Rare variants predict risk of common disease severity  

Illumina Inc. (NASDAQ:ILMN) and collaborators at the Broad Institute of MIT and Harvard improved the prediction power of identifying rare genetic variants that contribute to common disease phenotypes and found that “an individual at the phenotypic extreme and at the greatest risk for severe, early-onset disease is better identified by a few rare penetrant variants than by the collective action of many common variants with weak effects.”

The Science paper authors deployed PrimateAI-3D, a three-dimensional, convolutional neural network trained using common genetic variants identified from 233 species of non-human primates, and after comparing with the human genome, estimated the pathogenicity of rare coding variants in 454,712 participants from the UK Biobank...