{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,15]],"date-time":"2026-11-15T06:06:57Z","timestamp":1794722817680,"version":"4.9.1"},"reference-count":38,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"vor","delay-in-days":204,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001700","name":"MEXT","doi-asserted-by":"publisher","award":["JPNLDP202401"],"award-info":[{"award-number":["JPNLDP202401"]}],"id":[{"id":"10.13039\/501100001700","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004696","name":"NBDC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004696","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["NAC-ES-PUB-ASV-2025"],"award-info":[{"award-number":["NAC-ES-PUB-ASV-2025"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["PID2024-157010OB-I00"],"award-info":[{"award-number":["PID2024-157010OB-I00"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Querying the RDF Portal knowledge graph maintained by DBCLS\u2014which aggregates ~60 life-science databases\u2014requires proficiency in both SPARQL and database-specific RDF schemas, placing this resource beyond the reach of most researchers. Large Language Models (LLMs) can, in principle, translate natural-language questions into executable SPARQL, but without schema-level context, they frequently fabricate non-existent predicates or fail to resolve entity names to database-specific identifiers. We present TogoMCP, a system that recasts the LLM as a protocol-driven inference engine orchestrating specialized tools via the Model Context Protocol (MCP). Two mechanisms are essential to its design: (i) the MIE (Metadata-Interoperability-Exchange) file, a concise YAML document that dynamically supplies the LLM with each target database\u2019s structural and semantic context at query time; and (ii) a two-stage workflow separating entity resolution via external REST APIs from schema-guided SPARQL generation. On a benchmark of 50 biologically grounded questions spanning five types and 23 databases, TogoMCP achieved a large improvement over an unaided baseline (Cohen\u2019s $d = 1.82$, Wilcoxon $P \\lt .001$), with win rates exceeding 80% for question types with precise, verifiable answers. An ablation study shows that all component configurations deliver significant improvements, with MIE schema files providing the largest marginal contribution on mean per-question score ($\\Delta = +0.50$ relative to a no-MIE condition, two-sided Wilcoxon $P = .067$; 90% bootstrap CI $[+0.04,\\,\\,+0.94]$ excludes zero); a one-line instruction to load the relevant MIE file recovers the same mean improvement as a full procedural protocol, while the protocol additionally reduces downside risk (loss rate 1.6% vs. 4.8%, Fisher $P = .036$). These results suggest a general design principle: concise, dynamically delivered schema context is more valuable than complex orchestration logic for mean score performance, while procedural guidance plays a complementary role in narrowing variance. Database URL: \u00a0https:\/\/togomcp.rdfportal.org\/.<\/jats:p>","DOI":"10.1093\/database\/baag042","type":"journal-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T11:50:30Z","timestamp":1783770630000},"source":"Crossref","is-referenced-by-count":1,"title":["TogoMCP: natural language querying of life-science knowledge graphs via schema-guided LLMs and the Model Context Protocol"],"prefix":"10.1093","volume":"2026","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4006-8208","authenticated-orcid":false,"given":"Akira R","family":"Kinjo","sequence":"first","affiliation":[{"name":"Anima Machina G.K. , Osaka Station Building No. 3, 29th Floor, Room 1-1-1, 1-1-3 Umeda, Kita-ku, Osaka 530-0001 ,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6943-6887","authenticated-orcid":false,"given":"Yasunori","family":"Yamamoto","sequence":"additional","affiliation":[{"name":"Database Center for Life Science, Joint Support-Center for Data Science Research, Research Organization of Information and Systems , 10-3 Midori-cho, Tachikawa, 190-0014 Tokyo ,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8631-2682","authenticated-orcid":false,"given":"Samuel","family":"Bustamante-Larriet","sequence":"additional","affiliation":[{"name":"University of Oviedo, Department of Computer Science , C\/ Federico Garc\u00eda Lorca, S\/N, Oviedo, Aturias ,","place":["Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8907-5348","authenticated-orcid":false,"given":"Jose-Emilio","family":"Labra-Gayo","sequence":"additional","affiliation":[{"name":"University of Oviedo, Department of Computer Science , C\/ Federico Garc\u00eda Lorca, S\/N, Oviedo, Aturias ,","place":["Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8978-3344","authenticated-orcid":false,"given":"Takatomo","family":"Fujisawa","sequence":"additional","affiliation":[{"name":"Bioinformation and DDBJ Center, National Institute of Genetics, Research Organization of Information and Systems , 1111 Yata, Mishima, 411-8540 Shizuoka ,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,24]]},"reference":[{"key":"2026092206060846600_bib1","article-title":"RDF 1.1 Concepts and Abstract Syntax","author":"Cyganiak","year":"2014"},{"key":"2026092206060846600_bib2","doi-asserted-by":"publisher","first-page":"D609","DOI":"10.1093\/nar\/gkae1010","article-title":"UniProt: the Universal Protein Knowledgebase in 2025","volume":"53","author":"The