DNAscope: High accuracy small variant calling using machine learning

Donald Freed; Renke Pan; Haodong Chen; Zhipan Li; Jinnan Hu; Rafael Aldana

doi:10.1101/2022.05.20.492556

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.

Competing Interest Statement

D.F., H.C., Z.L., J.H. and R.A. are current employees of Sentieon, Inc., and hold stock options as part of the standard compensation package. R.P. is former employee of Sentieon.

The copyright holder for this preprint is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY 4.0 International license.