{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T08:07:15Z","timestamp":1793347635154,"version":"4.5.0"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1014822","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000}}],"reference-count":35,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T00:00:00Z","timestamp":1791244800000},"content-version":"vor","delay-in-days":0,"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":["R35GM142502"],"award-info":[{"award-number":["R35GM142502"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>The biomedical literature contains a vast collection of omics studies, yet most published data remain functionally inaccessible for computational reuse. When raw data are deposited in public repositories, essential information for reproducing reported results is dispersed across main text, supplementary files, and code repositories, and in the rarer cases where intermediate data (e.g., protein abundance files) are shared, their location is irregular. Here we present an agentic framework for the agent-supported retrieval, reanalysis, and synthesis of published omics data. The system employs large language model (LLM) agents with access to tools for fetching omics studies, extracting article metadata, identifying and downloading published data, executing containerized quantification pipelines, and synthesizing results across studies. Applied at corpus scale, the pipeline catalogued dataset references across thousands of PubMed Central articles; we report these as descriptive system outputs rather than as a validated measure of extraction accuracy. Using model context protocol (MCP) servers to expose containerized analysis tools, the agents retrieved and re-quantified data in five end-to-end reanalyses spanning data-dependent and data-independent proteomics and bulk RNA-seq. All five reanalyses completed, each with documented human guidance and workflow accommodations, and reproduced the authors\u2019 deposited abundances with high per-sample correlation (0.85\u20130.997) and strongly concordant differentially expressed features (fold-change Spearman 0.88\u20130.91), with no direction reversals among features called differentially expressed in both analyses; residual differences in significant-feature lists were attributable to threshold placement, tool-version, and preprocessing differences rather than to the underlying quantities. We further demonstrate that agents can identify semantically similar studies, judge data compatibility, and synthesize findings across studies, including a random-effects meta-analysis that recovered consistent protein regulation in liver fibrosis. Rather than a validated benchmark of literature-wide performance, this work is a feasibility demonstration together with an auditable, reusable toolset, establishing a foundation for prospective evaluation of automated omics-data reuse.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1014822","type":"journal-article","created":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T17:44:48Z","timestamp":1791308688000},"page":"e1014822","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Omics data discovery agents: Agent-supported retrieval, reanalysis, and synthesis of published omics data"],"prefix":"10.1371","volume":"22","author":[{"given":"Alexandre","family":"Hutton","sequence":"first","affiliation":[{"name":"Cedars-Sinai Medical Center","place":["Los Angeles, California, United States of America"],"department":["Department of Computational Biomedicine"]},{"name":"Advanced Clinical Biosystems Research Institute, Cedars-Sinai Medical Center","place":["Los Angeles, California, United States of America"]},{"name":"Board of Governors Innovation Center, Cedars-Sinai Medical Center","place":["Los Angeles, California, United States of America"]},{"name":"Smidt Heart Institute, Cedars-Sinai Medical Center","place":["Los Angeles, California, United States of America"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2753-3926","authenticated-orcid":true,"given":"Jesse G.","family":"Meyer","sequence":"additional","affiliation":[{"name":"Cedars-Sinai Medical Center","place":["Los Angeles, California, United States of America"],"department":["Department of Computational Biomedicine"]},{"name":"Advanced Clinical Biosystems Research Institute, Cedars-Sinai Medical Center","place":["Los Angeles, California, United States of America"]},{"name":"Board of Governors Innovation Center, Cedars-Sinai Medical Center","place":["Los Angeles, California, United States of America"]},{"name":"Smidt Heart Institute, Cedars-Sinai Medical Center","place":["Los Angeles, California, United States of America"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,6]]},"reference":[{"key":"pcbi.1014822.ref001","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkae1011","article-title":"The PRIDE database at 20 years: 2025 Update","volume":"53","author":"Y Perez-Riverol","year":"2025","journal-title":"Nucleic Acids