{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:13:00Z","timestamp":1772223180983,"version":"3.50.1"},"reference-count":15,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T00:00:00Z","timestamp":1749513600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["204979\/Z\/16\/Z"],"award-info":[{"award-number":["204979\/Z\/16\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Genome-wide association studies (GWAS) have successfully uncovered numerous associations between genetic variants and disease traits to date. Yet, identifying significantly associated loci remains a considerable challenge due to the concomitant multiple-testing burden of performing such analyses genome-wide. Here, we leverage the genetic associations of molecular traits \u2013 DNA CpG-site methylation status and RNA expression \u2013 to mitigate this problem. We encode their co-association across the genome using PinSage, a graph convolutional neural network-based recommender system previously deployed at Pinterest. We demonstrate, using this framework, that a model trained only on methylation quantitative trait locus (QTL) data could recapitulate over half (554,209\/1,021,052) of possible SNP-RNA associations identified in a large expression QTL meta-analysis. Taking advantage of a recent \u2018saturated\u2019 map of height associations, we then show that height-associated loci predicted by a model trained on molecular-QTL data replicated comparably, following Bonferroni correction, to those that were genome-wide significant in UK Biobank (88% compared to 91%). On a set of 64 disease outcomes in UK Biobank, the same model identified 143 independent novel disease associations, with at least one additional association for 64% (41\/64) of the disease outcomes examined. Excluding associations involving the MHC region, we achieve a total uplift of over 8% (128\/1,548). We successfully replicated 38% (39\/103) of the novel disease associations in an independent sample, with suggestive evidence for six additional associations from GWAS Catalog. Replicated associations included for instance that between rs10774625 (nearest gene: SH2B3\/ATXN2) and coeliac disease, and that between rs12350420 (nearest gene: MVB12B) and glaucoma. For many GWAS, attaining such an enhancement by simply increasing sample size may be prohibitively expensive, or impossible depending on disease prevalence.<\/jats:p>","DOI":"10.1371\/journal.pone.0324183","type":"journal-article","created":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T13:38:36Z","timestamp":1749562716000},"page":"e0324183","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging molecular-QTL co-association to predict novel disease-associated genetic loci using a graph convolutional neural network"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9250-0648","authenticated-orcid":true,"given":"Julian","family":"Ng-Kee-Kwong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9258-3140","authenticated-orcid":true,"given":"Andrew D.","family":"Bretherick","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,6,10]]},"reference":[{"key":"pone.0324183.ref001","unstructured":"Hamilton W, Ying R, Leskovec J. Representation learning on graphs: methods and applications. arXiv, preprint, 2018. https:\/\/arxiv.org\/abs\/1709.05584"},{"key":"pone.0324183.ref002","unstructured":"Kipf T, Welling M. Semi-supervised classification with graph convolutional networks. arXiv, preprint, 2017. https:\/\/arxiv.org\/abs\/1609.02907"},{"key":"pone.0324183.ref003","unstructured":"Wang M, Zheng D, Ye Z, Gan Q, Li M, Song X, et al. Deep graph library: a graph-centric, highly-performant package for graph neural networks. arXiv, preprint, 2020. https:\/\/arxiv.org\/abs\/1909.01315"},{"key":"pone.0324183.ref004","doi-asserted-by":"crossref","unstructured":"Ying R, He R, Chen K, Eksombatchai P, Hamilton W, Leskovec J. Graph convolutional neural networks for web-scale recommender systems. arXiv, preprint, 2018. doi: 10.48550\/arXiv.1806.01973","DOI":"10.1145\/3219819.3219890"},{"issue":"9","key":"pone.0324183.ref005","doi-asserted-by":"crossref","first-page":"1300","DOI":"10.1038\/s41588-021-00913-z","article-title":"Large-scale cis- and trans-eQTL analyses identify thousands of genetic loci and polygenic scores that regulate blood gene expression","volume":"53","author":"U V\u00f5sa","year":"2021","journal-title":"Nat Genet"},{"issue":"7933","key":"pone.0324183.ref006","doi-asserted-by":"crossref","first-page":"704","DOI":"10.1038\/s41586-022-05275-y","article-title":"A saturated map of common genetic variants associated with human height","volume":"610","author":"L Yengo","year":"2022","journal-title":"Nature"},{"issue":"7944","key":"pone.0324183.ref007","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1038\/s41586-022-05473-8","article-title":"FinnGen provides genetic insights from a well-phenotyped isolated population","volume":"613","author":"MI Kurki","year":"2023","journal-title":"Nature"},{"issue":"8","key":"pone.0324183.ref008","doi-asserted-by":"crossref","first-page":"856","DOI":"10.1038\/ng.3314","article-title":"The support of human genetic evidence for approved drug indications","volume":"47","author":"MR Nelson","year":"2015","journal-title":"Nat Genet"},{"issue":"12","key":"pone.0324183.ref009","doi-asserted-by":"crossref","first-page":"3343","DOI":"10.1093\/hmg\/ddu050","article-title":"A genome-wide association study of intra-ocular pressure suggests a novel association in the gene FAM125B in the TwinsUK cohort","volume":"23","author":"International Glaucoma Genetics Consortium","year":"2014","journal-title":"Hum Mol Genet"},{"key":"pone.0324183.ref010","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkac1010","article-title":"The NHGRI-EBI GWAS catalog: knowledgebase and deposition resource","volume":"51","author":"E Sollis","year":"2023","journal-title":"Nucleic Acids Res"},{"issue":"9","key":"pone.0324183.ref011","doi-asserted-by":"crossref","first-page":"1311","DOI":"10.1038\/s41588-021-00923-x","article-title":"Genomic and phenotypic insights from an atlas of genetic effects on DNA methylation","volume":"53","author":"JL Min","year":"2021","journal-title":"Nat Genet"},{"issue":"11","key":"pone.0324183.ref012","doi-asserted-by":"crossref","first-page":"1593","DOI":"10.1038\/s41588-018-0248-z","article-title":"An atlas of genetic associations in UK Biobank","volume":"50","author":"O Canela-Xandri","year":"2018","journal-title":"Nat Genet"},{"issue":"7571","key":"pone.0324183.ref013","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1038\/nature15393","article-title":"A global reference for human genetic variation","volume":"526","author":"1000 Genomes Project Consortium","year":"2015","journal-title":"Nature"},{"key":"pone.0324183.ref014","unstructured":"Peixoto TP. The graph-tool python library. figshare. Available from: 2014. doi: 10.6084\/m9.figshare.1164194"},{"key":"pone.0324183.ref015","unstructured":"Genome Reference Consortium. Human genome region MHC. 2023. Available from: https:\/\/www.ncbi.nlm.nih.gov\/grc\/human\/regions\/MHC?asm=GRCh37"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0324183","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T13:38:41Z","timestamp":1749562721000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0324183"}},"subtitle":[],"editor":[{"given":"Xiang","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,10]]},"references-count":15,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,10]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0324183","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.03.04.24303678","asserted-by":"object"}]},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,10]]}}}