{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T22:53:58Z","timestamp":1791500038182,"version":"4.3.4"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T00:00:00Z","timestamp":1790899200000},"content-version":"vor","delay-in-days":1,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"publisher","award":["R00 GM147304"],"award-info":[{"award-number":["R00 GM147304"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003130","name":"Fonds Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["FWO G 087625N"],"award-info":[{"award-number":["FWO G 087625N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]},{"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\/100005665","name":"Kinship Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2245300"],"award-info":[{"award-number":["2245300"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["mcponline.org","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Molecular & Cellular Proteomics"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.mcpro.2026.101673","type":"journal-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T23:48:45Z","timestamp":1791416925000},"page":"101673","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pretrained spectrum representations for diverse tandem mass spectrometry proteomics tasks"],"prefix":"10.1016","author":[{"given":"Justin","family":"Sanders","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7473-4785","authenticated-orcid":false,"given":"Melih","family":"Yilmaz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8054-7082","authenticated-orcid":false,"given":"Jacob H.","family":"Russell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3105-1359","authenticated-orcid":false,"given":"Wout","family":"Bittremieux","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William E.","family":"Fondrie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicholas M.","family":"Riley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sewoong","family":"Oh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7283-4715","authenticated-orcid":false,"given":"William S.","family":"Noble","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"7620","key":"10.1016\/j.mcpro.2026.101673_bib1","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1038\/nature19949","article-title":"Mass-spectrometric exploration of proteome structure and function","volume":"537","author":"Aebersold","year":"2016","journal-title":"Nature"},{"issue":"4","key":"10.1016\/j.mcpro.2026.101673_bib2","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1038\/s42256-022-00467-7","article-title":"Ad hoc learning of peptide fragmentation from mass spectra enables an interpretable detection of phosphorylated and cross-linked peptides","volume":"4","author":"Altenburg","year":"2022","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.mcpro.2026.101673_bib3","article-title":"Foundation model enables interpretable open and error-tolerant searching for mass spectrometry-based proteomics","author":"Altenburg","year":"2025","journal-title":"bioRxiv"},{"key":"10.1016\/j.mcpro.2026.101673_bib4","doi-asserted-by":"crossref","DOI":"10.1002\/pmic.202400398","article-title":"Peptide property prediction for mass spectrometry using AI: An introduction to state of the art models","author":"Angelis","year":"2025","journal-title":"Proteomics"},{"issue":"2","key":"10.1016\/j.mcpro.2026.101673_bib5","doi-asserted-by":"crossref","first-page":"271","DOI":"10.3892\/ijmm.2017.3036","article-title":"The crucial role of protein phosphorylation in cell signaling and its use as targeted therapy","volume":"40","author":"Ardito","year":"2017","journal-title":"International Journal of Molecular Medicine"},{"key":"10.1016\/j.mcpro.2026.101673_bib6","doi-asserted-by":"crossref","unstructured":"Gabriel Asher, Jennifer M. Campbell, Jack Geremia, and Timothy Kassis. LSM1-MS2: A Self-Supervised Foundation Model for Tandem Mass Spectrometry Applications, Encompassing Extensive Chemical Property Predictions and Spectral Matching, February 2024.","DOI":"10.26434\/chemrxiv-2024-k06gb-v2"},{"key":"10.1016\/j.mcpro.2026.101673_bib7","article-title":"Large-scale tandem mass spectrum clustering using fast nearest neighbor searching","author":"Bittremieux","year":"2021","journal-title":"Rapid Communications in Mass Spectrometry"},{"key":"10.1016\/j.mcpro.2026.101673_bib8","article-title":"Deep learning methods for de novo peptide sequencing","author":"Bittremieux","year":"2024","journal-title":"Mass Spectrometry Reviews"},{"key":"10.1016\/j.mcpro.2026.101673_bib9","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv