March 3 (Reuters) – Diagnostics firm Droplet Biosciences said on Tuesday it is collaborating with Nvidia to use the chipmaker’s AI infrastructure to speed up post-surgery cancer test results.
The company has been using Nvidia Parabricks, a GPU-accelerated software suite, to drastically speed up genomic data analysis for DNA sequencing.
* Droplet said its method can detect residual disease in 24hours by analyzing lymphatic fluid collected post surgery,compared to the four to six weeks it typically takes for tumorremnants to appear in blood-based tests. * “By leveraging NVIDIA Parabricks’ acceleration, we’ve beenable to compress some of our most computationally intensivesteps from more than a day down to just a few hours,” saidDroplet’s chief scientific officer, Wendy Winckler. * The company said it also realized operational benefitsdespite higher hourly costs for GPU compute, adding, “Thedramatically reduced runtime results in a lower overall cost persample.” * Faster turnaround allows patients to get the results whilestill in the hospital, while avoiding extra visits or long waitsfor traditional blood tests, it added. * “We are using Parabricks to speed up our genomic analysisand shorten turnaround time from 10 days to less than fivedays,” said Zhuosheng Gu, senior director of informatics, R&D atDroplet Biosciences. * The diagnostic startup’s first clinical test is forHPV-negative head and neck cancer, validated under the ClinicalLaboratory Improvement Amendments. * Droplet is a member of NVIDIA Inception, an AI startupaccelerator program, and an NVIDIA AI Enterprise customer.
(Reporting by Sneha S K in Bengaluru; Editing by Vijay Kishore)
