Iterating on spatial data took 10 hours per run. GPU acceleration cut this to 3 minutes, enabling scale to 100 million cells.
A nonprofit research institute generating massive genomic datasets, where just two runs on modern spatial platforms produce more cell data than the entire Human Lung Cell Atlas project.
Transitioning to spatial omics created massive data volumes, where standard analysis workflows required 10 to 14 hours per run. Since researchers...
“As we look forward, we’re talking about generating datasets with tens of millions or maybe even hundreds of millions of cells. Scalability across datasets of that size is only possible because we’ve been able to use this RAPIDS implementation.”
Biomedical research institute focused on genomic sequencing and personalized medicine.
NVIDIA is a technology company that specializes in semiconductors, graphics processing units, and artificial intelligence for applications in data centers, gaming, and more.
Related implementations across industries and use cases
Legacy CPUs bottlenecked genome analysis at 50 hours per sample. GPU pipelines cut this to 31 minutes—97x faster.
Analyzing 100k genomes dragged at 8 hours per case. GPU nodes cut processing to 40 minutes, unlocking the program’s scale.
Noisy wafer signals blocked scalable analysis. Deep learning now translates billions of data points to enable the $100 genome.
Silos forced teams to manually chase data. Now, AI agents identify adverse events in seconds, eliminating weeks of cross-referencing.
Attorneys juggled fragmented tools to search 50,000 cases. An AI orchestrator now routes queries to sub-agents in a single chat.
Lab supply orders were handwritten in notebooks. Digital ordering now takes seconds, saving 30,000 hours for research annually.
Experts spent 15 minutes pulling data from scattered systems. Natural language prompts now generate detailed reports instantly.