OncoCITE: Multimodal Multi-Agent Reconstruction of Clinical Oncology Knowledge Bases from Scientific Literature | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Resource OncoCITE: Multimodal Multi-Agent Reconstruction of Clinical Oncology Knowledge Bases from Scientific Literature Mujahid Quidwai, Santiago Thibaud, Dennis Shasha, Sundar Jagannath, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9160944/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Precision oncology depends on curated variant knowledge bases, yet manual curation creates latency, coverage gaps and errors, as well as inconsistent and incomplete annotation. Through systematic analysis of the 11,312 items in the CIViC database, we identified structural bottlenecks including long-tail literature distribution, resistance underrepresentation, and prolonged update delays. We developed OncoCITE, a multi-agent AI system for source-grounded extraction and harmonization of clinical genomic evidence from full-text publications. At database scale, we enriched all CIViC evidence items with ontology-standardized identifiers, achieving 83.12% item-level resolution. End-to-end extraction was validated in a disease-specific corpus using a three-way framework in which neither human curation nor AI output was treated as ground truth: the system recovered 84% of valid curated evidence, identified additional high-precision findings, and detected discrepancies in 24.2% of ground-truth items. Prospective application to emerging immunotherapy literature demonstrates real-time evidence synthesis. OncoCITE provides an auditable and open-source framework for scalable precision oncology knowledge curation. Biological sciences/Computational biology and bioinformatics/Software Biological sciences/Cancer/Cancer genomics Full Text Additional Declarations There is NO Competing Interest. Supplementary Files QuidwaietalSuppMat.pdf Supplementary Information Cite Share Download PDF Status: Under Review Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9160944","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Resource","associatedPublications":[],"authors":[{"id":612654535,"identity":"a3d46981-fb25-4f66-b2b1-5f13f3c4a7c5","order_by":0,"name":"Mujahid Quidwai","email":"","orcid":"https://orcid.org/0009-0004-8369-485X","institution":"Department of Oncological Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA","correspondingAuthor":false,"prefix":"","firstName":"Mujahid","middleName":"","lastName":"Quidwai","suffix":""},{"id":612654536,"identity":"fc4c3114-a0c8-4774-9780-611ebc96c65a","order_by":1,"name":"Santiago Thibaud","email":"","orcid":"","institution":"Division of Hematology and Medical Oncology, Icahn School of Medicine at Mount Sinai, New York, NY, USA","correspondingAuthor":false,"prefix":"","firstName":"Santiago","middleName":"","lastName":"Thibaud","suffix":""},{"id":612654537,"identity":"3f5c75e2-5b1e-425c-9d22-408f4d90f7db","order_by":2,"name":"Dennis Shasha","email":"","orcid":"","institution":"Courant Institute of Mathematical Sciences, New York University, New York, NY, USA","correspondingAuthor":false,"prefix":"","firstName":"Dennis","middleName":"","lastName":"Shasha","suffix":""},{"id":612654538,"identity":"bf7a716d-126b-42ba-b148-d53d210357fa","order_by":3,"name":"Sundar Jagannath","email":"","orcid":"https://orcid.org/0000-0003-2934-6518","institution":"Division of Hematology and Medical Oncology, Icahn School of Medicine at Mount Sinai, New York, NY, USA","correspondingAuthor":false,"prefix":"","firstName":"Sundar","middleName":"","lastName":"Jagannath","suffix":""},{"id":612654539,"identity":"10057605-8a41-41c2-ac88-0046b647a02e","order_by":4,"name":"Samir Parekh","email":"","orcid":"https://orcid.org/0000-0001-9694-8469","institution":"Division of Hematology and Medical Oncology, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Tisch Cancer Institute, Icahn School of Medicine at Mount Sinai, New York, NY, USA","correspondingAuthor":false,"prefix":"","firstName":"Samir","middleName":"","lastName":"Parekh","suffix":""},{"id":612654534,"identity":"bd2e7208-e1a5-4e9c-928b-d6d3fd41c1f0","order_by":5,"name":"Alessandro