Unsupervised representation learning improves genomic discovery and risk prediction for respiratory and circulatory functions and diseases
Taedong Yun, Justin Cosentino, Babak Behsaz, Zachary Ryan McCaw, Davin Hill, Robert Luben, Dongbing Lai, John Bates, Howard Hua Yang, Tae-Hwi Linus Schwantes-An, Yuchen Zhou, Anthony P. Khawaja, Andrew W. Carroll, Brian D. Hobbs, Michael H. Cho, , Farhad Hormozdiari
This paper introduces a deep learning framework, REGLE, that improves genomic discovery and risk prediction for respiratory and circulatory diseases by learning low-dimensional embeddings from high-dimensional clinical data.
Nature Genetics · Jul 8, 2024Peer-reviewedGenetic & Genomic Medicine