Parabricks is a GPU accelerated genomics software designed for secondary analysis. Compared to CPU based tools such as GATK, Parabricks is up to 80x faster for variant calling. This gives researchers the ability to run much more analysis on their data in a fraction of the time. In this workshop, we will show how Parabricks can be used to run and compare multiple variant callers. This was not feasible, especially for large data sets, using CPU versions of these tools, but Parabricks makes this possible. In this workshop we will work with the HG002 whole exome. First we will run Haplotypecaller and DeepVariant and compare the accuracy between the two. Next we will run DeepVariant again, but this time the model underneath has been trained specifically for WES data (as opposed to WGS data) and see how the accuracy changes again. Prerequisite(s): Basic familiarity with command line Linux, Python, and bioinformatics
*Please disregard any reference to "Event Code" for access to training materials. "Event Codes" are only valid during the original live session.
Explore more training options offered by the NVIDIA Deep Learning Institute (DLI). Choose from an extensive catalog of self-paced, online courses or instructor-led virtual workshops to help you develop key skills in AI, HPC, graphics & simulation, and more.