Predicting expression-altering promoter mutations with deep learning
Kishore Jaganathan, Nicole M. Ferraro, Gherman Novakovsky, Yuchuan Wang, Terena James, Jeremy Schwartzentruber, Petko Fiziev, Irfahan Kassam, Fan Cao, Johann S. Hawe, Henry Cavanagh, Ashley J. W. Lim, Grace Png, Jeremy F. McRae, Abhimanyu Banerjee, Arvind Kumar, Jacob C. Ulirsch, Yan Zhang, François Aguet, Pierrick Wainschtein, Laksshman Sundaram, Adriana Salcedo, Sofia Kyriazopoulou Panagiotopoulou, Delasa Aghamirzaie, Evin M. Padhi, Ziming Weng, Shan Dong, Damian Smedley, Mark J. Caulfield, Anne O’Donnell‐Luria, Heidi L. Rehm, Stephan Sanders, Anshul Kundaje, Stephen B. Montgomery, Mark T. Ross, Kyle Kai‐How Farh
Abstract
Only a minority of patients with rare genetic diseases are presently diagnosed by exome sequencing, suggesting that additional unrecognized pathogenic variants may reside in noncoding sequence. In this work, we describe PromoterAI, a deep neural network that accurately identifies noncoding promoter variants that dysregulate gene expression. We show that promoter variants with predicted expression-altering consequences produce outlier expression at both the RNA and protein levels in thousands of individuals and that these variants experience strong negative selection in human populations. We observed that clinically relevant genes in patients with rare diseases are enriched for such variants and validated their functional impact through reporter assays. Our estimates suggest that promoter variation accounts for 6% of the genetic burden associated with rare diseases.