xAtlas: scalable small variant calling across heterogeneous next-generation sequencing experiments

Abstract

Background: The growing volume and heterogeneity of next-generation sequencing (NGS) data complicate the further optimization of identifying DNA variation, especially considering that curated high-confidence variant call sets frequently used to validate these methods are generally developed from the analysis of comparatively small and homogeneous sample sets.

Findings: We have developed xAtlas, a single-sample variant caller for single-nucleotide variants (SNVs) and small insertions and deletions (indels) in NGS data. xAtlas features rapid runtimes, support for CRAM and gVCF file formats, and retraining capabilities. xAtlas reports SNVs with 99.11% recall and 98.43% precision across a reference HG002 sample at 60× whole-genome coverage in less than 2 CPU hours. Applying xAtlas to 3,202 samples at 30× whole-genome coverage from the 1000 Genomes Project achieves an average runtime of 1.7 hours per sample and a clear separation of the individual populations in principal component analysis across called SNVs.

Conclusions: xAtlas is a fast, lightweight, and accurate SNV and small indel calling method. Source code for xAtlas is available under a BSD 3-clause license at https://github.com/jfarek/xatlas.

Figure 1:

The major stages of xAtlas variant calling process.

Figure 2:

(A) Variant caller runtimes of xAtlas and 4 other small variant callers (single-threaded operation) on 3 Illumina HiSeq X NA12878 whole-genome samples at 30× average coverage. (B, C) Precision vs. sensitivity of passing variants called for these samples concordant with GIAB v4.2.1 NA12878 high-confidence variants. Marker shape indicates values per variant caller for SNVs only (“X”), indels only (“+”), or SNVs and indels together (filled circles).

Figure 3:

1000 Genome comparison: Sensitivity and precision of xAtlas variant calls compared against SNVs and indels from a high-coverage Illumina phased panel generated on 3,202 samples from the 1000 Genomes Project, using (A) all passing variants on chromosomes 1–22 and X and (B) passing variants within GIAB HG002 high-confidence variant regions on chromosomes 1–22. PCA plots of chromosome 22 SNVs with MAF ≥ 0.05 called by xAtlas on these 3,202 samples, showing (C) PC1 vs. PC2, (D) PC1 vs. PC3, and (E) PC2 vs. PC3.