SV2: accurate structural variation genotyping and de novo mutation detection from whole genomes

Motivation: Structural variation (SV) detection from short-read whole genome sequencing is error prone, presenting significant challenges for population or family-based studies of disease. Results: Here, we describe SV2, a machine-learning algorithm for genotyping deletions and duplications from paired-end sequencing data. SV2 can rapidly integrate variant calls from multiple structural variant discovery algorithms into a unified call set with high genotyping accuracy and capability to detect de novo mutations. Availability and implementation: SV2 is freely available on GitHub (https://github.com/dantaki/SV2). Contact: jsebat@ucsd.edu. Supplementary information: Supplementary data are available at Bioinformatics online.