UniProt Consortium","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026092206060846600_bib3","doi-asserted-by":"publisher","first-page":"bay123","DOI":"10.1093\/database\/bay123","article-title":"NBDC RDF portal: a comprehensive repository for semantic data in life sciences","volume":"2018","author":"Kawashima","year":"2018","journal-title":"Database"},{"key":"2026092206060846600_bib4","doi-asserted-by":"publisher","first-page":"D1180","DOI":"10.1093\/nar\/gkad1004","article-title":"The ChEMBL Database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods","volume":"52","author":"Zdrazil","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026092206060846600_bib5","first-page":"265","article-title":"Medical Subject Headings (MeSH)","volume":"88","author":"Lipscomb","year":"2000","journal-title":"Bull Med Libr Assoc"},{"key":"2026092206060846600_bib6","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1038\/75556","article-title":"Gene Ontology: tool for the unification of biology","volume":"25","author":"Ashburner","year":"2000","journal-title":"Nat Genet"},{"key":"2026092206060846600_bib7","article-title":"SPARQL 1.1 Query Language","author":"Harris","year":"2013"},{"key":"2026092206060846600_bib8","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.48550\/arXiv.2005.14165","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026092206060846600_bib9","article-title":"Augmented language models: a survey","author":"Mialon","year":"2023","journal-title":"Trans Mach Learn Res"},{"key":"2026092206060846600_bib10","doi-asserted-by":"publisher","first-page":"3580","DOI":"10.1109\/TKDE.2024.3352100","article-title":"Unifying large language models and knowledge graphs: a roadmap","volume":"36","author":"Pan","year":"2024","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2026092206060846600_bib11","article-title":"SPARQL generation: an analysis on fine-tuning OpenLLaMA for question answering over a life science knowledge graph","volume-title":"Proceedings of the 15th International Conference on Semantic Web Applications and Tools for Health Care and Life Sciences (SWAT4HCLS 2024)","author":"Rangel","year":"2024"},{"key":"2026092206060846600_bib12","doi-asserted-by":"publisher","article-title":"LLM-based SPARQL query generation from natural language over federated knowledge graphs","author":"Emonet","DOI":"10.48550\/arXiv.2410.06062"},{"key":"2026092206060846600_bib13","doi-asserted-by":"publisher","article-title":"SPARQL-LLM: real-time SPARQL query generation from natural language questions","author":"Smeros","DOI":"10.48550\/arXiv.2512.14277"},{"key":"2026092206060846600_bib14","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1007\/978-3-031-99554-5_8","article-title":"SPARQL Query Generation Using LLMs for Medical Information Retrieval","volume-title":"The Semantic Web: ESWC 2025 Satellite Events, LNCS","author":"Doulaverakis","year":"2026"},{"key":"2026092206060846600_bib15","doi-asserted-by":"publisher","first-page":"104993","DOI":"10.1016\/j.jbi.2026.104993","article-title":"Ontology-grounded knowledge graphs for mitigating hallucinations in large language models for clinical question answering","volume":"175","author":"Ali","year":"2026","journal-title":"J Biomed Inform"},{"key":"2026092206060846600_bib16","doi-asserted-by":"publisher","first-page":"D33","DOI":"10.1093\/nar\/gkad1044","article-title":"Database resources of the National Center for Biotechnology Information","volume":"52","author":"Sayers","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026092206060846600_bib17","doi-asserted-by":"publisher","first-page":"4194","DOI":"10.1093\/bioinformatics\/btac491","article-title":"TogoID: an exploratory ID converter to bridge biological datasets","volume":"38","author":"Ikeda","year":"2022","journal-title":"Bioinformatics"},{"key":"2026092206060846600_bib18","doi-asserted-by":"publisher","first-page":"btaf279","DOI":"10.1093\/bioinformatics\/btaf279","article-title":"OLS4: a new Ontology Lookup Service for a growing interdisciplinary knowledge ecosystem","volume":"41","author":"McLaughlin","year":"2025","journal-title":"Bioinformatics"},{"key":"2026092206060846600_bib19","article-title":"PubDictionaries: a public resource of dictionaries for life sciences","volume-title":"Proceedings of the 10th International Conference on Biomedical Ontology (ICBO)","author":"Kim","year":"2019"},{"key":"2026092206060846600_bib20","doi-asserted-by":"publisher","first-page":"D1373","DOI":"10.1093\/nar\/gkac956","article-title":"PubChem 2023 update","volume":"51","author":"Kim","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2026092206060846600_bib21","doi-asserted-by":"publisher","first-page":"D282","DOI":"10.1093\/nar\/gkw962","article-title":"Protein Data Bank Japan (PDBj): updated user interfaces, resource description framework, analysis tools for large structures","volume":"45","author":"Kinjo","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2026092206060846600_bib22","doi-asserted-by":"publisher","first-page":"D687","DOI":"10.1093\/nar\/gkab1028","article-title":"The Reactome pathway knowledgebase 2022","volume":"50","author":"Gillespie","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2026092206060846600_bib23","doi-asserted-by":"publisher","first-page":"D878","DOI":"10.1093\/nar\/gkae1118","article-title":"Bgee in 2024: focus on curated single-cell RNA-seq