Laganà","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFklEQVRIiWNgGAWjYDACdgjF2ADEByAiDVCpAzi0MCO0QNXwwJQSr0UiAb8W/mbmwx9/1NyR3d7ewHDgxy+7PP6Zr5M//sxhkOO7kYBVi8RhtjRpnmPPjOecOcBwsLcvuVjidu42ad5tDMaSOLQwHOYxY2ZgO5w4A+ieA7w9zIkNQC3MjNsYEjfg0CJ/mP/zxx//IFoO/u2pT5x/8+zmjz+3MdTj0mJwmIdBgrcNouUwz4/DQMN5N0gAHZZggEOL4WE2M2nevsPGM3gONhyWbTieuPEM2C8ShjPPPMCqRe548+OPP74dlp3B3nzw4Zs/1YnzjoMdZiPPdxyH9xEAGDWMbXCeBCHlMPCHWIWjYBSMglEwkgAAYPNub3LR+nIAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0003-1134-0564","institution":"Department of Oncological Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Tisch Cancer Institute, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA","correspondingAuthor":true,"prefix":"","firstName":"Alessandro","middleName":"","lastName":"Laganà","suffix":""}],"badges":[],"createdAt":"2026-03-18 15:10:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9160944/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9160944/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106402832,"identity":"041c6dac-19ae-4495-8832-02ed301e4e44","added_by":"auto","created_at":"2026-04-08 09:12:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1851219,"visible":true,"origin":"","legend":"Article File","description":"","filename":"QuidwaietalOncoCITE.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9160944/v1_covered_3111c552-e880-4636-8ef2-6bed8aa72ae6.pdf"},{"id":105776667,"identity":"f4af4a90-7356-4eab-961e-6fc1e1ccdf06","added_by":"auto","created_at":"2026-03-31 03:35:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":7061629,"visible":true,"origin":"","legend":"Supplementary Information","description":"","filename":"QuidwaietalSuppMat.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9160944/v1/c873637f8b08982a560664c8.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"OncoCITE: Multimodal Multi-Agent Reconstruction of Clinical Oncology Knowledge Bases from Scientific Literature","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"
[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-9160944/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9160944/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Precision oncology depends on curated variant knowledge bases, yet manual curation creates latency, coverage gaps and errors, as well as inconsistent and incomplete annotation. Through systematic analysis of the 11,312 items in the CIViC database, we identified structural bottlenecks including long-tail literature distribution, resistance underrepresentation, and prolonged update delays. We developed OncoCITE, a multi-agent AI system for source-grounded extraction and harmonization of clinical genomic evidence from full-text publications. At database scale, we enriched all CIViC evidence items with ontology-standardized identifiers, achieving 83.12% item-level resolution. End-to-end extraction was validated in a disease-specific corpus using a three-way framework in which neither human curation nor AI output was treated as ground truth: the system recovered 84% of valid curated evidence, identified additional high-precision findings, and detected discrepancies in 24.2% of ground-truth items. Prospective application to emerging immunotherapy literature demonstrates real-time evidence synthesis. OncoCITE provides an auditable and open-source framework for scalable precision oncology knowledge curation.","manuscriptTitle":"OncoCITE: Multimodal Multi-Agent Reconstruction of Clinical Oncology Knowledge Bases from Scientific Literature","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-31 03:35:40","doi":"10.21203/rs.3.rs-9160944/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"
[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"52ce8994-b960-43ef-9ea8-a2bd5cdc22e9","owner":[],"postedDate":"March 31st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":65189304,"name":"Biological sciences/Computational biology and bioinformatics/Software"},{"id":65189305,"name":"Biological sciences/Cancer/Cancer genomics"}],"tags":[],"updatedAt":"2026-04-15T13:57:07+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-31 03:35:40","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9160944","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9160944","identity":"rs-9160944","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.