{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T23:56:27Z","timestamp":1790898987061,"version":"4.1.0"},"reference-count":17,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":30,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Randox Ltd"},{"name":"National Institute for Health and Care Research Exeter Biomedical Research Centre","id":[{"id":"https:\/\/ror.org\/0187kwz08","id-type":"ROR","asserted-by":"crossref"}]},{"name":"NIHR or the Department of Health and Social Care","id":[{"id":"https:\/\/ror.org\/03sbpja79","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Purpose: Genetic risk scores (GRSs) are summaries of genetic data that can improve prediction of disease risk and progression. GRSs are increasing available but rely on high-quality input data to produce good output results; with noisy or missing inputs the GRS may be inaccurate. We aimed to develop a method to produce a robust estimate of the GRS when input data are missing, noisy or both. Approach: We developed a neural network approach, named masked-multi-layer perceptron (MLP), for robust GRS calculation trained on a set of GRS scores calculated on clean data. The masked-MLP includes additional input data and has noise inserted during training, both which make the model more robust. Results: A GRS for type 1 diabetes (T1D) calculated on input data with 10% of the data corrupted had a Spearman rank correlation to the clean GRS of 0.669 (0.665\u20130.674) while the equivalent for the masked-MLP was 0.951 (0.950\u20130.952). For the same data, the area under the receiver operating characteristic curve for separation of T1D from population samples fell from 0.919 (0.904\u20130.932) to 0.808 (0.787\u20130.827) for the GRS while the masked-MLP fell to 0.910 (0.895\u20130.924). Conclusions: The masked-MLP was more robust to noise when calculating a GRS than using standard approaches. Our approach has the potential to enable GRS calculations which are more robust to noise.<\/jats:p>","DOI":"10.1093\/bib\/bbag538","type":"journal-article","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T19:18:36Z","timestamp":1789672716000},"source":"Crossref","is-referenced-by-count":0,"title":["Machine learning methodology using a masked neural network for robust genetic risk score calculation from noisy and missing data"],"prefix":"10.1093","volume":"27","author":[{"given":"Steven","family":"Squires","sequence":"first","affiliation":[{"name":"Clinical and Biomedical Sciences, University of Exeter , Heavitree Road, EX1 2LU Devon,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael N","family":"Weedon","sequence":"additional","affiliation":[{"name":"Clinical and Biomedical Sciences, University of Exeter , Heavitree Road, EX1 2LU Devon,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard A","family":"Oram","sequence":"additional","affiliation":[{"name":"Clinical and Biomedical Sciences, University of Exeter , Heavitree Road, EX1 2LU Devon,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"key":"2026100119441557100_ref1","doi-asserted-by":"publisher","first-page":"e95","DOI":"10.1002\/cphg.95","article-title":"Genetic risk scores","volume":"104","author":"Igo","year":"2019","journal-title":"Curr Protoc Hum Genet"},{"key":"2026100119441557100_ref2","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s13073-020-00742-5","article-title":"Polygenic risk scores: from research tools to clinical instruments","volume":"12","author":"Lewis","year":"2020","journal-title":"Genome Med"},{"key":"2026100119441557100_ref3","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.ajhg.2011.11.029","article-title":"Five years of gwas discovery","volume":"90","author":"Visscher","year":"2012","journal-title":"Am J Hum Genet"},{"key":"2026100119441557100_ref4","doi-asserted-by":"publisher","first-page":"200","DOI":"10.2337\/dc18-1785","article-title":"Development and standardization of an improved type 1 diabetes genetic risk score for use in newborn screening and incident diagnosis","volume":"42","author":"Sharp","year":"2019","journal-title":"Diabetes Care"},{"key":"2026100119441557100_ref5","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1038\/s43856-023-00269-x","article-title":"Deep learning-based polygenic risk analysis for Alzheimer\u2019s disease prediction","volume":"3","author":"Xiaopu Zhou","year":"2023","journal-title":"Commun Med (Lond)"},{"key":"2026100119441557100_ref6","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1086\/519795","article-title":"PLINK: a tool set for whole-genome association and population-based linkage analyses","volume":"81","author":"Purcell","year":"2007","journal-title":"Am J Hum Genet"},{"key":"2026100119441557100_ref7","doi-asserted-by":"crossref","first-page":"vbaf158","DOI":"10.1093\/bioadv\/vbaf158","article-title":"Calculating genetic risk scores directly from summary statistics with an application to type 1 diabetes","volume":"5","author":"Squires","year":"2025","journal-title":"Bioinform Adv"},{"key":"2026100119441557100_ref8","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1002\/gepi.20516","article-title":"Quality control and quality assurance in genotypic data for genome-wide association studies","volume":"34","author":"Laurie","year":"2010","journal-title":"Genet Epidemiol"},{"key":"2026100119441557100_ref9","doi-asserted-by":"crossref","first-page":"1284","DOI":"10.1038\/ng.3656","article-title":"Next-generation genotype imputation service and methods","volume":"48","author":"Das","year":"2016","journal-title":"Nat Genet"},{"key":"2026100119441557100_ref10","doi-asserted-by":"crossref","first-page":"025056","DOI":"10.1088\/2057-1976\/adbb71","article-title":"Exploring the application of deep learning methods for polygenic risk score estimation","volume":"11","author":"Squires","year":"2025","journal-title":"Biomed Phys Eng Express"},{"key":"2026100119441557100_ref11","doi-asserted-by":"crossref","first-page":"e1001779","DOI":"10.1371\/journal.pmed.1001779","article-title":"UK biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age","volume":"12","author":"Sudlow","year":"2015","journal-title":"PLoS Med"},{"key":"2026100119441557100_ref12","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Netw"},{"key":"2026100119441557100_ref13","article-title":"PyTorch: an imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2026100119441557100_ref14","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"2026100119441557100_ref15","doi-asserted-by":"publisher","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":"2026100119441557100_ref16","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1038\/ng.3643","article-title":"A reference panel of 64,976 haplotypes for genotype imputation","volume":"48","author":"S","year":"2016","journal-title":"Nat Genet"},{"key":"2026100119441557100_ref17","doi-asserted-by":"crossref","first-page":"337","DOI":"10.2337\/dc15-1111","article-title":"A type 1 diabetes genetic risk score can aid discrimination between type 1 and type 2 diabetes in young adults","volume":"39","author":"Oram","year":"2016","journal-title":"Diabetes Care"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag538\/71561997\/bbag538.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag538\/71561997\/bbag538.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T23:44:24Z","timestamp":1790898264000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag538\/8859329"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,1]]},"references-count":17,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag538","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,9,1]]},"article-number":"bbag538"}}