{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T05:31:40Z","timestamp":1778909500433,"version":"3.51.4"},"reference-count":45,"publisher":"Oxford University Press (OUP)","issue":"14","license":[{"start":{"date-parts":[[2022,5,31]],"date-time":"2022-05-31T00:00:00Z","timestamp":1653955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"German Ministry of Research and Education"},{"name":"Bundesministerium f\u00fcr Bildung und Forschung\u2014BMBF","award":["01IS18051A"],"award-info":[{"award-number":["01IS18051A"]}]},{"name":"Bundesministerium f\u00fcr Bildung und Forschung\u2014BMBF","award":["031B0770E"],"award-info":[{"award-number":["031B0770E"]}]},{"name":"Bundesministerium f\u00fcr Bildung und Forschung\u2014BMBF","award":["01IS21010C"],"award-info":[{"award-number":["01IS21010C"]}]},{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Deutsche Forschungsgemeinschaft\u2014DFG","award":["KL 2698\/2-1"],"award-info":[{"award-number":["KL 2698\/2-1"]}]},{"name":"Deutsche Forschungsgemeinschaft\u2014DFG","award":["KL 2698\/5-1"],"award-info":[{"award-number":["KL 2698\/5-1"]}]},{"name":"Carl-Zeiss Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Medical images can provide rich information about diseases and their biology. However, investigating their association with genetic variation requires non-standard methods. We propose transferGWAS, a novel approach to perform genome-wide association studies directly on full medical images. First, we learn semantically meaningful representations of the images based on a transfer learning task, during which a deep neural network is trained on independent but similar data. Then, we perform genetic association tests with these representations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We validate the type I error rates and power of transferGWAS in simulation studies of synthetic images. Then we apply transferGWAS in a genome-wide association study of retinal fundus images from the UK Biobank. This first-of-a-kind GWAS of full imaging data yielded 60 genomic regions associated with retinal fundus images, of which 7 are novel candidate loci for eye-related traits and diseases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Our method is implemented in Python and available at https:\/\/github.com\/mkirchler\/transferGWAS\/.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btac369","type":"journal-article","created":{"date-parts":[[2022,5,31]],"date-time":"2022-05-31T20:42:30Z","timestamp":1654029750000},"page":"3621-3628","source":"Crossref","is-referenced-by-count":40,"title":["transferGWAS: GWAS of images using deep transfer learning"],"prefix":"10.1093","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0616-2740","authenticated-orcid":false,"given":"Matthias","family":"Kirchler","sequence":"first","affiliation":[{"name":"Digital Health\u2014Machine Learning Research Group, Digital Health Center, Hasso Plattner Institute, University of Potsdam , 14482 Potsdam, Germany"},{"name":"Department of Computer Science, TU Kaiserslautern , 67663 Kaiserslautern, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9966-6819","authenticated-orcid":false,"given":"Stefan","family":"Konigorski","sequence":"additional","affiliation":[{"name":"Digital Health\u2014Machine Learning Research Group, Digital Health Center, Hasso Plattner Institute, University of Potsdam , 14482 Potsdam, Germany"},{"name":"Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai , New York, NY 10029, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Norden","sequence":"additional","affiliation":[{"name":"Digital Health & Personalized Medicine Research Group, Digital Health Center, Hasso Plattner Institute, University of Potsdam , 14482 Potsdam, Germany"},{"name":"Department of Anesthesiology and Intensive Care Medicine, Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin , 10117 Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Meltendorf","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering - Mechatronics - Optometry, Beuth University of Applied Sciences Berlin , 13353 Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marius","family":"Kloft","sequence":"additional","affiliation":[{"name":"Department of Computer Science, TU Kaiserslautern , 67663 Kaiserslautern, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claudia","family":"Schurmann","sequence":"additional","affiliation":[{"name":"Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai , New York, NY 10029, USA"},{"name":"Digital Health & Personalized Medicine Research Group, Digital Health Center, Hasso Plattner Institute, University of Potsdam , 14482 Potsdam, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Lippert","sequence":"additional","affiliation":[{"name":"Digital Health\u2014Machine Learning Research Group, Digital Health Center, Hasso Plattner Institute, University of Potsdam , 14482 Potsdam, Germany"},{"name":"Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai , New York, NY 10029, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2022,5,31]]},"reference":[{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1016\/j.ajhg.2014.03.016","article-title":"Maximizing the power of principal-component analysis of correlated phenotypes in genome-wide association