Identification of Insulin Resistance-Related Genes Using Biomedical Knowledge Graphs Topology and Embeddings

Identification of Insulin Resistance-Related Genes Using Biomedical Knowledge Graphs Topology and Embeddings | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Identification of Insulin Resistance-Related Genes Using Biomedical Knowledge Graphs Topology and Embeddings Tankred Ott, Marc Boubnovski Martell, Viktor Sandberg, Ramneek Gupta, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3891412/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background: Knowledge graph (KG) feature engineering approaches, such as calculation of topological features and generation of embeddings, can be applied onto biomedical KGs (biomedKGs) to gain a better understanding of disease biology and identify novel gene-disease associations. However, evaluation of such approaches to study not only disease associations, but complex patho-physiologies, such as insulin resistance (IR), is lacking. In this study we used OpenBioLink and Hetionet biomedKGs to predict IR-related genes using topological feature engineering, link prediction, Elkanoto and outlier detection algorithms. We also evaluated how model performance was affected by the size of the training set and by enriching the biomedKG with IR information. Furthermore, we assessed the biological relation of the predictions to IR-related processes using the DepMap and Multiscale Interactome datasets and bioinformatic pathway functional annotations. Results: We found that models using topological features from both standard and enriched OpenBioLink achieved the best predictive performance, followed closely by Elkanoto using RotatE embeddings from both enriched and standard biomedKGs. Additionally, we found that a larger training set had a better effect on performance than enriching the biomedKGs with IR information. Our biological characterization showed that embeddings can capture the varied IR-related functions and broadly group them into related to cell proliferation and to metabolism. Notably, the enriched functional pathways of the top predicted genes included Chagas disease, which has a debated relation to IR. Conclusions: We comprehensively evaluated methods for identifying genes related to the complex patho-phenotype of IR. Our findings showed that biomedKG embeddings can capture complex biological information related to IR, without strong dependence on the specific schema of the biomedKG. Comparing biologically contextualized results, we found that embedding-based models had better generalization capabilities than the topology-based model, but there was a wide range of performance across the embedding-based models. Therefore, choosing a research approach should balance the need for accurate predictions and the possibility of discovering novel biological insights. Insulin resistance Knowledge graphs Knowledge graph embedding Link prediction Positive unlabelled learning Outlier detection Knowledge graphs feature engineering Knowledge graph topology Machine learning Graph neural networks Full Text Additional Declarations Competing interest reported. The authors declare being part of a pharmaceutical company, Novo Nordisk. Novo Nordisk will not in any way gain or lose financially from the publication of this manuscript, either now or in the future. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-3891412","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":278914771,"identity":"4a14e832-aa11-4637-9a85-cfa12729390e","order_by":0,"name":"Tankred Ott","email":"","orcid":"","institution":"Novo Nordisk (Denmark)","correspondingAuthor":false,"prefix":"","firstName":"Tankred","middleName":"","lastName":"Ott","suffix":""},{"id":278914773,"identity":"df10f876-365d-4c17-901d-f716a9682e14","order_by":1,"name":"Marc Boubnovski Martell","email":"","orcid":"","institution":"Novo Nordisk (United Kingdom)","correspondingAuthor":false,"prefix":"","firstName":"Marc","middleName":"Boubnovski","lastName":"Martell","suffix":""},{"id":278914776,"identity":"12c5775f-97ad-4bae-95b1-b94c1877f243","order_by":2,"name":"Viktor Sandberg","email":"","orcid":"","institution":"Novo Nordisk (Denmark)","correspondingAuthor":false,"prefix":"","firstName":"Viktor","middleName":"","lastName":"Sandberg","suffix":""},{"id":278914778,"identity":"2b430345-e97a-4429-88ee-96fa2274fe7a","order_by":3,"name":"Ramneek Gupta","email":"","orcid":"","institution":"Novo Nordisk (United Kingdom)","correspondingAuthor":false,"prefix":"","firstName":"Ramneek","middleName":"","lastName":"Gupta","suffix":""},{"id":278914780,"identity":"e2987c40-2f7a-4324-9106-61264cfb0210","order_by":4,"name":"Marie Lisandra Zepeda