Journal Article

MVP predicts the pathogenicity of missense variants by deep learning

Long, John J., Qi, Hongjian, Chen, Chen, Chung, Wendy K., Zhao, Yige, Shen, Yufeng, Zhang, Haicang, Guan, Yongtao

2021

Overview

Accurate pathogenicity prediction of missense variants is critically important in genetic studies and clinical diagnosis. Previously published prediction methods have facilitated the interpretation of missense variants but have limited performance. Here, we describe MVP (Missense Variant Pathogenicity prediction), a new prediction method that uses deep residual network to leverage large training data sets and many correlated predictors. We train the model separately in genes that are intolerant of loss of function variants and the ones that are tolerant in order to take account of potentially different genetic effect size and mode of action. We compile cancer mutation hotspots and de novo variants from developmental disorders for benchmarking. Overall, MVP achieves better performance in prioritizing pathogenic missense variants than previous methods, especially in genes tolerant of loss of function variants. Finally, using MVP, we estimate that de novo coding variants contribute to 7.8% of isolated congenital heart disease, nearly doubling previous estimates. Accurate prediction of variant pathogenicity is essential to understanding genetic risks in disease. Here, the authors present a deep neural network method for prediction of missense variant pathogenicity, MVP, and demonstrate its utility in prioritizing de novo variants contributing to developmental disorders.

• Publisher: Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
• Subject: 45 / 45/23 / 631/114/1305 / 631/114/2184 / 631/208/514/2184 / 631/208/737 / Algorithms / Artificial neural networks / Autism Spectrum Disorder - diagnosis / Autism Spectrum Disorder - genetics / Cancer / Cardiovascular disease / Cardiovascular diseases / Computational Biology - methods / Congenital diseases / Coronary artery disease / Datasets / Deep Learning / Developmental disabilities / Disorders / Drug dosages / Genes / Genetic Predisposition to Disease - genetics / Heart Defects, Congenital - diagnosis / Heart Defects, Congenital - genetics / Heart diseases / Humanities and Social Sciences / Humans / Machine learning / Mode of action / multidisciplinary / Mutation / Mutation hot spots / Mutation, Missense / Neoplasms - diagnosis / Neoplasms - genetics / Neural networks / Pathogenicity / Pathogens / Pediatrics / Predictions / Proteins / Reproducibility of Results / Science / Science (multidisciplinary) / Sensitivity and Specificity