studies","volume":"94","author":"Aschard","year":"2014","journal-title":"Am. J. Hum. Genet"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-021-21727-x","article-title":"Joint analysis of expression levels and histological images identifies genes associated with tissue morphology","volume":"12","author":"Ash","year":"2021","journal-title":"Nat. Commun"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.isci.2018.07.001","article-title":"Histopathological image QTL discovery of immune infiltration variants","volume":"5","author":"Barry","year":"2018","journal-title":"iScience"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1007\/s10519-009-9281-0","article-title":"Rank-based inverse normal transformations are increasingly used, but are they merited?","volume":"39","author":"Beasley","year":"2009","journal-title":"Behav. Genet"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1093\/hmg\/ddz294","article-title":"Insights into the genetic basis of retinal detachment","volume":"29","author":"Boutin","year":"2020","journal-title":"Hum. Mol. Genet"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"D1005","DOI":"10.1093\/nar\/gky1120","article-title":"The NHGRI-EBI GWAS catalog of published genome-wide association studies, targeted arrays and summary statistics 2019","volume":"47","author":"Buniello","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41586-018-0579-z","article-title":"The UK Biobank resource with deep phenotyping and genomic data","volume":"562","author":"Bycroft","year":"2018","journal-title":"Nature"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"105","DOI":"10.3389\/fcvm.2020.00105","article-title":"Improving the generalizability of convolutional neural network-based segmentation on CMR images","volume":"7","author":"Chen","year":"2020","journal-title":"Front. Cardiovasc. Med"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"812","DOI":"10.1016\/j.ophtha.2010.08.045","article-title":"Retinal vascular tortuosity, blood pressure, and cardiovascular risk factors","volume":"118","author":"Cheung","year":"2011","journal-title":"Ophthalmology"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1177\/193229680900300315","article-title":"Eyepacs: an adaptable telemedicine system for diabetic retinopathy screening","volume":"3","author":"Cuadros","year":"2009","journal-title":"J. Diabetes Sci. Technol"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1111\/pcmr.12546","article-title":"Oculocutaneous albinism type 1: link between mutations, tyrosinase conformational stability, and enzymatic activity","volume":"30","author":"Dolinska","year":"2017","journal-title":"Pigment Cell Melanoma Res"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1007\/s00439-011-1110-x","article-title":"A global view of the OCA2-HERC2 region and pigmentation","volume":"131","author":"Donnelly","year":"2012","journal-title":"Hum. Genet"},{"key":"2023041405363623600_","first-page":"4829","article-title":"Inverting visual representations with convolutional networks","author":"Dosovitskiy","year":"2016"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"1171","DOI":"10.1038\/ng.3667","article-title":"The genetics of blood pressure regulation and its target organs from association studies in 342,415 individuals","volume":"48","author":"Ehret","year":"2016","journal-title":"Nat. Genet"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1038\/s41586-018-0571-7","article-title":"Genome-wide association studies of brain imaging phenotypes in UK Biobank","volume":"562","author":"Elliott","year":"2018","journal-title":"Nature"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"774","DOI":"10.1016\/j.neuroimage.2012.01.021","article-title":"Freesurfer","volume":"62","author":"Fischl","year":"2012","journal-title":"Neuroimage"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"e1008044","DOI":"10.1371\/journal.pcbi.1008044","article-title":"Machine learning based histology phenotyping to investigate the epidemiologic and genetic basis of adipocyte morphology and cardiometabolic traits","volume":"16","author":"Glastonbury","year":"2020","journal-title":"PLoS Comput. Biol"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1002\/gepi.22336","article-title":"Chances and challenges of machine learning-based disease classification in genetic association studies illustrated on age-related macular degeneration","volume":"44","author":"Guenther","year":"2020","journal-title":"Genet. Epidemiol"},{"key":"2023041405363623600_","article-title":"End-to-end training of deep probabilistic CCA on paired biomedical observations","author":"Gundersen","year":"2020"},{"key":"2023041405363623600_","first-page":"770","author":"He","year":"2016"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"207","DOI":"10.2337\/db18-0708","article-title":"Genome-wide and abdominal MRI data provide evidence that a genetically determined favorable adiposity phenotype is characterized by lower ectopic liver fat and lower risk of type 2 diabetes, heart disease, and hypertension","volume":"68","author":"Ji","year":"2019","journal-title":"Diabetes"},{"key":"2023041405363623600_","first-page":"8110","author":"Karras","year":"2020"},{"key":"2023041405363623600_","author":"Kingma","year":"2014"},{"key":"2023041405363623600_","first-page":"1387","author":"Kirchler","year":"2020"},{"key":"2023041405363623600_","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1038\/nmeth.1681","article-title":"Fast