preprint arXiv:2108.07258"},{"key":"10.1016\/j.mcpro.2026.101673_bib10","first-page":"1","article-title":"Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS","author":"Bushuiev","year":"2025","journal-title":"Nature Biotechnology"},{"issue":"10","key":"10.1016\/j.mcpro.2026.101673_bib11","doi-asserted-by":"crossref","first-page":"918","DOI":"10.1038\/nbt.2377","article-title":"A cross-platform toolkit for mass spectrometry and proteomics","volume":"30","author":"Chambers","year":"2012","journal-title":"Nature Biotechnology"},{"key":"10.1016\/j.mcpro.2026.101673_bib12","doi-asserted-by":"crossref","unstructured":"T. Chen and C. Guestrin. XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD \u201916, pages 785\u2013794, New York, NY, USA, 2016. ACM.","DOI":"10.1145\/2939672.2939785"},{"issue":"1","key":"10.1016\/j.mcpro.2026.101673_bib13","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1021\/acs.jproteome.7b00563","article-title":"Identifying Tandem Mass Spectra of Phosphorylated Peptides before Database Search","volume":"17","author":"Dorl","year":"2018","journal-title":"Journal of Proteome Research"},{"key":"10.1016\/j.mcpro.2026.101673_bib14","first-page":"1","article-title":"Unifying the analysis of bottom-up proteomics data with CHIMERYS","author":"Frejno","year":"2025","journal-title":"Nature Methods"},{"issue":"6","key":"10.1016\/j.mcpro.2026.101673_bib15","doi-asserted-by":"crossref","first-page":"1568","DOI":"10.1093\/bioinformatics\/btab874","article-title":"SPEQ: quality assessment of peptide tandem mass spectra with deep learning","volume":"38","author":"Gholamizoj","year":"2022","journal-title":"Bioinformatics"},{"issue":"1","key":"10.1016\/j.mcpro.2026.101673_bib16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41392-024-01886-1","article-title":"Glycosylation: mechanisms, biological functions and clinical implications","volume":"9","author":"He","year":"2024","journal-title":"Signal Transduction and Targeted Therapy"},{"key":"10.1016\/j.mcpro.2026.101673_bib17","unstructured":"David Healey, Daniel Domingo-Fern\u00e1ndez, J Taylor, Christoph Krettler, Rose Lightheart, Tyson Park, Tobias Kind, August Allen, and Viswa Colluru. PRISM: A foundation model for life\u2019s chemistry."},{"key":"10.1016\/j.mcpro.2026.101673_bib18","unstructured":"D. Kingma and J. Ba. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations, 2015."},{"key":"10.1016\/j.mcpro.2026.101673_bib19","doi-asserted-by":"crossref","unstructured":"Kathryn Kothlow, Haley M. Schramm, Kayla A. Markuson, Jacob H. Russell, Emmajay Sutherland, Tim S. Veth, Ruby Zhang, Anna G. Duboff, Vishnu R. Tejus, Leah E. McDermott, Laura S. Dr\u00e4ger, and Nicholas M. Riley. Extracting informative glycan-specific ions from glycopeptide MS\/MS spectra with GlyCounter, March 2025. Pages: 2025.03.24.645139 Section: New Results.","DOI":"10.1101\/2025.03.24.645139"},{"issue":"23-24","key":"10.1016\/j.mcpro.2026.101673_bib20","doi-asserted-by":"crossref","DOI":"10.1002\/pmic.202200156","article-title":"Recent advances in demystifying O-glycosylation in health and disease","volume":"22","author":"Li","year":"2022","journal-title":"Proteomics"},{"issue":"9","key":"10.1016\/j.mcpro.2026.101673_bib21","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1080\/14789450.2021.1994390","article-title":"Strategies for Mass Spectrometry-based Phosphoproteomics using Isobaric Tagging","volume":"18","author":"Liu","year":"2021","journal-title":"Expert review of proteomics"},{"issue":"1","key":"10.1016\/j.mcpro.2026.101673_bib22","doi-asserted-by":"crossref","first-page":"3530","DOI":"10.1038\/s41467-025-58866-4","article-title":"DIA-BERT: pre-trained end-to-end transformer models for enhanced DIA proteomics data analysis","volume":"16","author":"Liu","year":"2025","journal-title":"Nature Communications"},{"issue":"8","key":"10.1016\/j.mcpro.2026.101673_bib23","doi-asserted-by":"crossref","first-page":"3628","DOI":"10.1021\/pr8001194","article-title":"Colander: a probability-based support vector machine algorithm for automatic screening for CID spectra of phosphopeptides prior to database search","volume":"7","author":"Lu","year":"2008","journal-title":"Journal of Proteome Research"},{"issue":"7","key":"10.1016\/j.mcpro.2026.101673_bib24","doi-asserted-by":"crossref","first-page":"2896","DOI":"10.1021\/pr200118r","article-title":"ScanRanker: Quality assessment of tandem mass spectra via sequence tagging","volume":"10","author":"Ma","year":"2011","journal-title":"Journal of Proteome