{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:19:06Z","timestamp":1792790346488,"version":"4.5.0"},"posted":{"date-parts":[[2026,8,22]]},"group-title":"Bioinformatics","reference-count":47,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T00:00:00Z","timestamp":1787356800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Advanced Research Projects Agency for Health","id":[{"id":"https:\/\/ror.org\/01r532x50","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,10,9]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:p>\n                  Existing general-purpose biomedical knowledge graphs tend to focus on disease mechanisms and drug repurposing, leaving multiomic and wellness-relevant content underrepresented. KRAKEN (Knowledge Research &amp; Analysis Kit for Evidence Networks) addresses this gap by integrating existing graphs (including Translator KG Open, RTX-KG2, and ROBOKOP) with specialized sources such as RefMet, LIPID MAPS, NIH Common Data Elements, Polygenic Score Catalog, and derived wellness measures including biological age and biological BMI. The resulting graph spans \u223c26M nodes and \u223c121M edges across 62 entity types. KRAKEN adopts the Biolink Model as its semantic layer, ensuring compatibility with standardized resources emerging from the NIH NCATS Biomedical Data Translator program. A lightweight, modular build system rebuilds the full graph (including entity resolution), with peak memory consumption &lt;48 GB, and supports flexible inclusion or exclusion of sources, allowing the user to scope the graph to a domain of interest. Built-in analytical tools include multi-hop reasoning, subgraph extraction, text, vector and hybrid entity search, and enrichment analyses, all accessible through an interactive web interface, a REST API, and a Model Context Protocol server, the last enabling direct consumption by agentic and LLM-based systems. KRAKEN is freely available at\n                  <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/app.krakenkg.com\">https:\/\/app.krakenkg.com<\/jats:ext-link>\n                  .\n                <\/jats:p>\n                <jats:sec>\n                  <jats:title>GRAPHICAL ABSTRACT<\/jats:title>\n                  <jats:fig id=\"ufig1\" position=\"float\" orientation=\"portrait\" fig-type=\"figure\">\n                    <jats:graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"745544v2_ufig1\" position=\"float\" orientation=\"portrait\"\/>\n                  <\/jats:fig>\n                <\/jats:sec>","DOI":"10.64898\/2026.08.18.745544","type":"posted-content","created":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T06:30:20Z","timestamp":1787466620000},"source":"Crossref","is-referenced-by-count":0,"title":["KRAKEN: A provenance-tracked knowledge graph for multiomic and wellness research"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3691-2290","authenticated-orcid":false,"given":"Amy K.","family":"Glen","sequence":"first","affiliation":[{"name":"Phenome Health, Seattle, WA, 98121, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Drew","family":"Witherington","sequence":"additional","affiliation":[{"name":"Phenome Health, Seattle, WA, 98121, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8188-2028","authenticated-orcid":false,"given":"Trent","family":"Leslie","sequence":"additional","affiliation":[{"name":"Phenome Health, Seattle, WA, 98121, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8463-1219","authenticated-orcid":false,"given":"Andrew","family":"Baumgartner","sequence":"additional","affiliation":[{"name":"Phenome Health, Seattle, WA, 98121, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0667-2345","authenticated-orcid":false,"given":"Ashen","family":"Fernando","sequence":"additional","affiliation":[{"name":"Phenome Health, Seattle, WA, 98121, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7031-8116","authenticated-orcid":false,"given":"Bhargav","family":"Vemuri","sequence":"additional","affiliation":[{"name":"Phenome Health, Seattle, WA, 98121, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5836-6724","authenticated-orcid":false,"given":"Ornit","family":"Nahman","sequence":"additional","affiliation":[{"name":"Buck Institute for Research on Aging, Novato, CA, 94945, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8060-5955","authenticated-orcid":false,"given":"Gw\u00eanlyn","family":"Glusman","sequence":"additional","affiliation":[{"name":"Phenome Health, Seattle, WA, 98121, USA"},{"name":"Institute for Systems Biology, Seattle, WA, 98109, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7158-3678","authenticated-orcid":false,"given":"Leroy","family":"Hood","sequence":"additional","affiliation":[{"name":"Phenome Health, Seattle, WA, 98121, USA"},{"name":"Institute for Systems Biology, Seattle, WA, 98109, USA"},{"name":"Buck Institute for Research on Aging, Novato, CA, 94945, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2237-5674","authenticated-orcid":false,"given":"Lance","family":"Pflieger","sequence":"additional","affiliation":[{"name":"Phenome