Mendoza","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwUlEQVRIiWNgGAWjYLCCDzAGjwGDAVE6GGeQrIWZB66FgQgtBtfOHv5su8MmsV+6+diHNwV1xgzsh49uwKvldl6Cce6ZtMSZc44lz5xjcNiMgSct7QY+LZKzcwySc9sOGxvcyDFm5jE4YMMgwWNGUMthS4SWOsJa+KVzDJsZ2w7LQbUwmxGjxZixty1NTnJGWjIj0C/GbIT8wgbU8uFnmw0Pv0TyYYY3f+oM+9kPH8OrBYshpCkfBaNgFIyCUYANAAA79EBonyovWAAAAABJRU5ErkJggg==","orcid":"","institution":"Novo Nordisk (United Kingdom)","correspondingAuthor":true,"prefix":"","firstName":"Marie","middleName":"Lisandra Zepeda","lastName":"Mendoza","suffix":""}],"badges":[],"createdAt":"2024-01-23 15:05:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3891412/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3891412/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":79193430,"identity":"a2dede73-a91b-466b-a31d-4cefc1861151","added_by":"auto","created_at":"2025-03-25 13:09:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":8657702,"visible":true,"origin":"","legend":"","description":"","filename":"IRNextGenMLSUBMISSION.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3891412/v1_covered_729043a4-91b5-48e9-a2f5-557bca06348b.pdf"}],"financialInterests":"Competing interest reported. The authors declare being part of a pharmaceutical company, Novo Nordisk. Novo Nordisk will not in any way gain or lose financially from the publication of this manuscript, either now or in the future.","formattedTitle":"Identification of Insulin Resistance-Related Genes Using Biomedical Knowledge Graphs Topology and Embeddings","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Insulin resistance, Knowledge graphs, Knowledge graph embedding, Link prediction, Positive unlabelled learning, Outlier detection, Knowledge graphs feature engineering, Knowledge graph topology, Machine learning, Graph neural networks","lastPublishedDoi":"10.21203/rs.3.rs-3891412/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3891412/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBackground: Knowledge graph (KG) feature engineering approaches, such as calculation of topological features and generation of embeddings, can be applied onto biomedical KGs (biomedKGs) to gain a better understanding of disease biology and identify novel gene-disease associations. However, evaluation of such approaches to study not only disease associations, but complex patho-physiologies, such as insulin resistance (IR), is lacking. In this study we used OpenBioLink and Hetionet biomedKGs to predict IR-related genes using topological feature engineering, link prediction, Elkanoto and outlier detection algorithms. We also evaluated how model performance was affected by the size of the training set and by enriching the biomedKG with IR information. Furthermore, we assessed the biological relation of the predictions to IR-related processes using the DepMap and Multiscale Interactome datasets and bioinformatic pathway functional annotations.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eResults: We found that models using topological features from both standard and enriched OpenBioLink achieved the best predictive performance, followed closely by Elkanoto using RotatE embeddings from both enriched and standard biomedKGs. Additionally, we found that a larger training set had a better effect on performance than enriching the biomedKGs with IR information. Our biological characterization showed that embeddings can capture the varied IR-related functions and broadly group them into related to cell proliferation and to metabolism. Notably, the enriched functional pathways of the top predicted genes included Chagas disease, which has a debated relation to IR.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eConclusions: We comprehensively evaluated methods for identifying genes related to the complex patho-phenotype of IR. Our findings showed that biomedKG embeddings can capture complex biological information related to IR, without strong dependence on the specific schema of the biomedKG. Comparing biologically contextualized results, we found that embedding-based models had better generalization capabilities than the topology-based model, but there was a wide range of performance across the embedding-based models. Therefore, choosing a research approach should balance the need for accurate predictions and the possibility of discovering novel biological insights.\u003c/p\u003e","manuscriptTitle":"Identification of Insulin Resistance-Related Genes Using Biomedical Knowledge Graphs Topology and Embeddings","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-25 13:09:03","doi":"10.21203/rs.3.rs-3891412/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"fd086177-f1fa-43dd-afae-732d5f9c0afd","owner":[],"postedDate":"March 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-03-25T13:09:03+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-25 13:09:03","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3891412","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3891412","identity":"rs-3891412","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}