Adapting bioinformatics data systems in the era of foundational models: leveraging retrieval-augmented generation and low-resource large language models

Adapting bioinformatics data systems in the era of foundational models: leveraging retrieval-augmented generation and low-resource large language models | 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 Short Report Adapting bioinformatics data systems in the era of foundational models: leveraging retrieval-augmented generation and low-resource large language models Chihiro Higuchi, Miho Irie, Takahiro Ide, Tatsuya Kushida This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7360068/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract We investigated how to leverage existing assets, such as curated life science database catalogs, in the era of information retrieval powered by large language models (LLMs). Although LLMs exhibit unprecedented information provision capabilities, they inherently suffer from hallucinations, which is an unavoidable limitation. Retrieval-augmented generation (RAG) is a promising approach to mitigate this issue. Furthermore, the analysis of personal data, such as human biological samples, must be conducted in an isolated environment, precluding the use of external Internet-based services. If a system that integrates LLMs and a RAG could be implemented within an isolated environment, it would significantly enhance research activities, including those involving personal data analysis. We evaluated the feasibility of using local LLMs and the effectiveness of the RAG score in reducing the incidence of hallucinations. Regarding the former, existing technologies such as those in Ollama suggest that local deployment is viable. For the latter, a rigorous selection of data sources for the RAG is essential. In particular, we found that establishing a well-structured repository of Japanese-language resources is crucial. Future challenges include optimizing the LLMs for this system and incorporating AI agent functionalities to enhance its overall performance. Foundational models Large language models Retrieval-augmented generation In-context learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted 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-7360068","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Short Report","associatedPublications":[],"authors":[{"id":501201115,"identity":"fbc2ed01-7ba3-46ec-8d63-9fd903e626c8","order_by":0,"name":"Chihiro Higuchi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzUlEQVRIiWNgGAWjYBACA2YgwdggIcfAzAMRYWwgUosxCVqgqhIbGHiIdJg5O/s1iZ87LNK3s/Mee8Dwy4aBeTYBayybecoke89I5O5s5ks3YOxLY2Ccc4CAww7zpEkztknkbjjMYybB2HOYgXFGAnFa0g1I0MJ+DKQlAayF4QdxtjBb9rZJGG44zJcmkdiQxkPYL+ePP7zxs61O3uD82WMSH/7YyBkSCjEGBh4DBDuxjYHHcAYhHQzsD5A4fxgY5CUIahkFo2AUjIIRBgDL5D8gSO5JZAAAAABJRU5ErkJggg==","orcid":"","institution":"National Institutes of Biomedical Innovation, Health and Nutrition (NIBN)","correspondingAuthor":true,"prefix":"","firstName":"Chihiro","middleName":"","lastName":"Higuchi","suffix":""},{"id":501201116,"identity":"fe361169-5776-4bd5-8327-3184db05df95","order_by":1,"name":"Miho Irie","email":"","orcid":"","institution":"Ono Pharmaceutical Co., Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Miho","middleName":"","lastName":"Irie","suffix":""},{"id":501201117,"identity":"fd25e84a-b4a3-4d79-ae7e-6f164ca66dae","order_by":2,"name":"Takahiro Ide","email":"","orcid":"","institution":"Office of NBDC Program, Japan Science and Technology Agency","correspondingAuthor":false,"prefix":"","firstName":"Takahiro","middleName":"","lastName":"Ide","suffix":""},{"id":501201118,"identity":"ca0c0e30-bee3-47a0-9396-639b676bc6f1","order_by":3,"name":"Tatsuya Kushida","email":"","orcid":"","institution":"RIKEN","correspondingAuthor":false,"prefix":"","firstName":"Tatsuya","middleName":"","lastName":"Kushida","suffix":""}],"badges":[],"createdAt":"2025-08-13 02:38:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7360068/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7360068/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":99314296,"identity":"a78372df-ee50-4c7f-84f5-bc919c0ed566","added_by":"auto","created_at":"2025-12-31 16:21:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":247790,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7360068/v1_covered_b9804aac-8170-4555-8319-4ea827f5128a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Adapting bioinformatics data systems in the era of foundational models: leveraging retrieval-augmented generation and low-resource large language models","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Foundational models, Large language models, Retrieval-augmented generation, In-context learning","lastPublishedDoi":"10.21203/rs.3.rs-7360068/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7360068/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWe investigated how to leverage existing assets, such as curated life science database catalogs, in the era of information retrieval powered by large language models (LLMs). Although LLMs exhibit unprecedented information provision capabilities, they inherently suffer from hallucinations, which is an unavoidable limitation. Retrieval-augmented generation (RAG) is a promising approach to mitigate this issue. Furthermore, the analysis of personal data, such as human biological samples, must be conducted in an isolated environment, precluding the use of external Internet-based services. If a system that integrates LLMs and a RAG could be implemented within an isolated environment, it would significantly enhance research activities, including those involving personal data analysis. We evaluated the feasibility of using local LLMs and the effectiveness of the RAG score in reducing the incidence of hallucinations. Regarding the former, existing technologies such as those in Ollama suggest that local deployment is viable. For the latter, a rigorous selection of data sources for the RAG is essential. In particular, we found that establishing a well-structured repository of Japanese-language resources is crucial. Future challenges include optimizing the LLMs for this system and incorporating AI agent functionalities to enhance its overall performance.\u003c/p\u003e","manuscriptTitle":"Adapting bioinformatics data systems in the era of foundational models: leveraging retrieval-augmented generation and low-resource large language models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-19 08:13:45","doi":"10.21203/rs.3.rs-7360068/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"aa478e39-ed5c-4423-99e4-7236da788f8c","owner":[],"postedDate":"August 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-12-27T09:54:07+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-19 08:13:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7360068","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7360068","identity":"rs-7360068","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}