Research"},{"issue":"3","key":"10.1016\/j.mcpro.2026.101673_bib25","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1038\/s41592-023-01802-5","article-title":"Sampling the proteome by emerging single-molecule and mass spectrometry methods","volume":"20","author":"MacCoss","year":"2023","journal-title":"Nature methods"},{"issue":"1","key":"10.1016\/j.mcpro.2026.101673_bib26","doi-asserted-by":"crossref","DOI":"10.1074\/mcp.R110.000133","article-title":"mzML\u2013a community standard for mass spectrometry data","volume":"10","author":"Martens","year":"2011","journal-title":"Mol Cell Proteomics"},{"issue":"3","key":"10.1016\/j.mcpro.2026.101673_bib27","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1038\/s41587-019-0344-3","article-title":"The functional landscape of the human phosphoproteome","volume":"38","author":"Ochoa","year":"2020","journal-title":"Nature Biotechnology"},{"issue":"5","key":"10.1016\/j.mcpro.2026.101673_bib28","doi-asserted-by":"crossref","DOI":"10.1016\/j.mcpro.2023.100538","article-title":"MSFragger-Labile: A flexible method to improve labile PTM analysis in proteomics","volume":"22","author":"Polasky","year":"2023","journal-title":"Molecular & Cellular Proteomics"},{"key":"10.1016\/j.mcpro.2026.101673_bib29","doi-asserted-by":"crossref","unstructured":"Cl\u00e9ment M. Potel, Mira Lea Burtscher, Martin Garrido-Rodriguez, Amber Brauer-Nikonow, Isabelle Becher, Cecile Le Sueur, Athanasios Typas, Michael Zimmermann, and Mikhail M. Savitski. Uncovering protein glycosylation dynamics and heterogeneity using deep quantitative glycoprofiling (DQGlyco). Nature Structural & Molecular Biology, pages 1\u201316, February 2025. Publisher: Nature Publishing Group.","DOI":"10.1038\/s41594-025-01485-w"},{"issue":"3","key":"10.1016\/j.mcpro.2026.101673_bib30","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1089\/omi.2004.8.255","article-title":"Spectral quality assessment for high-throughput tandem mass spectrometry proteomics","volume":"8","author":"Purvine","year":"2004","journal-title":"Omics: a journal of integrative biology"},{"key":"10.1016\/j.mcpro.2026.101673_bib31","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning, pages 8748\u20138763. PMLR, 2021."},{"key":"10.1016\/j.mcpro.2026.101673_bib32","unstructured":"Alec Radford, Karthik Narasimhan, Tim Salimans, Ilya Sutskever, et al. Improving language understanding by generative pre-training, 2018."},{"issue":"8","key":"10.1016\/j.mcpro.2026.101673_bib33","doi-asserted-by":"crossref","first-page":"3286","DOI":"10.1021\/acs.jproteome.0c00218","article-title":"Optimal Dissociation Methods Differ for N- and O-Glycopeptides","volume":"19","author":"Riley","year":"2020","journal-title":"Journal of Proteome Research"},{"issue":"1","key":"10.1016\/j.mcpro.2026.101673_bib34","first-page":"560391","article-title":"Increasing the productivity of glycopeptides analysis by using higher-energy collision dissociation-accurate mass-product-dependent electron transfer dissociation","author":"Saba","year":"2012","journal-title":"International Journal of Proteomics"},{"issue":"4","key":"10.1016\/j.mcpro.2026.101673_bib35","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1093\/bioinformatics\/bti829","article-title":"Quality classification of tandem mass spectrometry data","volume":"22","author":"Salmi","year":"2006","journal-title":"Bioinformatics"},{"issue":"5","key":"10.1016\/j.mcpro.2026.101673_bib36","doi-asserted-by":"crossref","first-page":"576","DOI":"10.1016\/j.sbi.2011.08.005","article-title":"Mechanisms and principles of N-linked protein glycosylation","volume":"21","author":"Schwarz","year":"2011","journal-title":"Current Opinion in Structural Biology"},{"issue":"9","key":"10.1016\/j.mcpro.2026.101673_bib37","doi-asserted-by":"crossref","first-page":"4517","DOI":"10.1021\/pr300257c","article-title":"Higher Energy Collision Dissociation (HCD) Product Ion-Triggered Electron Transfer Dissociation (ETD) Mass Spectrometry for the Analysis of N-Linked Glycoproteins","volume":"11","author":"Singh","year":"2012","journal-title":"Journal of Proteome Research"},{"key":"10.1016\/j.mcpro.2026.101673_bib38","article-title":"Improvements to Casanovo, a deep learning de novo peptide sequencer","author":"Straub","year":"2025","journal-title":"bioRxiv"},{"issue":"12","key":"10.1016\/j.mcpro.2026.101673_bib39","doi-asserted-by":"crossref","first-page":"5606","DOI":"10.1021\/acs.jproteome.4c00723","article-title":"Autonomous Dissociation-type Selection for Glycoproteomics Using a Real-Time Library