CAPICE: a computational method for Consequence-Agnostic Pathogenicity Interpretation of Clinical Exome variations

Shuang� Li; K. Joeri van der Velde; Dick de Ridder; Aalt D. J. van Dijk; Dimitrios Soudis; Leslie R. Zwerwer; Patrick Deelen; Dennis Hendriksen; Bart Charbon; Marielle E van Gijn; Kristin M. Abbott; Birgit Sikkema‐Raddatz; Cleo C. van Diemen; Wilhelmina S. Kerstjens‐Frederikse; Richard J. Sinke; Morris A. Swertz

doi:10.1186/s13073-020-00775-w

Genetic & Genomic MedicineGenome MedicineAug 24, 2020

Peer-reviewed journal article

CAPICE: a computational method for Consequence-Agnostic Pathogenicity Interpretation of Clinical Exome variations

Shuang� Li iD, K. Joeri van der Velde iD, Dick de Ridder iD, Aalt D. J. van Dijk iD, Dimitrios Soudis iD, Leslie R. Zwerwer iD, Patrick Deelen iD, Dennis Hendriksen iD, Bart Charbon iD, Marielle E van Gijn iD, Kristin M. Abbott iD, Birgit Sikkema‐Raddatz iD, Cleo C. van Diemen iD, Wilhelmina S. Kerstjens‐Frederikse iD, Richard J. Sinke iD, Morris A. Swertz iD

Abstract

Exome sequencing is now mainstream in clinical practice, however, identification of pathogenic Mendelian variants remains time consuming, partly because limited accuracy of current computational prediction methods leaves much manual classification. Here we introduce CAPICE, a new machine-learning based method for prioritizing pathogenic variants, including SNVs and short InDels, that outperforms best general (CADD, GAVIN) and consequence-type-specific (REVEL, ClinPred) computational prediction methods, for both rare and ultra-rare variants. CAPICE is easily integrated into diagnostic pipelines and is available as free and open source command-line software, file of pre-computed scores, and as a web application with web service API.

PDF DOI