Accelerating Gene Variant Detection With Deep Learning

Dr. Tychele Turner, from the Washington University School of Medicine in St. Louis, will present her lab's development of a computational workflow, called HAT, to detect de novo variants from whole-exome and whole-genome sequencing datasets. She’ll detail the development of this hybrid CPU/GPU workflow and discuss the application to >6,000 parent-child sequenced families. Dr. Turner will also describe her lab’s utilization of GPUs in detecting variants from long-read sequencing data. 

Dr. Turner’s talk will focus on areas of particular utility of GPU-based acceleration of genomic tools, including her lab’s use of NVIDIA Parabricks®, a suite of GPU-accelerated and deep learning industry-standard genomics analysis tools for next-generation sequencing data.

In this webinar you will:

• Understand what a de novo variant is and how it is detected from sequencing data
• Learn key uses of deep learning-based variant calling to detect de novo variants
• Identify key differences between short- and long-read sequencing
• Learn key uses of GPU-based acceleration to assess long-read sequencing data