Rapid and accurate multi-phenotype imputation for millions of individuals

Rapid and accurate multi-phenotype imputation for millions of individuals | 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 Technical Report Rapid and accurate multi-phenotype imputation for millions of individuals Ming Fang, Lin-Lin Gu, Hong-Shan Wu, Yong-Jie Zhang, Tian-Yi Liu, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3406520/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 04 Jan, 2025 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Abstract Deep phenotyping can enhance the power of genetic analysis such as genome-wide association study (GWAS), but recurrence of missing phenotypes compromises the potentials of such resources. Although many phenotypic imputation methods have been developed, accurate imputation for millions of individuals still remains extremely challenging. In the present study, leveraging efficient machine learning (ML)-based algorithms, we developed a novel multi-phenotype imputation method based on mixed fast random forest (PIXANT), which is several orders of magnitude in runtime and computer memory usage than the state-of-the-art methods when applied to the UK Biobank (UKB) data and scalable to cohorts with millions of individuals. Our simulations with hundreds of individuals showed that PIXANT was superior to or comparable to the most advanced methods available in terms of accuracy. We also applied PIXANT to impute 425 phenotypes for the UKB data of 277,301 unrelated white British citizens and performed GWAS on imputed phenotypes, and identified a 15.6% more GWAS loci than before imputation (8,710 vs 7,355). Due to the increased statistical power of GWAS, a certain proportion of novel genes were rediscovered, such as RNF220 , SCN10A and RGS6 that affect heart rate, demonstrating the use of imputed phenotype data in a large cohort to discover novel genes for complex traits. Biological sciences/Computational biology and bioinformatics/Software Biological sciences/Genetics/Genetic association study/Genome-wide association studies phenotype imputation machine learning UK Biobank non linear effect Full Text Additional Declarations There is NO Competing Interest. Supplementary Files Table.pdf Supplementary Tables Cite Share Download PDF Status: Published Journal Publication published 04 Jan, 2025 Read the published version in Nature Communications → 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-3406520","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Technical Report","associatedPublications":[],"authors":[{"id":239326135,"identity":"e5935caf-d40f-4c94-89b5-cbd0268e45f1","order_by":0,"name":"Ming Fang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIie3QsQrCMBCA4YNAXAJZ08VnCBQKouirnBQyRXF0FAQ7iPgqbq7VgFO7d3BQBAdxUJwEERvU0bajQ/7hpnwHFwCX6w+rjeyUAJyQ1Q6HrXLC4g/xIhrKXaKqEqvmLPD2k3UFUkvNKRts2wtC1RBpDDyaYjFhfdXU8hguCdlkyLYgknRRSDqgA19LEzbGVGUojiBFr5gwfn4TaVgwQGkqEKH9Q07algBiJXIOSE7QG9NQYKxY6S2Ma/+mH6bDuVld789WnUezYpJHRT66o++Osuc2cgH7cy6Xy+X61Qv5a0nACwS5fgAAAABJRU5ErkJggg==","orcid":"","institution":"Jimei University","correspondingAuthor":true,"prefix":"","firstName":"Ming","middleName":"","lastName":"Fang","suffix":""},{"id":239326136,"identity":"6a9ea7f0-c7eb-4eac-a6df-729c56bed3e8","order_by":1,"name":"Lin-Lin Gu","email":"","orcid":"","institution":"Jimei University","correspondingAuthor":false,"prefix":"","firstName":"Lin-Lin","middleName":"","lastName":"Gu","suffix":""},{"id":239326137,"identity":"172ae929-a879-442b-86c0-d4f24b5e93a4","order_by":2,"name":"Hong-Shan Wu","email":"","orcid":"","institution":"Jimei University","correspondingAuthor":false,"prefix":"","firstName":"Hong-Shan","middleName":"","lastName":"Wu","suffix":""},{"id":239326138,"identity":"b5512ce7-ce41-4c92-8fbf-2adae4fc5b18","order_by":3,"name":"Yong-Jie Zhang","email":"","orcid":"","institution":"Jimei University","correspondingAuthor":false,"prefix":"","firstName":"Yong-Jie","middleName":"","lastName":"Zhang","suffix":""},{"id":239326139,"identity":"10e56178-aced-40d6-8ff6-6660ed846d3e","order_by":4,"name":"Tian-Yi Liu","email":"","orcid":"","institution":"Jimei University","correspondingAuthor":false,"prefix":"","firstName":"Tian-Yi","middleName":"","lastName":"Liu","suffix":""},{"id":239326140,"identity":"27fbcfd0-9bc9-4ef2-b36b-7376b50c490c","order_by":5,"name":"Jing-Cheng He","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Jing-Cheng","middleName":"","lastName":"He","suffix":""},{"id":239326141,"identity":"a1677d96-5f05-49e2-9b5a-666e1fbb9d01","order_by":6,"name":"Xiaolei Liu","email":"","orcid":"","institution":"Key Laboratory of Agricultural Animal Genetics, Breeding and Reproduction, Ministry of Education \u0026 College of Animal Science and Technology, Huazhong