Health, Seattle, WA, 98121, USA"},{"name":"Institute for Systems Biology, Seattle, WA, 98109, USA"},{"name":"Buck Institute for Research on Aging, Novato, CA, 94945, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8643-2055","authenticated-orcid":false,"given":"Noa","family":"Rappaport","sequence":"additional","affiliation":[{"name":"Phenome Health, Seattle, WA, 98121, USA"},{"name":"Institute for Systems Biology, Seattle, WA, 98109, USA"},{"name":"Buck Institute for Research on Aging, Novato, CA, 94945, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026101409001551000_2026.08.18.745544v2.1","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.26726"},{"key":"2026101409001551000_2026.08.18.745544v2.2","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/s41597-023-01960-3","article-title":"Building a knowledge graph to enable precision medicine","volume":"10","year":"2023","journal-title":"Sci. Data"},{"key":"2026101409001551000_2026.08.18.745544v2.3","doi-asserted-by":"crossref","unstructured":"Morris, J.H. , Soman, K. , Akbas, R.E. , et al. (2023) The scalable precision medicine open knowledge engine (SPOKE): a massive knowledge graph of biomedical information. Bioinformatics, 39, btad080.","DOI":"10.1093\/bioinformatics\/btad080"},{"key":"2026101409001551000_2026.08.18.745544v2.4","doi-asserted-by":"crossref","first-page":"e70284","DOI":"10.1111\/cts.70284","article-title":"Announcing the Biomedical Data Translator: Initial Public Release","volume":"18","year":"2025","journal-title":"Clin. Transl. Sci"},{"key":"2026101409001551000_2026.08.18.745544v2.5","doi-asserted-by":"publisher","DOI":"10.1111\/CTS.13302"},{"key":"2026101409001551000_2026.08.18.745544v2.6","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-022-04932-3"},{"key":"2026101409001551000_2026.08.18.745544v2.7","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-026-53036-y"},{"key":"2026101409001551000_2026.08.18.745544v2.8","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.3870"},{"key":"2026101409001551000_2026.08.18.745544v2.9","doi-asserted-by":"crossref","first-page":"3191","DOI":"10.1038\/s41591-025-03790-9","article-title":"Deep phenotyping of health-disease continuum in the Human Phenotype Project","volume":"31","year":"2025","journal-title":"Nat. Med"},{"key":"2026101409001551000_2026.08.18.745544v2.10","doi-asserted-by":"crossref","unstructured":"Nguyen, Q.-H. , Nguyen, H. , Oh, E.C. , et al. (2024) Current approaches and outstanding challenges of functional annotation of metabolites: a comprehensive review. Brief. Bioinform., 25, bbae498.","DOI":"10.1093\/bib\/bbae498"},{"key":"2026101409001551000_2026.08.18.745544v2.11","first-page":"103","article-title":"Good practices and recommendations for using and benchmarking computational metabolomics metabolite annotation tools","volume":"18","year":"2022","journal-title":"Metabolomics Off. J. Metabolomic Soc"},{"key":"2026101409001551000_2026.08.18.745544v2.12","doi-asserted-by":"crossref","unstructured":"Earls, J.C. , Rappaport, N. , Heath, L ., et al. (2019) Multi-Omic Biological Age Estimation and Its Correlation With Wellness and Disease Phenotypes: A Longitudinal Study of 3, 558 Individuals. J. Gerontol. A. Biol. Sci. Med. Sci., 74, S52\u2013S60.","DOI":"10.1093\/gerona\/glz220"},{"key":"2026101409001551000_2026.08.18.745544v2.13","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02248-0"},{"key":"2026101409001551000_2026.08.18.745544v2.14","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-021-01145-6"},{"key":"2026101409001551000_2026.08.18.745544v2.15","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-023-01848-y"},{"key":"2026101409001551000_2026.08.18.745544v2.16","doi-asserted-by":"crossref","unstructured":"Caufield, J.H. , Putman, T. , Schaper, K. , et al. (2023) KG-Hub-building and exchanging biological knowledge graphs. Bioinformatics, 39, btad418.","DOI":"10.1093\/bioinformatics\/btad418"},{"key":"2026101409001551000_2026.08.18.745544v2.17","doi-asserted-by":"publisher","DOI":"10.2196\/70176"},{"key":"2026101409001551000_2026.08.18.745544v2.18","doi-asserted-by":"crossref","first-page":"5778","DOI":"10.1038\/s41467-026-71411-1","article-title":"Hyper-RAG: combating LLM hallucinations using hypergraph-driven retrieval-augmented generation","volume":"17","year":"2026","journal-title":"Nat. Commun"},{"key":"2026101409001551000_2026.08.18.745544v2.19","doi-asserted-by":"crossref","unstructured":"Soman, K. , Rose, P.W. , Morris, J.H. , et al. (2024) Biomedical knowledge graph-optimized prompt generation for large language models. Bioinformatics, 40, btae560.","DOI":"10.1093\/bioinformatics\/btae560"},{"key":"2026101409001551000_2026.08.18.745544v2.20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2510.20345"},{"key":"2026101409001551000_2026.08.18.745544v2.21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.16130"},{"key":"2026101409001551000_2026.08.18.745544v2.