An initiative led by the Stanford University School of Medicine has set a world record for the fastest DNA sequencing by identifying rare genetic diseases in just above five hours using AI. The team used NVIDIA Clara, Google DeepVariant, and Oxford Nanopore Technologies sequencing to spot a contagious variant to determine an epilepsy-causing genetic disorder in a three-month-old infant! The same exercise traditionally - through a genetic material panel - would have taken at least two weeks, precious time for diagnosing many critical cases.

“Genomic information can provide rich insights and enable a clearer picture to be built,” said Gordon Sanghera, CEO of Oxford Nanopore Technologies. “A workflow which could deliver this information in near real-time has the potential to provide meaningful benefits in a variety of settings in which rapid access to information is critical.”

The processes were accelerated by meticulously planning each section with the help of artificial intelligence (AI) and machine learning. The complete process - acquiring blood samples to sequencing the whole genome to identifying variants linked to the disease - now takes a few hours via the ultra-rapid sequencing method. The method was developed collectively by researchers from Stanford University, NVIDIA, Oxford Nanopore Technologies, Google, Baylor College of Medicine and the University of California at Santa Cruz.

The samples were prepared and nanopore sequencing was done via Oxford Nanopore’s PromethION Flow Cell which generated more than 100GB of data every hour!

NVIDIA GPUs were run on Google Cloud to accelerate both - base and variant calling; in addition, they further accelerated variant calling by converting it into an application with Clara Parabricks, a computational genomics application framework.

NVIDIA Tensor Core GPUs processed the sequencing data for base-calling on a Google Cloud computing environment. which allowed them to categorise unidentified signals from the device into A, T G and C nucleotides. 

"It’s a lengthy process: A typical whole human genome sequencing diagnostic test takes six to eight weeks. Even rapid turnaround tests take two or three days. In many cases, this can be too slow to make a difference in the treatment of a critically ill patient," stated the blog on the official NVIDIA website

The researchers will now focus on discovering the minute variations in DNA sequences that lead to genetic disorders. Clara Parabricks used a GPU-accelerated version of PEPPER-Margin-DeepVariant, (a pipeline developed in a collaboration between Google and UC Santa Cruz’s Computational Genomics Laboratory) for the variant calling stage.

“Together with our collaborators and some of the world’s leaders in genomics, we were able to develop a rapid sequencing analysis workflow that has already shown tangible clinical benefits,” said NVIDIA’s Mehrzad Samadi, who co-led the creation of Parabricks and co-authored the New England Journal of Medicine article. “These are the kinds of high-impact problems we live to solve.”

Euan Ashley, MB ChB, DPhil, the paper’s corresponding author and a professor of medicine, genetics and of biomedical data science at Stanford University School of Medicine, will be speaking at NVIDIA GTC, a virtual AI developers' conference, from March 21-24.