Agricultural University, Wuhan","correspondingAuthor":false,"prefix":"","firstName":"Xiaolei","middleName":"","lastName":"Liu","suffix":""},{"id":239326142,"identity":"91b1bfde-05f9-4c70-89c7-b5e521d982c9","order_by":7,"name":"Guo-Bo Chen","email":"","orcid":"","institution":"Zhejiang Provincial People’s Hospital","correspondingAuthor":false,"prefix":"","firstName":"Guo-Bo","middleName":"","lastName":"Chen","suffix":""},{"id":239326143,"identity":"f87083d3-75a7-4952-97c3-27dc8959ac27","order_by":8,"name":"Dan Jiang","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Dan","middleName":"","lastName":"Jiang","suffix":""}],"badges":[],"createdAt":"2023-10-03 05:05:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3406520/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3406520/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41467-024-55496-0","type":"published","date":"2025-01-04T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":72985861,"identity":"7ee18e0e-2b6b-40a7-a89f-7e1cf4fc993f","added_by":"auto","created_at":"2025-01-05 08:05:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1211106,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3406520/v1_covered_d910a452-4c77-4404-8d9d-1a54ea4912f9.pdf"},{"id":47596462,"identity":"c8085733-d04b-457c-9e26-7ceaa8b4a611","added_by":"auto","created_at":"2023-12-05 01:28:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":334181,"visible":true,"origin":"","legend":"Supplementary Tables","description":"","filename":"Table.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3406520/v1/d0a604dc2e6f357c90f09d35.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Rapid and accurate multi-phenotype imputation for millions of individuals","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"phenotype imputation, machine learning, UK Biobank, non linear effect","lastPublishedDoi":"10.21203/rs.3.rs-3406520/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3406520/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDeep phenotyping can enhance the power of genetic analysis such as genome-wide association study (GWAS), but recurrence of missing phenotypes compromises the potentials of such resources. Although many phenotypic imputation methods have been developed, accurate imputation for millions of individuals still remains extremely challenging. In the present study, leveraging efficient machine learning (ML)-based algorithms, we developed a novel multi-phenotype imputation method based on mixed fast random forest (PIXANT), which is several orders of magnitude in runtime and computer memory usage than the state-of-the-art methods when applied to the UK Biobank (UKB) data and scalable to cohorts with millions of individuals. Our simulations with hundreds of individuals showed that PIXANT was superior to or comparable to the most advanced methods available in terms of accuracy. We also applied PIXANT to impute 425 phenotypes for the UKB data of 277,301 unrelated white British citizens and performed GWAS on imputed phenotypes, and identified a 15.6% more GWAS loci than before imputation (8,710 vs 7,355). Due to the increased statistical power of GWAS, a certain proportion of novel genes were rediscovered, such as \u003cem\u003eRNF220\u003c/em\u003e, \u003cem\u003eSCN10A \u003c/em\u003eand \u003cem\u003eRGS6 \u003c/em\u003ethat affect heart rate, demonstrating the use of imputed phenotype data in a large cohort to discover novel genes for complex traits.\u003c/p\u003e","manuscriptTitle":"Rapid and accurate multi-phenotype imputation for millions of individuals","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-12-05 01:28:20","doi":"10.21203/rs.3.rs-3406520/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"8038687e-9ee9-42be-9316-5d66229f6bb8","owner":[],"postedDate":"December 5th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":25305201,"name":"Biological sciences/Computational biology and bioinformatics/Software"},{"id":25305202,"name":"Biological sciences/Genetics/Genetic association study/Genome-wide association studies"}],"tags":[],"updatedAt":"2025-01-05T08:05:49+00:00","versionOfRecord":{"articleIdentity":"rs-3406520","link":"https://doi.org/10.1038/s41467-024-55496-0","journal":{"identity":"nature-communications","isVorOnly":false,"title":"Nature Communications"},"publishedOn":"2025-01-04 05:00:00","publishedOnDateReadable":"January 4th, 2025"},"versionCreatedAt":"2023-12-05 01:28:20","video":"","vorDoi":"10.1038/s41467-024-55496-0","vorDoiUrl":"https://doi.org/10.1038/s41467-024-55496-0","workflowStages":[]},"version":"v1","identity":"rs-3406520","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3406520","identity":"rs-3406520","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}