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01009-y"},{"key":"2026101409001551000_2026.08.18.745544v2.23","first-page":"D1677","article-title":"LIPID MAPS: update to databases and tools for the lipidomics community","volume":"52","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2026101409001551000_2026.08.18.745544v2.24","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-024-01937-x"},{"key":"2026101409001551000_2026.08.18.745544v2.25","doi-asserted-by":"publisher","DOI":"10.1373\/49.4.624"},{"key":"2026101409001551000_2026.08.18.745544v2.26","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkh061"},{"key":"2026101409001551000_2026.08.18.745544v2.27","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gku1055"},{"key":"2026101409001551000_2026.08.18.745544v2.28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2022.01.014"},{"key":"2026101409001551000_2026.08.18.745544v2.29","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-37653-z"},{"key":"2026101409001551000_2026.08.18.745544v2.30","doi-asserted-by":"crossref","first-page":"100352","DOI":"10.1016\/j.envadv.2023.100352","article-title":"Identifying environmental risk factors for post-acute sequelae of SARS-CoV-2 infection: An EHR-based cohort study from the recover program","volume":"11","year":"2023","journal-title":"Environ. Adv"},{"key":"2026101409001551000_2026.08.18.745544v2.31","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.8823"},{"key":"2026101409001551000_2026.08.18.745544v2.32","doi-asserted-by":"crossref","unstructured":"Goetz, S.L. , Glen, A.K. and Glusman, G . (2025) MicrobiomeKG: bridging microbiome research and host health through knowledge graphs. Front . Syst. Biol., 5.","DOI":"10.3389\/fsysb.2025.1544432"},{"key":"2026101409001551000_2026.08.18.745544v2.33","doi-asserted-by":"publisher","DOI":"10.1101\/2024.11.14.623648"},{"key":"2026101409001551000_2026.08.18.745544v2.34","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkab1062"},{"key":"2026101409001551000_2026.08.18.745544v2.35","doi-asserted-by":"crossref","unstructured":"The Gene Ontology knowledgebase in 2026 (2025) Nucleic Acids Res., 54, D1779\u2013D1792.","DOI":"10.1093\/nar\/gkag678"},{"key":"2026101409001551000_2026.08.18.745544v2.36","doi-asserted-by":"crossref","unstructured":"Grissa, D. , Junge, A. , Oprea, T.I. , et al. (2022) Diseases 2.0: a weekly updated database of disease-gene associations from text mining and data integration. Database J. Biol. Databases Curation, 2022, baac019.","DOI":"10.1093\/database\/baac019"},{"key":"2026101409001551000_2026.08.18.745544v2.37","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1186\/2041-1480-5-21","article-title":"Unification of multi-species vertebrate anatomy ontologies for comparative biology in Uberon","volume":"5","year":"2014","journal-title":"J. Biomed. Semant"},{"key":"2026101409001551000_2026.08.18.745544v2.38","doi-asserted-by":"publisher","DOI":"10.1126\/science.7678183"},{"key":"2026101409001551000_2026.08.18.745544v2.39","doi-asserted-by":"publisher","DOI":"10.1172\/JCI200319246"},{"key":"2026101409001551000_2026.08.18.745544v2.40","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-018-0121-0"},{"key":"2026101409001551000_2026.08.18.745544v2.41","doi-asserted-by":"publisher","DOI":"10.1016\/j.taap.2004.10.005"},{"key":"2026101409001551000_2026.08.18.745544v2.42","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.1200\/JCO.2011.38.0410","article-title":"Results of a pivotal phase II study of brentuximab vedotin for patients with relapsed or refractory Hodgkin\u2019s lymphoma","volume":"30","year":"2012","journal-title":"J. Clin. Oncol. Off. J. Am. Soc. Clin. Oncol"},{"key":"2026101409001551000_2026.08.18.745544v2.43","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-14144-8"},{"key":"2026101409001551000_2026.08.18.745544v2.44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaci.2006.07.014"},{"key":"2026101409001551000_2026.08.18.745544v2.45","doi-asserted-by":"publisher","DOI":"10.1002\/eji.200839004"},{"key":"2026101409001551000_2026.08.18.745544v2.46","first-page":"297","article-title":"Soluble CD30 serum levels in atopic dermatitis and bronchial asthma and its relationship with disease severity in pediatric age","volume":"17","year":"2006","journal-title":"Pediatr. Allergy Immunol. Off. Publ. Eur. Soc. Pediatr. Allergy Immunol"},{"key":"2026101409001551000_2026.08.18.745544v2.47","first-page":"e106","article-title":"Association of serum-soluble CD26 and CD30 levels with asthma, lung function and bronchial hyper-responsiveness at school age","volume":"100","year":"2011","journal-title":"Acta Paediatr"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.08.18.745544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:00:35Z","timestamp":1791993635000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.08.18.745544"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,22]]},"references-count":47,"URL":"https:\/\/doi.org\/10.64898\/2026.08.18.745544","relation":{},"subject":[],"published":{"date-parts":[[2026,8,22]]},"subtype":"preprint"}}