Comprehensive and accurate genome analysis at scale using DRAGEN accelerated algorithms

Abstract

Research and medical genomics require comprehensive and scalable solutions to drive the discovery of novel disease targets, evolutionary drivers, and genetic markers with clinical significance. This necessitates a framework to identify all types of variants independent of their size (e.g., SNV/SV) or location (e.g., repeats). Here we present DRAGEN that utilizes novel methods based on multigenomes, hardware acceleration, and machine learning based variant detection to provide novel insights into individual genomes with ~30min computation time (from raw reads to variant detection). DRAGEN outperforms all other state-of-the-art methods in speed and accuracy across all variant types (SNV, indel, STR, SV, CNV) and further incorporates specialized methods to obtain key insights in medically relevant genes (e.g., HLA, SMN, GBA). We showcase DRAGEN across 3,202 genomes and demonstrate its scalability, accuracy, and innovations to further advance the integration of comprehensive genomics for research and medical applications.

Figure 1:. Overview of DRAGEN variant calling pipeline.

DRAGEN improves the variant identification from single bp up to multiple Mbp of alleles. This is achieved by implementing multiple optimized novel concepts: i) Mapping utilizes a multigenome (graph) including 64 haplotypes; ii) SV calling is significantly improved over local assemblies based on breakpoint graphs; iii) SNV calling is improved using multiple novelties including machine learning based scoring and filtering; iv) CNV calling utilizes the multigenome (graph) and the SV calling information to make informed decisions; vi) Additional nine tools targeting specific difficult regions of the genome are included, four of them not reported before; vi) STR calling is integrated based on Expansion Hunter; and vii) A gVCF genotyper implementation to provide a population level fully genotyped VCF file.

Figure 2:. Performance overview of DRAGEN based on GIAB benchmarks.

A) length distribution of small and large variants discovered by DRAGEN (bin sizes used for the plot (from left to right) are: 500, 250,150,50, 150, 250, 500), B) SNV comparison based on GIAB SNV 4.2.1, C) SNV call comparisons based on CMRG v1.0, D) Comparison of SV call performance (INS and DEL types) based on GIAB SV v0.6, E) Comparison of CMRG SV call performance (INS and DEL types) based on GIAB CMRG SV v1.0, F) CNV caller comparison of DRAGEN compared to CNVnator across different sizes of deletions based on GIAB SV v0.6, and G) The benchmarking of short tandem repeats using GIAB v1.0. The recall and F-measure was calculated using GIAB catalog and the recall* and F-measure* were calculated using the catalogs of DRAGEN and GangSTR.

Figure 3:. Performance overview of DRAGEN for HG001–07 samples

A) Length distribution of different variants for all samples (bin sizes used for the plot from left to right are: 500, 250,150,50300,150, 250, 500); B) The recall, precision, and F-measure of DRAGEN for HG001–07 samples; C) The comparison of False negative (FN) and False positive numbers among DeepVariant with BWA, DeepVariant with Giraffe, and DRAGEN for HG001–07 SNV calls; and D) Comparison of recall, precision and F-measure of these samples for four different tools i.e., DRAGEN, GATK, and DeepVariant-BWA, DeepVariant-Giraffe. E) The average F-measures, and errors (false positives and false negatives) for different tools.

Figure 4:. DRAGEN SNV calls for 1kGP sample:

A) PCA plot of principal component 1 and 2 for SNVs across the population B) Distribution of SNV counts and C) Distribution of indel counts at super-population level D) Singleton (allele count=1), rare (allele frequency <= 1%) and common variant (allele frequency > 1%) counts of GATK v4.1 and DRAGEN v4.0.3 callsets of SNV and E) indel across the cohort level. The Known and Novel variants based on dbSNP 155 database F) The distribution of SNVs based on their functional annotations shown in the upper plot and the lower plot showing the fraction of Known and Novel variants G) The distribution of small insertion and deletions based on their functional annotations.

Figure 5:. DRAGEN SV calls for 1kGP sample:

A) PCA of merged STR, SV and CNV for deletions >5% on chromosome. B) Distribution of insertion and C) deletion type structural variants (>= 50bp) among populations D) Distribution of SV, STR (for ~50K loci) and CNV variants based on average count i.e., total variants of a population / population count E) distribution of variant numbers among all 3,202 samples for the 12 challenging medically relevant gene (CMRG) regions (in GRCh38) that are impacted due to falsely duplication and falsely collapsed errors. DRAGEN uses the corrected reference as a part of its multi genome approach to correctly identify more variants in duplicated and in collapsed regions. F) Class I HLA allele frequency distributions among all 1kGP populations