linear mixed models for genome-wide association studies","volume":"8","author":"Lippert","year":"2011","journal-title":"Nat. Methods"},{"key":"2023041405363623600_","author":"Lippert","year":"2014"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1038\/nmeth.2037","article-title":"Improved linear mixed models for genome-wide association studies","volume":"9","author":"Listgarten","year":"2012","journal-title":"Nat. Methods"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1038\/ng.3190","article-title":"Efficient Bayesian mixed-model analysis increases association power in large cohorts","volume":"47","author":"Loh","year":"2015","journal-title":"Nat. Genet"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"906","DOI":"10.1038\/s41588-018-0144-6","article-title":"Mixed-model association for Biobank-scale datasets","volume":"50","author":"Loh","year":"2018","journal-title":"Nat. Genet"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1038\/nature08494","article-title":"Finding the missing heritability of complex diseases","volume":"461","author":"Manolio","year":"2009","journal-title":"Nature"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"e25489","DOI":"10.1371\/journal.pone.0025489","article-title":"Foxf2: a novel locus for anterior segment dysgenesis adjacent to the foxc1 gene","volume":"6","author":"McKeone","year":"2011","journal-title":"PLoS One"},{"key":"2023041405363623600_","first-page":"8026","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","article-title":"Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning","volume":"2","author":"Poplin","year":"2018","journal-title":"Nat. Biomed. Eng"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"1624","DOI":"10.1038\/s41588-019-0511-y","article-title":"Genetic architecture of subcortical brain structures in 38,851 individuals","volume":"51","author":"Satizabal","year":"2019","journal-title":"Nat. Genet"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"675","DOI":"10.3389\/fonc.2020.00675","article-title":"Generalization vs. specificity: in which cases should a clinic train its own segmentation models?","volume":"10","author":"Schreier","year":"2020","journal-title":"Front. Oncol"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1001\/jamaophthalmol.2018.5646","article-title":"Prevalence of foxc1 variants in individuals with a suspected diagnosis of primary congenital glaucoma","volume":"137","author":"Siggs","year":"2019","journal-title":"JAMA Ophthalmol"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1002\/gepi.22188","article-title":"A fully adjusted two-stage procedure for rank-normalization in genetic association studies","volume":"43","author":"Sofer","year":"2019","journal-title":"Genet. Epidemiol"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1038\/s41588-018-0127-7","article-title":"Genome-wide association meta-analysis highlights light-induced signaling as a driver for refractive error","volume":"50","author":"Tedja","year":"2018","journal-title":"Nat. Genet"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"2542","DOI":"10.1161\/ATVBAHA.119.312552","article-title":"Novel genetic locus influencing retinal venular tortuosity is also associated with risk of coronary artery disease","volume":"39","author":"Veluchamy","year":"2019","journal-title":"Arterioscler. Thromb. Vasc. Biol"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1002\/gepi.22111","article-title":"Whole genome association study of brain-wide imaging phenotypes: a study of the ping cohort","volume":"42","author":"Wen","year":"2018","journal-title":"Genet. Epidemiol"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"1429","DOI":"10.3233\/JAD-181104","article-title":"Association of cognitive function with amyloid-\u03b2 and tau proteins in the vitreous humor","volume":"68","author":"Wright","year":"2019","journal-title":"J. Alzheimers. Dis"},{"key":"2023041405363623600_","author":"Yosinski","year":"2014"},{"key":"2023041405363623600_","first-page":"818","volume-title":"European Conference on Computer Vision","author":"Zeiler","year":"2014"},{"key":"2023041405363623600_","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1038\/nmeth.2848","article-title":"Efficient multivariate linear mixed model algorithms for genome-wide association studies","volume":"11","author":"Zhou","year":"2014","journal-title":"Nat. Methods"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac369\/43992656\/btac369.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/14\/3621\/49883992\/btac369.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/14\/3621\/49883992\/btac369.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,22]],"date-time":"2023-11-22T08:38:20Z","timestamp":1700642300000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/14\/3621\/6596043"}},"subtitle":[],"editor":[{"given":"Russell","family":"Schwartz","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2022,5,31]]},"references-count":45,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2022,7,11]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac369","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2021.10.22.465430","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,7,15]]},"published":{"date-parts":[[2022,5,31]]}}}