InvitedHackathonTeam

NVIDIA × scverse GPU omics

Single-cell RNA and ATAC analysis on GPUs with RAPIDS, cuML and cuGraph. Invited participant, cuGraph lead.

13–26×

Faster than CPU, on up to 16,000 cells

When: September 2025
Context: NVIDIA × scverse GPU omics hackathon (invited)
Team: Team
My role: Led the cuGraph work
Tools: RAPIDS, cuML, cuGraph, scRNA-seq, ATAC-seq

What I did

I was selected by recommendation for the hackathon and owned the cuGraph part of the work, analyzing scRNA and ATAC data with RAPIDS, cuML and cuGraph.

Results

On up to 16,000 cells, the GPU workflow ran 13 to 26 times faster than the CPU version.

Next projectPrompt2Pump