Search","volume":"23","author":"Sutherland","year":"2024","journal-title":"Journal of Proteome Research"},{"key":"10.1016\/j.mcpro.2026.101673_bib40","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"24","key":"10.1016\/j.mcpro.2026.101673_bib41","doi-asserted-by":"crossref","first-page":"7183","DOI":"10.1111\/febs.16148","article-title":"Global functions of O-glycosylation: promises and challenges in O-glycobiology","volume":"288","author":"Wandall","year":"2021","journal-title":"The FEBS Journal"},{"key":"10.1016\/j.mcpro.2026.101673_bib42","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1016\/j.cels.2018.08.004","article-title":"Assembling the community-scale discoverable human proteome","volume":"7","author":"Wang","year":"2018","journal-title":"Cell Systems"},{"issue":"1","key":"10.1016\/j.mcpro.2026.101673_bib43","doi-asserted-by":"crossref","first-page":"9815","DOI":"10.1038\/s41467-025-64928-4","article-title":"Carafe enables high quality in silico spectral library generation for data-independent acquisition proteomics","volume":"16","author":"Wen","year":"2025","journal-title":"Nature Communications"},{"issue":"6","key":"10.1016\/j.mcpro.2026.101673_bib44","first-page":"1","article-title":"Quality assessment of peptide tandem mass spectra","volume":"9","author":"Wu","year":"2008","journal-title":"BMC Bioinformatics"},{"issue":"11","key":"10.1016\/j.mcpro.2026.101673_bib45","doi-asserted-by":"crossref","first-page":"5478","DOI":"10.1021\/ac500945m","article-title":"Novel LC-MS2 Product Dependent Parallel Data Acquisition Function and Data Analysis Workflow for Sequencing and Identification of Intact Glycopeptides","volume":"86","author":"Wu","year":"2014","journal-title":"Analytical Chemistry"},{"issue":"1","key":"10.1016\/j.mcpro.2026.101673_bib46","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1021\/jasms.5c00168","article-title":"SpecQuality: A tool for reliable spectral quality assessment in proteomics and proteogenomics","volume":"37","author":"Yadav","year":"2026","journal-title":"Journal of the American Society for Mass Spectrometry"},{"issue":"1","key":"10.1016\/j.mcpro.2026.101673_bib47","doi-asserted-by":"crossref","first-page":"6427","DOI":"10.1038\/s41467-024-49731-x","article-title":"Sequence-to-sequence translation from mass spectra to peptides with a transformer model","volume":"15","author":"Yilmaz","year":"2024","journal-title":"Nature Communications"},{"key":"10.1016\/j.mcpro.2026.101673_bib48","doi-asserted-by":"crossref","unstructured":"M. Yilmaz, W. E. Fondrie, W. Bittremieux, S. Oh, and W. S. Noble. De novo mass spectrometry peptide sequencing with a transformer model. In Proceedings of the International Conference on Machine Learning, pages 25514\u201325522, 2022.","DOI":"10.1101\/2022.02.07.479481"},{"issue":"1","key":"10.1016\/j.mcpro.2026.101673_bib49","doi-asserted-by":"crossref","first-page":"3329","DOI":"10.1038\/s41467-025-58728-z","article-title":"MSFragger-DDA+ enhances peptide identification sensitivity with full isolation window search","volume":"16","author":"Yu","year":"2025","journal-title":"Nature Communications"},{"issue":"9","key":"10.1016\/j.mcpro.2026.101673_bib50","doi-asserted-by":"crossref","first-page":"4088","DOI":"10.1021\/pr2002726","article-title":"Combining High-Energy C-Trap Dissociation and Electron Transfer Dissociation for Protein O-GlcNAc Modification Site Assignment","volume":"10","author":"Peng","year":"2011","journal-title":"Journal of Proteome Research"}],"container-title":["Molecular & Cellular Proteomics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1535947626001696?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1535947626001696?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T22:40:22Z","timestamp":1791499222000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1535947626001696"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":50,"alternative-id":["S1535947626001696"],"URL":"https:\/\/doi.org\/10.1016\/j.mcpro.2026.101673","relation":{},"ISSN":["1535-9476"],"issn-type":[{"value":"1535-9476","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Pretrained spectrum representations for diverse tandem mass spectrometry proteomics tasks","name":"articletitle","label":"Article Title"},{"value":"Molecular & Cellular Proteomics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.mcpro.2026.101673","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 THE AUTHORS. Published by Elsevier Inc on behalf of American Society for Biochemistry and Molecular Biology.","name":"copyright","label":"Copyright"}],"article-number":"101673"}}