Res"},{"issue":"4","key":"pcbi.1014822.ref002","article-title":"Assembling the community-scale discoverable human proteome","volume":"7","author":"M Wang","year":"2018","journal-title":"Cell Syst"},{"issue":"1","key":"pcbi.1014822.ref003","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1093\/nar\/30.1.207","article-title":"Gene Expression Omnibus: NCBI gene expression and hybridization array data repository","volume":"30","author":"R Edgar","year":"2002","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1014822.ref004","article-title":"NCBI GEO: Archive for functional genomics data sets--update","volume":"41","author":"T Barrett","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1014822.ref005","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkab1053","article-title":"The Sequence Read Archive: A decade more of explosive growth","volume":"50","author":"K Katz","year":"2022","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"pcbi.1014822.ref006","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.cub.2013.11.014","article-title":"The availability of research data declines rapidly with article age","volume":"24","author":"TH Vines","year":"2014","journal-title":"Curr Biol"},{"key":"pcbi.1014822.ref007","unstructured":"ScienceMachine. ScienceMachine | analyze scientific data 100x faster with AI. Undated Web Resource; n.d. [cited 2026 Mar 2]. Available from: https:\/\/sciencemachine.ai"},{"key":"pcbi.1014822.ref008","unstructured":"Mitchener L, Yiu A, Chang B, Bourdenx M, Nadolski T, Sulovari A, et al. Kosmos: An AI scientist for autonomous discovery. 2025. https:\/\/arxiv.org\/abs\/2511.02824"},{"issue":"7","key":"pcbi.1014822.ref009","doi-asserted-by":"crossref","first-page":"3580","DOI":"10.1109\/TKDE.2024.3352100","article-title":"Unifying large language models and knowledge graphs: A roadmap","volume":"36","author":"S Pan","year":"2024","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"pcbi.1014822.ref010","article-title":"Biomni: A general-purpose biomedical AI agent","author":"K Huang","year":"2025","journal-title":"bioRxiv"},{"key":"pcbi.1014822.ref011","unstructured":"Ollama. Ollama; n.d. Available from: https:\/\/ollama.com"},{"issue":"1","key":"pcbi.1014822.ref012","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1038\/s41592-019-0638-x","article-title":"DIA-NN: Neural networks and interference correction enable deep proteome coverage in high throughput","volume":"17","author":"V Demichev","year":"2020","journal-title":"Nat Methods"},{"issue":"12","key":"pcbi.1014822.ref013","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":"Nat Protoc"},{"key":"pcbi.1014822.ref014","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkae1010","article-title":"UniProt: The universal protein knowledgebase in 2025","volume":"53","author":"The UniProt Consortium","year":"2025","journal-title":"Nucleic Acids Res"},{"issue":"4","key":"pcbi.1014822.ref015","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1038\/nmeth.4197","article-title":"Salmon provides fast and bias-aware quantification of transcript expression","volume":"14","author":"R Patro","year":"2017","journal-title":"Nat Methods"},{"issue":"6","key":"pcbi.1014822.ref016","doi-asserted-by":"crossref","first-page":"100991","DOI":"10.1016\/j.mcpro.2025.100991","article-title":"Proteomics and phosphoproteomics revealed dysregulated kinases and potential therapy for liver fibrosis","volume":"24","author":"X Cheng","year":"2025","journal-title":"Mol Cell Proteom"},{"issue":"3","key":"pcbi.1014822.ref017","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1038\/nbt.2839","article-title":"ProteomeXchange provides globally coordinated proteomics data submission and dissemination","volume":"32","author":"JA Vizca\u00edno","year":"2014","journal-title":"Nat Biotechnol"},{"key":"pcbi.1014822.ref018","article-title":"iProX: An integrated proteome resource","volume":"47","author":"J Ma","year":"2019","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"pcbi.1014822.ref019","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1021\/acs.jproteome.5c00889","article-title":"Impact of PPP1R1A knockdown on the proteomic landscape of INS-1 cells: A focus on significant modulated pathways","volume":"25","author":"J Taneera","year":"2026","journal-title":"J Proteome Res"},{"issue":"12","key":"pcbi.1014822.ref020","doi-asserted-by":"crossref","first-page":"101462","DOI":"10.1016\/j.mcpro.2025.101462","article-title":"Quantitative proteomics identifies potential molecular adaptations in mouse models of congenital stationary night blindness type 2","volume":"24","author":"M Ganglberger","year":"2025","journal-title":"Mol Cell Proteom"},{"issue":"10","key":"pcbi.1014822.ref021","article-title":"Seizure evolution in a mouse model of West syndrome involves complex and time-dependent synapse remodeling, gliosis and alterations in lipid metabolism","volume":"23","author":"R Ma","year":"2025","journal-title":"PLoS