Deep structured learning for variant prioritization in Mendelian diseases

Nature Communications, vol. 14, pp. 4167

Abstract

Effective computer-aided or automated variant evaluations for monogenic diseases will expedite clinical diagnostic and research efforts of known and novel disease-causing genes. Here we introduce MAVERICK: a Mendelian Approach to Variant Effect pRedICtion built in Keras. MAVERICK is an ensemble of transformer-based neural networks that can classify a wide range of protein-altering single nucleotide variants (SNVs) and indels and assesses whether a variant would be pathogenic in the context of dominant or recessive inheritance. We demonstrate that MAVERICK outperforms all other major programs that assess pathogenicity in a Mendelian context. In a cohort of 644 previously solved patients with Mendelian diseases, MAVERICK ranks the causative pathogenic variant within the top five variants in over 95% of cases. Seventy-six percent of cases were solved by the top-ranked variant. MAVERICK ranks the causative pathogenic variant in hitherto novel disease genes within the first five candidate variants in 70% of cases. MAVERICK has already facilitated the identification of a novel disease gene causing a degenerative motor neuron disease. These results represent a significant step towards automated identification of causal variants in patients with Mendelian diseases.

Authors 7

1. Matt Christopher Danzi

   University of Miami

   Affiliation as printed

   Dr. John T. Macdonald Foundation Department of Human Genetics and John P. Hussman Institute for Human Genomics, University of Miami Miller School of Medicine, Miami, FL, USA

2. Maike Franziska Dohrn Aachen Department of Neurology, Medical Faculty

   University of Miami · RWTH Aachen University

   Affiliation as printed

   Department of Neurology, Medical Faculty of the RWTH Aachen University, Aachen, Germany

   Dr. John T. Macdonald Foundation Department of Human Genetics and John P. Hussman Institute for Human Genomics, University of Miami Miller School of Medicine, Miami, FL, USA

3. Sarah Fazal

   University of Miami

   Affiliation as printed

   Dr. John T. Macdonald Foundation Department of Human Genetics and John P. Hussman Institute for Human Genomics, University of Miami Miller School of Medicine, Miami, FL, USA

4. Danique Beijer

   University of Miami

   Affiliation as printed

   Dr. John T. Macdonald Foundation Department of Human Genetics and John P. Hussman Institute for Human Genomics, University of Miami Miller School of Medicine, Miami, FL, USA

5. Adriana P. Rebelo

   University of Miami

   Affiliation as printed

   Dr. John T. Macdonald Foundation Department of Human Genetics and John P. Hussman Institute for Human Genomics, University of Miami Miller School of Medicine, Miami, FL, USA

6. Vívian Pedigone Cintra

   University of Miami

   Affiliation as printed

   Dr. John T. Macdonald Foundation Department of Human Genetics and John P. Hussman Institute for Human Genomics, University of Miami Miller School of Medicine, Miami, FL, USA

7. Stephan L. Zuchner corresponding

   University of Miami

   Affiliation as printed

   Dr. John T. Macdonald Foundation Department of Human Genetics and John P. Hussman Institute for Human Genomics, University of Miami Miller School of Medicine, Miami, FL, USA. szuchner@med.miami.edu

   Dr. John T. Macdonald Foundation Department of Human Genetics and John P. Hussman Institute for Human Genomics, University of Miami Miller School of Medicine, Miami, FL, USA