{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T13:59:45Z","timestamp":1788357585162,"version":"build-2803163510"},"posted":{"date-parts":[[2026,3,18]]},"group-title":"Health Informatics","reference-count":39,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,3,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Advances in medicine depend on analyzing large and complex data sources, but discovery is partly constrained by the limited time and domain expertise of human researchers. Agentic artificial intelligence (agentic AI) can accelerate discovery by automating components of the scientific workflow, including information retrieval, data analysis, and knowledge synthesis.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Aim<\/jats:title>\n                  <jats:p>OpenScientist, an open-source agentic AI co-scientist, aims to accelerate biomedical discovery by semi-autonomously investigating scientist-defined queries and generating clinically relevant, verifiable scientific insights.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>Domain experts evaluated OpenScientist for novel discoveries in four clinical case studies: (1) a prespecified analysis in a community-based Alzheimer\u2019s disease biomarker cohort, (2) unsupervised modeling for plasma proteomic survival prediction, (3) hypothesis investigation in single-cell transcriptomic data from neurons with neurofibrillary tangles, and (4) hypothesis generation with validation in a multiple myeloma dataset with a randomized negative control.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>OpenScientist completed analyses in minutes that otherwise would take weeks to months of human time and expertise. It identified %ptau217 as the best predictor of amyloid PET status, generated a plasma proteomic survival model with performance comparable to published models, proposed a mechanism linking tau pathology to altered lysosomal acidification, and generated multiple myeloma hypotheses that were validated in an external cohort while distinguishing true signal from randomized controls.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>OpenScientist demonstrates that open, auditable, agentic AI can support real-world clinical research by generating hypotheses, executing analyses, and discovering insights from complex datasets.<\/jats:p>\n                <\/jats:sec>","DOI":"10.64898\/2026.03.15.26348338","type":"posted-content","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T23:40:18Z","timestamp":1773877218000},"source":"Crossref","is-referenced-by-count":3,"title":["OpenScientist: evaluating an open agentic AI co-scientist to accelerate biomedical discovery"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6483-9153","authenticated-orcid":false,"given":"Kaleigh F.","family":"Roberts","sequence":"first","affiliation":[{"name":"Department of Pathology & Immunology, Washington University in St. Louis, St. Louis, MO, USA"},{"name":"Tracy Family SILQ Center, Washington University in St. Louis, MO, USA"},{"name":"Consortium for Biomedical Research & AI in Neurodegeneration (C-BRAIN)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5219-9996","authenticated-orcid":false,"given":"Zachary B.","family":"Abrams","sequence":"additional","affiliation":[{"name":"Institute for Informatics, Data Science, and Biostatistics, Washington University in St. Louis, St. Louis, MO, USA"},{"name":"Consortium for Biomedical Research & AI in Neurodegeneration (C-BRAIN)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Cappelletti","sequence":"additional","affiliation":[{"name":"Department of Biology, University of Fribourg, Fribourg, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahdi","family":"Moqri","sequence":"additional","affiliation":[{"name":"Department of Medicine, Harvard Medical School, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicholas","family":"Heugel","sequence":"additional","affiliation":[{"name":"Tracy Family SILQ Center, Washington University in St. Louis, MO, USA"},{"name":"Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA"},{"name":"Consortium for Biomedical Research & AI in Neurodegeneration (C-BRAIN)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J. Harry","family":"Caufield","sequence":"additional","affiliation":[{"name":"Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathieu","family":"Bourdenx","sequence":"additional","affiliation":[{"name":"UK Dementia Research Institute at University College London, London, UK"},{"name":"Consortium for Biomedical Research & AI in Neurodegeneration (C-BRAIN)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jineta","family":"Banerjee","sequence":"additional","affiliation":[{"name":"Sage Bionetworks, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Foschini","sequence":"additional","affiliation":[{"name":"Sage Bionetworks, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diego","family":"Galeano","sequence":"additional","affiliation":[{"name":"Electronics and Mechatronics Department, Facultad de Ingenieria, Universidad Nacional de Asuncion, Paraguay"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nomi L.","family":"Harris","sequence":"additional","affiliation":[{"name":"Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melody","family":"Li","sequence":"additional","affiliation":[{"name":"Tracy Family SILQ Center, Washington University in St. Louis, MO, USA"},{"name":"Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kejun","family":"Ying","sequence":"additional","affiliation":[{"name":"Department