{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T02:15:34Z","timestamp":1779243334588,"version":"3.51.4"},"reference-count":17,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"content-version":"vor","delay-in-days":4,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR00112490472"],"award-info":[{"award-number":["HR00112490472"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-22-1-0215"],"award-info":[{"award-number":["FA9550-22-1-0215"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Integrating Large Language Models (LLMs) with research tools presents technical and reproducibility challenges for biomedical research. While commercial artificial intelligence (AI) systems are easy to adopt, they obscure data provenance, lack transparency, and can generates false information, making them unfit for many research problems. To address these challenges, we developed the Bioinformatics Retrieval Augmented Digital (BRAD) agent software system.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Here, we introduce BRAD, an agentic system that integrates LLMs with external tools and data to streamline research workflows. BRAD\u2019s modular agents retrieve information from literature, custom software, and online databases while maintaining transparent protocols to increase the reliability of AI generated results. We apply BRAD to a biomarker discovery pipeline, automating both execution and the generation of enrichment reports. This workflow contextualizes user data within the literature, enabling a level of interpretation and automation that surpasses conventional research tools. Beyond the workflow we highlight here, BRAD is a flexible system that has been deployed in other applications including a chatbot, video RAG, and analysis of single cell data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The source code for BRAD is available at https:\/\/github.com\/Jpickard1\/BRAD; Information for pip installation, tutorials, documentation, and further information can be found at: ReadTheDocs.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf159","type":"journal-article","created":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T14:45:48Z","timestamp":1746456348000},"source":"Crossref","is-referenced-by-count":10,"title":["Automatic biomarker discovery and enrichment with BRAD"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8763-3200","authenticated-orcid":false,"given":"Joshua","family":"Pickard","sequence":"first","affiliation":[{"name":"Gilbert S. Omenn Department of Computational Medicine and Bioinformatics, University of Michigan Medical School , Ann Arbor, MI 48109,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ram","family":"Prakash","sequence":"additional","affiliation":[{"name":"Gilbert S. Omenn Department of Computational Medicine and Bioinformatics, University of Michigan Medical School , Ann Arbor, MI 48109,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc Andrew","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of Michigan , Ann Arbor, MI 48109,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Natalie","family":"Oliven","sequence":"additional","affiliation":[{"name":"Gilbert S. Omenn Department of Computational Medicine and Bioinformatics, University of Michigan Medical School , Ann Arbor, MI 48109,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cooper","family":"Stansbury","sequence":"additional","affiliation":[{"name":"Gilbert S. Omenn Department of Computational Medicine and Bioinformatics, University of Michigan Medical School , Ann Arbor, MI 48109,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jillian","family":"Cwycyshyn","sequence":"additional","affiliation":[{"name":"Gilbert S. Omenn Department of Computational Medicine and Bioinformatics, University of Michigan Medical School , Ann Arbor, MI 48109,","place":["United States"]},{"name":"Department of Biomedical Engineering, University of Michigan , Ann Arbor, MI 48109,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas","family":"Galioto","sequence":"additional","affiliation":[{"name":"Gilbert S. Omenn Department of Computational Medicine and Bioinformatics, University of Michigan Medical School , Ann Arbor, MI 48109,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Gorodetsky","sequence":"additional","affiliation":[{"name":"Department of Aerospace Engineering, University of Michigan , Ann Arbor, MI 48109,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6757-105X","authenticated-orcid":false,"given":"Alvaro","family":"Velasquez","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Colorado Boulder , Boulder, CO 80309,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6160-9168","authenticated-orcid":false,"given":"Indika","family":"Rajapakse","sequence":"additional","affiliation":[{"name":"Gilbert S. Omenn Department of Computational Medicine and Bioinformatics, University of Michigan Medical School , Ann Arbor, MI 48109,","place":["United States"]},{"name":"Department of Mathematics, University of Michigan , Ann Arbor, MI 48109,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,5,5]]},"reference":[{"key":"2025051307512110700_btaf159-B1","volume-title":"Generative AI with LangChain: Build Large Language Model (LLM) Apps with Python, ChatGPT, and Other LLMs","author":"Affarth","year":"2023"},{"key":"2025051307512110700_btaf159-B2","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1038\/s41586-023-06792-0","article-title":"Autonomous chemical research with large language models","volume":"624","author":"Boiko","year":"2023","journal-title":"Nature"},{"key":"2025051307512110700_btaf159-B3","doi-asserted-by":"crossref","first-page":"8002","DOI":"10.1073\/pnas.1505822112","article-title":"Functional organization of the human 4D nucleome","volume":"112","author":"Chen","year":"2015","journal-title":"Proc Natl Acad Sci USA"},{"key":"2025051307512110700_btaf159-B4","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae679","article-title":"LMRAC: a functionally extensible tool for LLM interrogation of user experimental results","volume":"40","author":"Craig","year":"2024","journal-title":"Bioinformatics"},{"key":"2025051307512110700_btaf159-B5","author":"Gao","year":"2023"},{"key":"2025051307512110700_btaf159-B6","doi-asserted-by":"crossref","first-page":"W90","DOI":"10.1093\/nar\/gkw377","article-title":"Enrichr: a comprehensive gene set enrichment analysis web server 2016 update","volume":"44","author":"Kuleshov","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2025051307512110700_btaf159-B7","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025051307512110700_btaf159-B8","doi-asserted-by":"crossref","first-page":"btac836","DOI":"10.1093\/bioinformatics\/btac836","article-title":"Efficient querying of genomic reference databases with GGET","volume":"39","author":"Luebbert","year":"2023","journal-title":"Bioinformatics"},{"key":"2025051307512110700_btaf159-B9","doi-asserted-by":"crossref","first-page":"btaf031","DOI":"10.1093\/bioinformatics\/btaf031","article-title":"Escargot: an ai agent leveraging large language models, dynamic graph of thoughts, and biomedical knowledge graphs for enhanced reasoning","volume":"41","author":"Matsumoto","year":"2025","journal-title":"Bioinformatics"},{"key":"2025051307512110700_btaf159-B10","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae353","article-title":"Kragen: a knowledge graph-enhanced rag framework for biomedical problem solving using large language models","volume":"40","author":"Matsumoto","year":"2024","journal-title":"Bioinformatics"},{"key":"2025051307512110700_btaf159-B11","author":"Pickard","year":"2024"},{"key":"2025051307512110700_btaf159-B12","author":"Sahoo","year":"2024"},{"key":"2025051307512110700_btaf159-B13","author":"Schaefer","year":"2024"},{"key":"2025051307512110700_btaf159-B14","author":"Shavit","year":"2023"},{"key":"2025051307512110700_btaf159-B15","author":"Swanson","year":"2024"},{"key":"2025051307512110700_btaf159-B16","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025051307512110700_btaf159-B17","first-page":"819","volume-title":"Cold Spring Harbor Symposia on Quantitative Biology","author":"Weintraub","year":"1993"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf159\/63054849\/btaf159.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/5\/btaf159\/63054849\/btaf159.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/5\/btaf159\/63054849\/btaf159.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T11:51:35Z","timestamp":1747137095000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf159\/8125018"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":17,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5,6]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf159","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,5]]},"published":{"date-parts":[[2025,5]]},"article-number":"btaf159"}}