Back

DNAscope: High accuracy small variant calling using machine learning

Freed, D. N.; Pan, R.; Chen, H.; Li, Z.; Hu, J.; Aldana, R.

2022-05-22 bioinformatics
10.1101/2022.05.20.492556 bioRxiv
Show 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 GATKs HaplotypeCaller with a machine-learned genotyping model. Benchmarks of DNAscope and DNAseq (Sentieons GATK-matching germline variant calling pipeline) demonstrate that DNAscope achieves superior SNP and insertion/deletion accuracy with reduced computational cost.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.