of Neurology and Neurological Sciences, Stanford University, Stanford, CA, USA"},{"name":"Institute for Protein Design, University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justin A.","family":"Melendez","sequence":"additional","affiliation":[{"name":"Tracy Family SILQ Center, Washington University in St. Louis, MO, USA"},{"name":"Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA"},{"name":"Consortium for Biomedical Research & AI in Neurodegeneration (C-BRAIN)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas R.","family":"Barth\u00e9lemy","sequence":"additional","affiliation":[{"name":"Tracy Family SILQ Center, Washington University in St. Louis, MO, USA"},{"name":"Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James G.","family":"Bollinger","sequence":"additional","affiliation":[{"name":"Tracy Family SILQ Center, Washington University in St. Louis, MO, USA"},{"name":"Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingxin","family":"He","sequence":"additional","affiliation":[{"name":"Tracy Family SILQ Center, Washington University in St. Louis, MO, USA"},{"name":"Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vitaliy","family":"Ovod","sequence":"additional","affiliation":[{"name":"Tracy Family SILQ Center, Washington University in St. Louis, MO, USA"},{"name":"Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tammie L. S.","family":"Benzinger","sequence":"additional","affiliation":[{"name":"Department of Radiology, Washington University in St. Louis, St. Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaney","family":"Flores","sequence":"additional","affiliation":[{"name":"Department of Radiology, Washington University in St. Louis, St. Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian A.","family":"Gordon","sequence":"additional","affiliation":[{"name":"Department of Radiology, Washington University in St. Louis, St. Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adegoke A.","family":"Ojewole","sequence":"additional","affiliation":[{"name":"Consortium for Biomedical Research & AI in Neurodegeneration (C-BRAIN)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2126-3723","authenticated-orcid":false,"given":"Mukta","family":"Phatak","sequence":"additional","affiliation":[{"name":"The 10,000 Brains Project, Oakland, CA, USA"},{"name":"Consortium for Biomedical Research & AI in Neurodegeneration (C-BRAIN)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6480-9536","authenticated-orcid":false,"given":"Donald L.","family":"Elbert","sequence":"additional","affiliation":[{"name":"Department of Neurology, University of Washington, Seattle, WA, USA"},{"name":"Consortium for Biomedical Research & AI in Neurodegeneration (C-BRAIN)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah","family":"Biber","sequence":"additional","affiliation":[{"name":"Institute for Informatics, Data Science, and Biostatistics, Washington University in St. Louis, St. Louis, MO, USA"},{"name":"Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA"},{"name":"Consortium for Biomedical Research & AI in Neurodegeneration (C-BRAIN)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric C.","family":"Landsness","sequence":"additional","affiliation":[{"name":"Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA"},{"name":"Consortium for Biomedical Research & AI in Neurodegeneration (C-BRAIN)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher J.","family":"Mungall","sequence":"additional","affiliation":[{"name":"Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7729-1702","authenticated-orcid":false,"given":"Randall J.","family":"Bateman","sequence":"additional","affiliation":[{"name":"Tracy Family SILQ Center, Washington University in St. Louis, MO, USA"},{"name":"Department of Neurology, Washington University in St. Louis, St. Louis, MO, USA"},{"name":"Consortium for Biomedical Research & AI in Neurodegeneration (C-BRAIN)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2170-2250","authenticated-orcid":false,"given":"Justin T.","family":"Reese","sequence":"additional","affiliation":[{"name":"Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"},{"name":"Consortium for Biomedical Research & AI in Neurodegeneration (C-BRAIN)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026032004150975000_2026.03.15.26348338v1.1","doi-asserted-by":"publisher","DOI":"10.1126\/science.adi2336"},{"key":"2026032004150975000_2026.03.15.26348338v1.2","doi-asserted-by":"publisher","DOI":"10.1038\/S41586-021-03819-2"},{"key":"2026032004150975000_2026.03.15.26348338v1.3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.18864"},{"key":"2026032004150975000_2026.03.15.26348338v1.4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2408.06292"},{"key":"2026032004150975000_2026.03.15.26348338v1.5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2511.02824"},{"key":"2026032004150975000_2026.03.15.26348338v1.6","doi-asserted-by":"publisher","DOI":"10.1101\/2025.05.30.656746"},{"key":"2026032004150975000_2026.03.15.26348338v1.7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2508.07043"},{"key":"2026032004150975000_2026.03.15.26348338v1.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2024.09.022"},{"key":"2026032004150975000_2026.03.15.26348338v1.9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2508.14111"},{"key":"2026032004150975000_2026.03.15.26348338v1.10","doi-asserted-by":"crossref","first-page":"100398","DOI":"10.1016\/j.tjpad.2025.100398","article-title":"Towards an AI biomedical scientist: Accelerating discoveries in neurodegenerative disease","volume":"13","year":"2026","journal-title":"The Journal of Prevention of Alzheimer\u2019s Disease"},{"key":"2026032004150975000_2026.03.15.26348338v1.11","unstructured":"Anthropic. Claude Code."