How AI describes GATK

The Genome Analysis Toolkit (GATK) from the Broad Institute is a genomic analysis toolkit focused on variant discovery and genotyping in high-throughput sequencing data, and is the industry standard for identifying SNPs and indels in germline DNA and RNA-seq data, now expanding to somatic variants, CNV, and structural variation. It includes data processing and quality-control utilities and bundles the Picard toolkit; it is designed for exomes and whole genomes and can be adapted to other technologies and organisms with any ploidy, running on Linux with Java 1.8 and supporting Docker, cloud, and Spark-based HPC. GATK provides Best Practices workflows for germline and somatic variant discovery, CNV, and SV, offering a suite of tools to process reads-to-results that can be chained into scripted workflows, backed by documentation, forums, and downloads.