unstructured":"Mus musculus (Mouse) (UniProt, 2025); https:\/\/www.uniprot.org\/uniprotkb?dir=ascend&facets=model_organism%3A10090&query=antibody&sort=accession"},{"key":"880_CR30","doi-asserted-by":"publisher","first-page":"D447","DOI":"10.1093\/nar\/gkv1145","volume":"44","author":"JA Vizca\u00edno","year":"2016","unstructured":"Vizca\u00edno, J. A. et al. 2016 Update of the pride database and its related tools. Nucleic Acids Res. 44, D447\u2013D456 (2016).","journal-title":"Nucleic Acids Res."},{"key":"880_CR31","doi-asserted-by":"publisher","unstructured":"Li, K., Shan, B., Xin, L., Li, M. & Wang, L. Datasets and databases for proteoform search from protein database with top-down mass spectra. figshare https:\/\/doi.org\/10.6084\/m9.figshare.29634140.v2 (2025).","DOI":"10.6084\/m9.figshare.29634140.v2"},{"key":"880_CR32","doi-asserted-by":"publisher","unstructured":"Li, K., Shan, B., Xin, L., Li, M. & Wang, L. sTopMG. Zenodo https:\/\/doi.org\/10.5281\/zenodo.16597445 (2025).","DOI":"10.5281\/zenodo.16597445"},{"key":"880_CR33","doi-asserted-by":"publisher","unstructured":"Li, K., Shan, B., Xin, L., Li, M. & Wang, L. TopDown-MaSS-Simulator. Zenodo https:\/\/doi.org\/10.5281\/zenodo.16597493 (2025).","DOI":"10.5281\/zenodo.16597493"}],"container-title":["Nature Computational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00880-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00880-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00880-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T04:02:17Z","timestamp":1763697737000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s43588-025-00880-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"references-count":33,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["880"],"URL":"https:\/\/doi.org\/10.1038\/s43588-025-00880-z","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-5429797\/v1","asserted-by":"object"}]},"ISSN":["2662-8457"],"issn-type":[{"value":"2662-8457","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]},"assertion":[{"value":"11 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}