DeepVariant is one of the most popular variant callers in genomics right now. It uses image-based deep learning methods to predict mutations in a genome. DeepVariant comes with a pre-trained model out of the box that works very well across a wide set of genomes; however, for more advanced applications, it's possible to train new models to be used with DeepVariant. In this workshop we'll use Parabricks to run the vanilla DeepVariant model on our dataset and measure the performance. We expect to see good performance out of the box. Then we'll retrain this model on new data and evaluate the performance again. We should see a higher accuracy using our new model.
Prerequisite(s):
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.