MVP: predicting pathogenicity of missense variants by deep learning

Abstract

Accurate pathogenicity prediction of missense variants is critical to improve power in genetic studies and accurate interpretation in clinical genetic testing. Here we describe a new prediction method, MVP, which uses a deep learning approach to leverage large training data sets and many correlated predictors. Using cancer mutation hotspots and de novo germline mutations from developmental disorders for benchmarking, MVP achieved better performance in prioritizing pathogenic missense variants than previous methods.