@article {Layer018259, author = {Ryan M. Layer and Neil Kindlon and Konrad J. Karczewski and Exome Aggregation Consortium and Aaron R. Quinlan}, title = {Efficient compression and analysis of large genetic variation datasets}, elocation-id = {018259}, year = {2015}, doi = {10.1101/018259}, publisher = {Cold Spring Harbor Laboratory}, abstract = {The economy of human genome sequencing has catalyzed ambitious efforts to interrogate the genomes of large cohorts in search of deeper insight into the genetic basis of disease. This manuscript introduces Genotype Query Tools (GQT) as a new indexing strategy and powerful toolset that enables interactive analyses based on genotypes, phenotypes and sample relationships. Speed improvements are achieved by operating directly on a compressed index without decompression. GQT{\textquoteright}s data compression ratios increase favorably with cohort size and therefore, by avoiding data inflation, relative analysis performance improves in kind. We demonstrate substantial query performance improvements over state-of-the-art tools using datasets from the 1000 Genomes Project (46 fold), the Exome Aggregation Consortium (443 fold), and simulated datasets of up to 100,000 genomes (218 fold). Moreover, our genotype indexing strategy complements existing formats and toolsets to provide a powerful framework for current and future analyses of massive genome datasets.URLS All source code for the GQT toolkit is available at https://github.com/ryanlayer/gqt. Furthermore, all commands used for the experiments conducted in this study are available at https://github.com/ryanlayer/gqt_paper.}, URL = {https://www.biorxiv.org/content/early/2015/04/20/018259}, eprint = {https://www.biorxiv.org/content/early/2015/04/20/018259.full.pdf}, journal = {bioRxiv} }