NVIDIA announced this week a new partnership with Harvard and MIT’s Broad Institute, bringing advanced analytics tools to the institute’s Terra cloud platform and the more than 25,000 life science researchers who use it.
WHY IT MATTERS
By connecting NVIDIA’s computing and artificial intelligence tools with Broad Institute scientists, the open platform can help advance biomedical research, genomics and other precision medicine innovations. The aim is to help academic researchers – as well as startups and large pharma companies – gain the AI-enabled computing power to mine large amounts of healthcare data.
The initial focus will be on several key areas, according to the company, starting with Parabricks, a GPU-accelerated software suite for secondary analysis of sequencing data. NVIDIA says it’s making it available in six new Terra workflows, enabling researchers to analyze a whole genome in a bit more than an hour, compared to 24 hours in a CPU-based environment. This, in turn, can reduce computing costs significantly.
Another focus will be building large language models, helping researchers develop foundational models for DNA and RNA to better understand human biology. They can use NVIDIA’s BioNeMo technology, a just-unveiled AI application framework designed for LLMs.
NVIDIA is also working on a new deep learning model for the Broad Institute’s Genome Analysis Toolkit, which is used by more than 100,000 researchers. It can help spot and identify genetic variants associated with disease, advancing drug discovery research and development of new treatments.
Broad Institute researchers will also gain access to MONAI, a medical imaging-focused deep learning framework, and NVIDIA RAPIDS, a toolkit that can enable faster data preparation for genomic single-cell analysis.
THE LARGER TREND
The Broad Institute is working to innovate biomedical and precision medicine, building out its open cloud platform to connect researchers with each other and give them datasets and powerful AI tools to analyze genomic and other life sciences data for scientific breakthroughs.
It’s doing this with several technology partnerships like the one with NVIDIA. In 2021, for instance, it launched a new collaboration with Microsoft and Verily to accelerate new advancements in biomedicine through the Terra platform.
But the MIT-Harvard joint research venture has been generous with its own technology innovations as well. In 2017, the Broad Institute made its GATK genomic analytics software open source, to make it available to more science researchers.
ON THE RECORD
“There’s a need across the healthcare ecosystem for better computational tools to enable breakthroughs in the way we understand disease, develop diagnostics and deliver treatments,” said Kimberly Powell, NVIDIA’s vice president of healthcare in a statement. “By expanding our collaboration with the Broad Institute, we can bring the power of large language models to ultimately deliver joint solutions and narrow the divide between insights from researchers and real benefits for patients.”
“Life sciences are in the midst of a data revolution, and researchers are in critical need of a new approach to bring machine learning into biomedicine,” added Broad Institute Chief Data Scientist Anthony Philippakis. “In this collaboration, we aim to expand our mission of data sharing and collaborative processes to scale genomics research.”