{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T18:55:46Z","timestamp":1791572146565,"version":"4.3.4"},"reference-count":13,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T00:00:00Z","timestamp":1790380800000},"content-version":"vor","delay-in-days":268,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DBI-2321666"],"award-info":[{"award-number":["DBI-2321666"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"United States Department of Energy","doi-asserted-by":"publisher","award":["DE-SC0019749"],"award-info":[{"award-number":["DE-SC0019749"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000060","name":"National Institute of Allergy and Infectious Diseases","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000060","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Institute of General Medical Sciences of the National Institutes of Health","award":["R01GM157729"],"award-info":[{"award-number":["R01GM157729"]}],"id":[{"id":"https:\/\/ror.org\/04q48ey07","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Structural biologists have contributed more than 260\u2009000 experimentally determined three-dimensional structures of biological macromolecules to the Protein Data Bank. Incoming depositions are validated and biocurated by approximately 20 expert biocurators at the collaborating data centers worldwide. Biocurators at the Research Collaboratory for Structural Bioinformatics Protein Data Bank, who process more than 40% of global depositions, face growing difficulty sustaining efficient Help Desk operations, having received roughly 19\u2009000 depositor messages across some 8000 entries in 2025.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We developed an artificial intelligence Help Desk assistant built on retrieval-augmented generation. Source documents are converted to Markdown with layout preserved, divided by a two-stage chunking procedure, embedded, and stored in a relational vector database. At query time, maximal marginal relevance retrieval selects diverse supporting passages, a topical guardrail filters out-of-scope questions, and a purpose-built system prompt prevents disclosure of internal curation terminology. Separate language model configurations handle question condensing and answer generation. The service runs in production on a container orchestration platform, providing around-the-clock depositor assistance with streaming, citation-backed responses.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Freely available at https:\/\/rcsb-deposit-help.rcsb.org. Source code: https:\/\/github.com\/rcsb\/rcsb-pdb-helpdesk (archived at Zenodo: https:\/\/doi.org\/10.5281\/zenodo.19560785).<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioadv\/vbag289","type":"journal-article","created":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T11:11:22Z","timestamp":1790334682000},"source":"Crossref","is-referenced-by-count":0,"title":["RCSB PDB AI Help Desk: retrieval-augmented generation for protein structure deposition support"],"prefix":"10.1093","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1804-5035","authenticated-orcid":false,"given":"Vivek Reddy","family":"Chithari","sequence":"first","affiliation":[{"name":"RCSB Protein Data Bank, Rutgers, The State University of New Jersey , Piscataway, NJ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8896-6878","authenticated-orcid":false,"given":"Jasmine Y","family":"Young","sequence":"additional","affiliation":[{"name":"RCSB Protein Data Bank, Rutgers, The State University of New Jersey , Piscataway, NJ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9544-8390","authenticated-orcid":false,"given":"Irina","family":"Persikova","sequence":"additional","affiliation":[{"name":"RCSB Protein Data Bank, Rutgers, The State University of New Jersey , Piscataway, NJ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0574-2041","authenticated-orcid":false,"given":"Yuhe","family":"Liang","sequence":"additional","affiliation":[{"name":"RCSB Protein Data Bank, Rutgers, The State University of New Jersey , Piscataway, NJ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0512-1031","authenticated-orcid":false,"given":"Gregg V","family":"Crichlow","sequence":"additional","affiliation":[{"name":"RCSB Protein Data Bank, Rutgers, The State University of New Jersey , Piscataway, NJ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5406-8156","authenticated-orcid":false,"given":"Justin W","family":"Flatt","sequence":"additional","affiliation":[{"name":"RCSB Protein Data Bank, Rutgers, The State University of New Jersey , Piscataway, NJ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8784-0894","authenticated-orcid":false,"given":"Sutapa","family":"Ghosh","sequence":"additional","affiliation":[{"name":"RCSB Protein Data Bank, Rutgers, The State University of New Jersey , Piscataway, NJ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6121-9442","authenticated-orcid":false,"given":"Brian P","family":"Hudson","sequence":"additional","affiliation":[{"name":"RCSB Protein Data Bank, Rutgers, The State University of New Jersey , Piscataway, NJ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7905-6327","authenticated-orcid":false,"given":"Ezra","family":"Peisach","sequence":"additional","affiliation":[{"name":"RCSB Protein Data Bank, Rutgers, The State University of New Jersey , Piscataway, NJ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2694-7003","authenticated-orcid":false,"given":"Monica","family":"Sekharan","sequence":"additional","affiliation":[{"name":"RCSB Protein Data Bank, Rutgers, The State University of New Jersey , Piscataway, NJ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6817-7476","authenticated-orcid":false,"given":"Chenghua","family":"Shao","sequence":"additional","affiliation":[{"name":"RCSB Protein Data Bank, Rutgers, The State University of New Jersey , Piscataway, NJ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2487-9713","authenticated-orcid":false,"given":"Stephen K","family":"Burley","sequence":"additional","affiliation":[{"name":"RCSB Protein Data Bank, Rutgers, The State University of New Jersey , Piscataway, NJ,","place":["United States"]},{"name":"RCSB Protein Data Bank, San Diego Supercomputer Center, University of California San Diego , San Diego, CA,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"2026100914414107100_vbag289-B1","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The Protein Data Bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2026100914414107100_vbag289-B2","doi-asserted-by":"publisher","first-page":"D464","DOI":"10.1093\/nar\/gky1004","article-title":"RCSB Protein Data Bank: biological macromolecular structures enabling research and education in fundamental biology, biomedicine, biotechnology and energy","volume":"47","author":"Burley","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2026100914414107100_vbag289-B3","first-page":"335","author":"Carbonell","year":"1998"},{"key":"2026100914414107100_vbag289-B4","author":"Chase","year":"2026"},{"key":"2026100914414107100_vbag289-B5","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":"2026100914414107100_vbag289-B6","first-page":"Article 2","article-title":"Docker: lightweight Linux containers for consistent development and deployment","volume":"2014","author":"Merkel","year":"2014","journal-title":"Linux Journal"},{"key":"2026100914414107100_vbag289-B7","author":"OpenAI","year":"2025"},{"key":"2026100914414107100_vbag289-B8","author":"OpenAI","year":"2024"},{"key":"2026100914414107100_vbag289-B9","author":"pgvector","year":"2026"},{"key":"2026100914414107100_vbag289-B10","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1038\/newbio233223b0","article-title":"Crystallography: Protein Data Bank","volume":"233","author":"Protein Data Bank","year":"1971","journal-title":"Nature New Biol"},{"key":"2026100914414107100_vbag289-B11","doi-asserted-by":"publisher","first-page":"D520","DOI":"10.1093\/nar\/gky949","article-title":"Protein Data Bank: the single global archive for 3D macromolecular structure data","volume":"47","author":"wwPDB Consortium","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2026100914414107100_vbag289-B12","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1016\/j.str.2017.01.004","article-title":"OneDep: unified wwPDB system for deposition, biocuration, and validation of macromolecular structures in the PDB archive","volume":"25","author":"Young","year":"2017","journal-title":"Structure"},{"key":"2026100914414107100_vbag289-B13","doi-asserted-by":"publisher","first-page":"bay002","DOI":"10.1093\/database\/bay002","article-title":"Worldwide Protein Data Bank biocuration supporting open access to high-quality 3D structural biology data","volume":"2018","author":"Young","year":"2018","journal-title":"Database"}],"container-title":["Bioinformatics Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/advance-article-pdf\/doi\/10.1093\/bioadv\/vbag289\/71400350\/vbag289.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article-pdf\/6\/1\/vbag289\/71400350\/vbag289.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article-pdf\/6\/1\/vbag289\/71400350\/vbag289.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T18:41:52Z","timestamp":1791571312000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformaticsadvances\/article\/doi\/10.1093\/bioadv\/vbag289\/8836409"}},"subtitle":[],"editor":[{"given":"Michael","family":"Gromiha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":13,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,7]]}},"URL":"https:\/\/doi.org\/10.1093\/bioadv\/vbag289","relation":{},"ISSN":["2635-0041"],"issn-type":[{"value":"2635-0041","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026]]},"published":{"date-parts":[[2026]]},"article-number":"vbag289"}}