DNAscope: High accuracy small variant calling using machine learning

Abstract

Abstract We present DNAscope, an accurate and efficient germline small-variant caller. DNAscope combines the robust and well-established preprocessing and assembly mathematics of the GATK’s HaplotypeCaller with a machine-learned genotyping model. Benchmarks of DNAscope and DNAseq (Sentieon’s GATK-matching germline variant calling pipeline) demonstrate that DNAscope achieves superior SNP and insertion/deletion accuracy with reduced computational cost.