Biol"},{"issue":"9","key":"pcbi.1014822.ref022","doi-asserted-by":"crossref","first-page":"4033","DOI":"10.7150\/thno.109771","article-title":"Hepatic stellate cell-derived microfibrillar-associated protein 2 prevents liver fibrosis by regulating extracellular matrix and inflammation","volume":"15","author":"W Zhang","year":"2025","journal-title":"Theranostics"},{"key":"pcbi.1014822.ref023","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.98023","article-title":"Dynamics of compartment-specific proteomic landscapes of hepatotoxic and cholestatic models of liver fibrosis","volume":"13","author":"M Jirouskova","year":"2025","journal-title":"eLife"},{"issue":"1","key":"pcbi.1014822.ref024","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1002\/pmic.70090","article-title":"A proteomics resource investigating fibrosis: Proof-of-concept for identifying novel drug candidates","volume":"26","author":"H Devos","year":"2026","journal-title":"Proteomics"},{"issue":"11","key":"pcbi.1014822.ref025","doi-asserted-by":"crossref","first-page":"1442","DOI":"10.3390\/cells8111442","article-title":"Clusterin attenuates hepatic fibrosis by inhibiting hepatic stellate cell activation and downregulating the Smad3 signaling pathway","volume":"8","author":"H-Y Seo","year":"2019","journal-title":"Cells"},{"issue":"3","key":"pcbi.1014822.ref026","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1053\/j.gastro.2025.08.022","article-title":"Clusterin drives fiber endocytosis by mesothelial cells to resolve liver fibrosis","volume":"170","author":"M Wang","year":"2026","journal-title":"Gastroenterology"},{"issue":"13","key":"pcbi.1014822.ref027","doi-asserted-by":"crossref","first-page":"10969","DOI":"10.3390\/ijms241310969","article-title":"Association of differentially altered liver fibrosis with deposition of TGFBi in stabilin-deficient mice","volume":"24","author":"J Krzistetzko","year":"2023","journal-title":"Int J Mol Sci"},{"issue":"1","key":"pcbi.1014822.ref028","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1038\/s42003-026-09601-2","article-title":"TGFBI promotes liver fibrosis through remodeling the profibrotic microenvironment by a positive feedback regulatory loop","volume":"9","author":"H Wu","year":"2026","journal-title":"Commun Biol"},{"issue":"1","key":"pcbi.1014822.ref029","doi-asserted-by":"crossref","first-page":"16749","DOI":"10.1038\/s41598-018-35194-w","article-title":"Hepatokine \u03b11-microglobulin signaling exacerbates inflammation and disturbs fibrotic repair in mouse myocardial infarction","volume":"8","author":"D Hakuno","year":"2018","journal-title":"Sci Rep"},{"issue":"1","key":"pcbi.1014822.ref030","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.jhep.2010.06.020","article-title":"Distinct roles for non-muscle myosin II isoforms in mouse hepatic stellate cells","volume":"54","author":"Z Liu","year":"2011","journal-title":"J Hepatol"},{"key":"pcbi.1014822.ref031","doi-asserted-by":"crossref","first-page":"150785","DOI":"10.1016\/j.bbrc.2024.150785","article-title":"Elevated PRELP expression in heart and liver fibrosis promotes collagen production","volume":"734","author":"Y Yamauchi","year":"2024","journal-title":"Biochem Biophys Res Commun"},{"issue":"12","key":"pcbi.1014822.ref032","doi-asserted-by":"crossref","first-page":"1712","DOI":"10.1038\/labinvest.2012.121","article-title":"Lumican, an extracellular matrix proteoglycan, is a novel requisite for hepatic fibrosis","volume":"92","author":"A Krishnan","year":"2012","journal-title":"Lab Invest"},{"issue":"13","key":"pcbi.1014822.ref033","doi-asserted-by":"crossref","first-page":"3603","DOI":"10.1111\/febs.16039","article-title":"Collagen VI as a driver and disease biomarker in human fibrosis","volume":"289","author":"L Williams","year":"2022","journal-title":"FEBS J"},{"issue":"10","key":"pcbi.1014822.ref034","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0140418","article-title":"Microfibrillar-associated protein 4: A potential biomarker for screening for liver fibrosis in a mixed patient cohort","volume":"10","author":"SG S\u00e6kmose","year":"2015","journal-title":"PLoS ONE"},{"issue":"6","key":"pcbi.1014822.ref035","article-title":"Extracellular matrix dynamics in hepatocarcinogenesis: A comparative proteomics study of PDGFC transgenic and Pten null mouse models","volume":"7","author":"KKY Lai","year":"2011","journal-title":"PLoS Genet"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1014822","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T18:07:39Z","timestamp":1791569259000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014822"}},"subtitle":[],"editor":[{"given":"Marc R","family":"Birtwistle","sequence":"first","affiliation":[{"name":"Clemson University","place":["UNITED STATES OF AMERICA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,6]]},"references-count":35,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,6]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1014822","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,6]]}}}