The Wellcome Sanger Institute needed to analyze mutational signatures across large cancer datasets, but the non-negative matrix factorization workloads in its pipeline were so compute-intensive on CPUs that results took days or weeks and limited the number and complexity of experiments researchers could run.
Reported impact
Running the pipeline on NVIDIA DGX-1 delivered an average 30x acceleration, reduced a real-life analysis from roughly twenty days to sixteen hours, and let researchers run more and more complex experiments that could improve cancer research and treatment discovery.
The Wellcome Sanger Institute accelerated its cancer-signature research by moving the heavy portions of its SigProfiler pipeline onto an NVIDIA DGX-1 Server. The mutational-signature workflow uses non-negative matrix factorization to process tumor DNA profiles, so NVIDIA and the Mutographs teams offloaded the most time-consuming parts of the code to the DGX-1's eight NVIDIA V100 Tensor Core GPUs connected by NVIDIA NVLink. The remaining application logic continues on CPUs, but the GPU platform becomes the core engine for the computational bottleneck. In benchmark and real-life runs, the institute compared the DGX-1 against 60-core OpenStack CPU virtual machines to execute the same pipeline faster, enabling researchers to work through larger datasets and run more ambitious cancer-signature experiments.
Tumor DNA mutation profiles are fed into SigProfiler, the NMF-heavy steps are offloaded onto the DGX-1's V100 GPU cluster over NVLink, the rest of the application continues on CPUs, and the resulting mutational signatures are returned to researchers for downstream cancer analysis.
An average of 30X acceleration was observed when the pipeline jobs were executed on the DGX-1 platform compared to those on CPU hardware.
NVIDIA GPUs accelerate the scientific application by offloading the most time-consuming parts of the code.
Sanger Institute uses the NVIDIA DGX server to power its mutational cancer signature analysis pipeline—improving performance by 30x.
The DGX-1 delivered accurate results in sixteen hours for an equivalent CPU job that usually took twenty days in a real-life analysis.
This work requires the solution of a computationally intensive machine learning problem known as non-negative matrix factorization (NMF).
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
NVIDIA Sample Sep 22, 2026 DELFI Diagnostics DELFI Diagnostics needed to speed genomic analysis for cancer screening and therapeutic monitoring, but CPU-bound alignment and somatic variant-calling steps created turnaround-time and cost bottlenecks that limited how… 10–20 business days DeepSomatic · MutectCaller · NVIDIA Parabricks NVIDIA Sample Jul 10, 2026 Astellas Pharma Inc. Astellas needed to shorten the slow handoff between experimental scientists and computational chemists in early drug discovery so more researchers could use structure prediction and affinity screening without waiting on… More than 50 regular users and over 2,000 total users within four months NVIDIA BioNeMo · NVIDIA Boltz-2 NIM · NVIDIA DGX H100/H200 NVIDIA Sample Apr 23, 2026 Biofy Hospitals needed pathogen identification and antibiotic-resistance analysis much faster than five-day culture and antibiogram workflows, but CPU-bound genomic processing and limited AI expertise made it hard to turn… 100,000+ synthetic DNA sequences generated by the biology model Abby · H100 Tensor Core GPUs · NVIDIA CUDA-accelerated libraries 