{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T02:42:25Z","timestamp":1780540945863,"version":"3.54.1"},"posted":{"date-parts":[[2025,7,18]]},"group-title":"Bioinformatics","reference-count":18,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T00:00:00Z","timestamp":1752796800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"NIH\/NIAID","award":["U24AI171008"],"award-info":[{"award-number":["U24AI171008"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,7,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Vaccine research faces challenges in integrating diverse biomedical datasets. While the Vaccine Investigation and Online Information Network (VIOLIN) provides comprehensive vaccine data, implemented in traditional relational models limit complex analysis. Similarly, the Vaccine Ontology (VO) offers standardized semantic frameworks but lacks comprehensive empirical data. This study addresses these limitations by developing the Vaccine Knowledge Graph (VaxKG) that integrates VIOLIN\u2019s dataset with VO\u2019s standardized terminology. Using Neo4j, we transformed 12 core VIOLIN tables into a graph structure enriched with VO concepts. The resulting knowledge graph comprises 28,123 VIOLIN data nodes and 101,282 VO resource nodes, connected by 412,865 relationships. Our comparative analysis of Brucella and Influenza vaccines demonstrates VaxKG\u2019s ability to enable complex semantic queries and reveal insights unavailable from either resource alone. We further demonstrate VaxKG\u2019s utility through VaxChat, a large language model application that leverages the VaxKG as Retrieval-Augmented Generation (RAG) for intuitive vaccine information access.<\/jats:p>","DOI":"10.1101\/2025.07.15.664450","type":"posted-content","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T19:20:11Z","timestamp":1752866411000},"source":"Crossref","is-referenced-by-count":1,"title":["VaxKG: Integrating The Vaccine Ontology And VIOLIN For Advanced Vaccine Queries And LLM-Powered Chat Systems"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2294-3571","authenticated-orcid":false,"given":"Feng-Yu","family":"(Leo) Yeh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Asato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-0103","authenticated-orcid":false,"given":"Jie","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9189-9661","authenticated-orcid":false,"given":"Yongqun Oliver","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"issue":"12","key":"2025072114101680000_2025.07.15.664450v1.1","first-page":"241","article-title":"Ten great public health achievements--United States, 1900-1999","volume":"48","author":"Centers for Disease Control and Prevention (CDC","year":"1999","journal-title":"MMWR. Morbidity and mortality weekly report"},{"issue":"Suppl_1","key":"2025072114101680000_2025.07.15.664450v1.2","first-page":"D923","article-title":"VIOLIN: vaccine investigation and online information network","volume":"36","year":"2007","journal-title":"Nucleic acids research"},{"key":"2025072114101680000_2025.07.15.664450v1.3","doi-asserted-by":"crossref","unstructured":"He Y , Cowell L , Diehl AD , Mobley HL , Peters B , Ruttenberg A , Scheuermann RH , Brinkman RR , Courtot M , Mungall C. The 1st International Conference on Biomedical Ontology (ICBO 2009). InVO: Vaccine Ontology 2009.","DOI":"10.1038\/npre.2009.3553.1"},{"key":"2025072114101680000_2025.07.15.664450v1.4","doi-asserted-by":"crossref","unstructured":"Reese JT , Unni D , Callahan TJ , Cappelletti L , Ravanmehr V , Carbon S , Shefchek KA , Good BM , Balhoff JP , Fontana T , Blau H. KG-COVID-19: a framework to produce customized knowledge graphs for COVID-19 response. Patterns. 2021 Jan 8;2(1).","DOI":"10.1016\/j.patter.2020.100155"},{"key":"2025072114101680000_2025.07.15.664450v1.5","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac957"},{"key":"2025072114101680000_2025.07.15.664450v1.6","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"2025072114101680000_2025.07.15.664450v1.7","unstructured":"Zheng J , He Y. VO [Internet]. 2025 [cited 2025 Feb 28]. Available from: http:\/\/purl.obolibrary.org\/obo\/vo\/releases\/2025-02-26\/vo.owl"},{"key":"2025072114101680000_2025.07.15.664450v1.8","unstructured":"Feng-Yu Y. VaxKG [Internet]. 2025 [cited 2025 March 23]. Available from: https:\/\/github.com\/VIOLINet\/VaxKG"},{"key":"2025072114101680000_2025.07.15.664450v1.9","unstructured":"Jes\u00fas B , Adam C. neosemantics (n10s) [Internet]. 2024 [cited 2025 March 01]. Available from: https:\/\/github.com\/neo4j-labs\/neosemantics"},{"key":"2025072114101680000_2025.07.15.664450v1.10","unstructured":"Chase H. Langchain [Internet]. 2025 [cited 2025 March 17]. Available from: https:\/\/github.com\/langchain-ai\/langchain"},{"key":"2025072114101680000_2025.07.15.664450v1.11","unstructured":"Matthew A. VaxKG [Internet]. 2025 [cited 2025 March 20]. Available from: https:\/\/github.com\/crazab0i\/VaxChat"},{"key":"2025072114101680000_2025.07.15.664450v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.vaccine.2012.11.066"},{"key":"2025072114101680000_2025.07.15.664450v1.13","doi-asserted-by":"crossref","first-page":"639491","DOI":"10.3389\/fimmu.2021.639491","article-title":"VaximmutorDB: A web-based vaccine immune factor database and its application for understanding vaccine-induced immune mechanisms","volume":"12","year":"2021","journal-title":"Frontiers in immunology"},{"key":"2025072114101680000_2025.07.15.664450v1.14","article-title":"Scalable zero-shot entity linking with dense entity retrieval","year":"2019","journal-title":"arXiv preprint"},{"issue":"1","key":"2025072114101680000_2025.07.15.664450v1.15","first-page":"17","article-title":"Knowledge graphs: introduction, history and perspectives","volume":"43","year":"2022","journal-title":"AI Magazine"},{"key":"2025072114101680000_2025.07.15.664450v1.16","doi-asserted-by":"crossref","unstructured":"Dominguez-Sal D , Urb\u00f3n-Bayes P , Gim\u00e9nez-Van\u00f3 A , G\u00f3mez-Villamor S , Mart\u00ednez-Bazan N , Larriba-Pey JL . Survey of graph database performance on the hpc scalable graph analysis benchmark. InInternational Conference on Web-Age Information Management 2010 Jul 15 (pp. 37\u201348). Berlin, Heidelberg: Springer Berlin Heidelberg.","DOI":"10.1007\/978-3-642-16720-1_4"},{"issue":"1","key":"2025072114101680000_2025.07.15.664450v1.17","first-page":"1","article-title":"ImmPort, toward repurposing of open access immunological assay data for translational and clinical research","volume":"5","year":"2018","journal-title":"Scientific data"},{"key":"2025072114101680000_2025.07.15.664450v1.18","doi-asserted-by":"publisher","DOI":"10.1038\/75556"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.07.15.664450","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T09:09:05Z","timestamp":1768468145000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.07.15.664450"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1101\/2025.07.15.664450","relation":{},"subject":[],"published":{"date-parts":[[2025,7,18]]},"subtype":"preprint"}}