datasets, and query tools","volume":"53","author":"Bastian","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026092206060846600_bib24","doi-asserted-by":"publisher","first-page":"D513","DOI":"10.1093\/nar\/gkad1020","article-title":"OMA orthology in 2024: improved prokaryote coverage, ancestral and extant GO enrichment, a revamped synteny viewer and more in the OMA Ecosystem","volume":"52","author":"Altenhoff","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026092206060846600_bib25","doi-asserted-by":"publisher","first-page":"D527","DOI":"10.1093\/nar\/gkaf1113","article-title":"BRENDA in 2026: a Global Core Biodata Resource for functional enzyme and metabolic data within the DSMZ Digital Diversity","volume":"54","author":"Hauenstein","year":"2026","journal-title":"Nucleic Acids Res"},{"key":"2026092206060846600_bib26","doi-asserted-by":"publisher","first-page":"D1098","DOI":"10.1093\/nar\/gkaf1229","article-title":"Genenames.org: the HGNC and PGNC resources in 2026","volume":"54","author":"Seal","year":"2026","journal-title":"Nucleic Acids Res"},{"key":"2026092206060846600_bib27","doi-asserted-by":"publisher","first-page":"D462","DOI":"10.1093\/nar\/gkae1032","article-title":"jPOST environment accelerates the reuse and reanalysis of public proteome mass spectrometry data","volume":"53","author":"Okuda","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026092206060846600_bib28","doi-asserted-by":"publisher","first-page":"907","DOI":"10.1007\/s00216-024-05692-0","article-title":"Updates implemented in version 4 of the GlyCosmos Glycoscience Portal","volume":"417","author":"Lee","year":"2025","journal-title":"Anal Bioanal Chem"},{"key":"2026092206060846600_bib29","doi-asserted-by":"publisher","first-page":"D44","DOI":"10.1093\/nar\/gkad902","article-title":"The SIB Swiss Institute of Bioinformatics Semantic Web of data","volume":"52","author":"SIB Swiss Institute of Bioinformatics RDF Group Members","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026092206060846600_bib30","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1145\/2660517.2660523","article-title":"Shape expressions: an RDF validation and transformation language","volume-title":"Proceedings of the 10th International Conference on Semantic Systems","author":"Prud\u2019hommeaux","year":"2014"},{"key":"2026092206060846600_bib31","doi-asserted-by":"publisher","first-page":"46595","DOI":"10.48550\/arXiv.2306.05685","article-title":"Judging LLM-as-a-judge with MT-Bench and Chatbot Arena","volume":"36","author":"Zheng","year":"2023","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026092206060846600_bib32","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1186\/s12859-015-0564-6","article-title":"An overview of the BioASQ large-scale biomedical semantic indexing and question answering competition","volume":"16","author":"Tsatsaronis","year":"2015","journal-title":"BMC Bioinformatics"},{"key":"2026092206060846600_bib33","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1037\/0033-2909.86.2.420","article-title":"Intraclass correlations: uses in assessing rater reliability","volume":"86","author":"Shrout","year":"1979","journal-title":"Psychol Bull"},{"key":"2026092206060846600_bib34","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.jcm.2016.02.012","article-title":"A guideline of selecting and reporting intraclass correlation coefficients for reliability research","volume":"15","author":"Koo","year":"2016","journal-title":"J Chiropr Med"},{"key":"2026092206060846600_bib35","doi-asserted-by":"publisher","first-page":"353","DOI":"10.3233\/SSW240028","article-title":"Generating SPARQL from natural language using chain-of-thoughts prompting","volume-title":"Proceedings of the 20th International Conference on Semantic Systems (SEMANTiCS 2024), Studies on the Semantic Web","author":"Zahera","year":"2024"},{"key":"2026092206060846600_bib36","doi-asserted-by":"publisher","first-page":"btae075","DOI":"10.1093\/bioinformatics\/btae075","article-title":"GeneGPT: augmenting large language models with domain tools for improved access to biomedical information","volume":"40","author":"Jin","year":"2024","journal-title":"Bioinformatics"},{"key":"2026092206060846600_bib37","doi-asserted-by":"publisher","first-page":"9459","DOI":"10.48550\/arXiv.2005.11401","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026092206060846600_bib38","doi-asserted-by":"publisher","first-page":"160018","DOI":"10.1038\/sdata.2016.18","article-title":"The FAIR Guiding Principles for scientific data management and stewardship","volume":"3","author":"Wilkinson","year":"2016","journal-title":"Sci Data"}],"container-title":["Database"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/database\/article-pdf\/doi\/10.1093\/database\/baag042\/69943124\/baag042.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/database\/article-pdf\/doi\/10.1093\/database\/baag042\/69943124\/baag042.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T10:06:16Z","timestamp":1790071576000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/database\/article\/doi\/10.1093\/database\/baag042\/8741313"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1093\/database\/baag042","relation":{},"ISSN":["1758-0463"],"issn-type":[{"value":"1758-0463","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026]]},"published":{"date-parts":[[2026]]},"article-number":"baag042"}}