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 quickly the company could move assays into clinical use.
Reported impact
DELFI showed that Parabricks can cut compute time 5.4x with a 4.1x cost reduction for FirstLook Lung and 6.6x with an 8.1x cost reduction for DELFI-TF, helping the company shorten turnaround times, make genome-wide somatic calling affordable, and prepare its monitoring workflow for clinical-scale sample growth.
DELFI evaluated NVIDIA Parabricks as a drop-in accelerator for the genomic pipelines behind FirstLook Lung and DELFI-TF. The company already used low-pass and deeper whole-genome sequencing on cell-free DNA to screen for lung cancer and monitor recurrence, so the key opportunity was to replace slow CPU-based secondary-analysis stages without rewriting upstream or downstream workflows. Parabricks FQ2BAM took over alignment and preprocessing tasks such as BWA-MEM, SAM sorting, duplicate marking, and optional BQSR, while GPU-accelerated variant callers including MutectCaller and DeepSomatic made genome-wide somatic analysis practical for DELFI-TF. Because inputs and outputs remain compatible with existing pipelines, DELFI can add GPU acceleration directly into its production flow, cut compute time and cost, and open the door to deeper sequencing coverage and faster clinical turnaround as sample volumes grow.
Sequencing reads from DELFI's liquid-biopsy assays enter Parabricks for GPU-accelerated alignment and preprocessing, variant-calling tools such as MutectCaller and DeepSomatic analyze the resulting data, and the outputs feed DELFI's screening and therapeutic-monitoring products without changing the surrounding pipeline contracts.
DELFI-TF's current turnaround time is 10–20 business days.
For FirstLook Lung, running Parabricks on a low-pass WGS pipeline yielded 5.4x faster compute time and a 4.1x reduction in cost for sequence alignment.
Parabricks' FQ2BAM is a GPU-accelerated tool that replaces the CPU-based alignment and preprocessing steps.
incorporating this technology can achieve 6.6x faster compute time and an 8.1x reduction in compute cost.
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.
The Organization JSON-LD lists numberOfEmployees with value 137. An employee count of 137 maps to SMB.
Related
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 NVIDIA Sample Apr 8, 2026 SimBioSys Traditional breast-cancer presurgical planning relied on grayscale MRI images and short radiology summaries, which made tumor geometry hard to interpret, contributed to variable surgical decisions and unnecessary… above 20 percent MONAI · NVIDIA A100 Tensor Core GPUs · NVIDIA CUDA-X 