Guinness World Records this week presented a research team led by Stanford University with the first record for the fastest DNA sequencing technique – a reference set using an AI-accelerated workflow and the accelerated calculation.
Completed in five hours and two minutes, the DNA sequencing record can allow clinicians to take a blood sample from an intensive care patient and arrive at a diagnosis of a genetic disorder the same day. The recognition was bestowed by a Guinness World Records judge on Wednesday at Stanford University’s Jen-Hsun Huang Engineering Center, named after the founder and CEO of NVIDIA, a Stanford alumnus.
The landmark study behind the world record was led by Dr. Euan Ashley, professor of medicine, genetics and biomedical data science at Stanford School of Medicine. Collaborators include researchers from Stanford, NVIDIA, Oxford Nanopore Technologies, Google, Baylor College of Medicine and the University of California, Santa Cruz.
“I think we’re unanimous in saying this is nothing short of a miracle,” Kimberly Powell, vice president of healthcare at NVIDIA, said at the event. “It is an achievement that has entered the history books and will inspire another five and ten years of fantastic work in the digital biology revolution, in which genomics is at the forefront.”
Diagnose with a genome in record time
Researchers achieved record speed by optimizing every step of the sequencing workflow. They used high-throughput nanopore sequencing on Oxford Nanopore PromethION Flow Cells to generate over 100 gigabases of data per hour, and accelerated base calling and variant calling using GPUs NVIDIA on Google Cloud. A gigabase is one billion nucleotides.
“These innovations didn’t come from one individual, or even one team,” Greg Corrado, Distinguished Scientist at Google Research, said at the event. “You really need this group of people to come together to solve these problems.”
To speed up every step – from basic Oxford Nanopore AI calling to variant calling, where scientists identify the millions of variants in a genome – the researchers relied on the application framework of computational genomics from NVIDIA Clara Parabricks. They used a GPU-accelerated version of PEPPER-Margin-DeepVariant, a pipeline developed by Google and the Computational Genomics Lab at UC Santa Cruz.
“I believe that the innovations we will see in biology and medicine in the next century will depend much more on this type of collaboration than on the siled R&D centers of the past,” Corrado said.
New possibilities for patient care
Ultra-fast genome sequencing is not about setting world records. Reducing the turnaround time for a genetic diagnosis from weeks to just hours can provide doctors with the rapid answers needed to treat patients in intensive care, where every second counts.
And, as the technology becomes more accessible, more hospitals and research centers will be able to use whole genome sequencing as an essential tool for patient care.
“Genomics is still in its infancy – it’s not the standard of care,” Powell said. “I think we can help bring it into the norm by reducing cost and complexity and democratizing it.”
Not content with the five-hour record, the team is already exploring ways to reduce DNA sequencing time even further.
“There is a promise we will make. We will break this record very quickly in collaboration with Euan and his team, as well as NVIDIA and Google,” said Gordon Sanghera, CEO of Oxford Nanopore Technologies.
Learn more about this research from Dr. Euan Ashley by registering for free at NVIDIA GTC, where he will present a talk titled “When Every Second Counts: Accelerated Genome Sequencing for Critical Care” on Tuesday, March 22 at 2 p.m. of the Pacific).
To subscribe to NVIDIA Health News Here.