},{"key":"2026032004150975000_2026.03.15.26348338v1.12","doi-asserted-by":"crossref","first-page":"e073358","DOI":"10.1002\/alz.073358","article-title":"An Alzheimer\u2019s disease blood test study in a diverse community-based population: Preliminary results from SEABIRD","volume":"19","year":"2023","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026032004150975000_2026.03.15.26348338v1.13","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000008081"},{"key":"2026032004150975000_2026.03.15.26348338v1.14","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02869-z"},{"key":"2026032004150975000_2026.03.15.26348338v1.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2014.07.003"},{"key":"2026032004150975000_2026.03.15.26348338v1.16","doi-asserted-by":"crossref","unstructured":"Bateman, R. et al. Alzheimer\u2019s disease blood tests of amyloid-beta 42\/40, %p-tau217, 181, and 205 ratios and MTBR-243 in real-world populations: Results from SEABIRD and BioFINDER2. Alzheimer\u2019s & Dementia 20, (2025).","DOI":"10.1002\/alz.088405"},{"key":"2026032004150975000_2026.03.15.26348338v1.17","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-7962593\/v1"},{"key":"2026032004150975000_2026.03.15.26348338v1.18","doi-asserted-by":"publisher","DOI":"10.1101\/2024.10.29.620782"},{"key":"2026032004150975000_2026.03.15.26348338v1.19","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1186\/s12916-022-02425-x","article-title":"Plasma neurofilament light and its association with all-cause mortality risk among urban middle-aged men and women","volume":"20","year":"2022","journal-title":"BMC Med"},{"key":"2026032004150975000_2026.03.15.26348338v1.20","doi-asserted-by":"crossref","first-page":"107348","DOI":"10.1016\/j.phrs.2024.107348","article-title":"CX3C chemokine: Hallmarks of fibrosis and ageing","volume":"208","year":"2024","journal-title":"Pharmacological Research"},{"key":"2026032004150975000_2026.03.15.26348338v1.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2023.08.003"},{"key":"2026032004150975000_2026.03.15.26348338v1.22","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1038\/s43587-025-00987-y","article-title":"A unified framework for systematic curation and evaluation of aging biomarkers","volume":"5","year":"2025","journal-title":"Nat Aging"},{"key":"2026032004150975000_2026.03.15.26348338v1.23","doi-asserted-by":"publisher","DOI":"10.18632\/aging.101684"},{"key":"2026032004150975000_2026.03.15.26348338v1.24","doi-asserted-by":"publisher","DOI":"10.18632\/aging.204434"},{"key":"2026032004150975000_2026.03.15.26348338v1.25","doi-asserted-by":"publisher","DOI":"10.18632\/AGING.101414"},{"key":"2026032004150975000_2026.03.15.26348338v1.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.molcel.2012.10.016"},{"key":"2026032004150975000_2026.03.15.26348338v1.27","doi-asserted-by":"publisher","DOI":"10.1186\/gb-2013-14-10-r115"},{"key":"2026032004150975000_2026.03.15.26348338v1.28","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.73420"},{"key":"2026032004150975000_2026.03.15.26348338v1.29","doi-asserted-by":"publisher","DOI":"10.1212\/wnl.0000000000200898"},{"key":"2026032004150975000_2026.03.15.26348338v1.30","doi-asserted-by":"publisher","DOI":"10.1186\/s13073-019-0667-1"},{"key":"2026032004150975000_2026.03.15.26348338v1.31","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1820843116"},{"key":"2026032004150975000_2026.03.15.26348338v1.32","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1038\/s43587-023-00557-0","article-title":"Causality-Enriched Epigenetic Age Uncouples Damage and Adaptation","volume":"4","year":"2024","journal-title":"Nat Aging"},{"key":"2026032004150975000_2026.03.15.26348338v1.33","first-page":"1758","article-title":"Epigenetic clock for skin and blood cells applied to Hutchinson Gilford Progeria Syndrome and ex vivo studies","volume":"10","year":"2018","journal-title":"Aging (Albany NY)"},{"key":"2026032004150975000_2026.03.15.26348338v1.34","first-page":"394","article-title":"DNA methylation levels at individual age-associated CpG sites can be indicative for life expectancy","volume":"8","year":"2016","journal-title":"Aging (Albany NY)"},{"key":"2026032004150975000_2026.03.15.26348338v1.35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2022.06.021"},{"key":"2026032004150975000_2026.03.15.26348338v1.36","doi-asserted-by":"publisher","DOI":"10.1101\/2022.08.30.505920"},{"key":"2026032004150975000_2026.03.15.26348338v1.37","doi-asserted-by":"publisher","DOI":"10.1101\/2023.03.22.533675"},{"key":"2026032004150975000_2026.03.15.26348338v1.38","doi-asserted-by":"publisher","DOI":"10.1016\/j.tibs.2018.10.006"},{"key":"2026032004150975000_2026.03.15.26348338v1.39","doi-asserted-by":"publisher","DOI":"10.3324\/haematol.2013.087809"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.03.15.26348338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T11:15:21Z","timestamp":1774005321000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.03.15.26348338"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":39,"URL":"https:\/\/doi.org\/10.64898\/2026.03.15.26348338","relation":{},"subject":[],"published":{"date-parts":[[2026,3,18]]},"subtype":"preprint"}}