Accelerated long-read variant calling with Clair3 for whole-genome sequencing

What this source contributed

Records in this release that cite this source. A record can cite several sources.

• 1 model
• 5 configurations
• 5 protocols
• 2 datasets
• 12 evaluations
• 374 results
• 6 evidence claims

Results

Values as the source printed them. Compare results only under compatible protocols, datasets and metrics.

Claims

Statements this source supports, each with where in the source it was checked.

• Relevance of Clair3 GPU workflow stage runtimes on HG003 ONT and PacBio WGS (Zheng et al. 2026) to "Select an execution workflow for large-scale diagnostic genomics": Assessed by Clair3 GPU workflow stage runtimes on HG003 ONT and PacBio WGS (Zheng et al. 2026 Supplementary Table 1) (model-execution-20261011-source-zheng2026-clair3-supplement: Supplementary Table 1; Supplementary Notes; model-execution-20261011-source-zheng2026-clair3: Results 3.1-3.2; Conflict of interests; Data availability)
• Relevance of HG003 ONT WGS small-variant accuracy against GIAB v4.2.1, Clair3 versus DeepVariant (Zheng et al. 2026) to "Select an execution workflow for large-scale diagnostic genomics": Assessed by HG003 ONT WGS small-variant accuracy against GIAB v4.2.1, Clair3 versus DeepVariant (Zheng et al. 2026 Supplementary Table 3) (model-execution-20261011-source-zheng2026-clair3-supplement: Supplementary Table 3; Supplementary Notes; model-execution-20261011-source-zheng2026-clair3: Results 3.1-3.2; Conflict of interests; Data availability)
• Relevance of HG003 ONT WGS variant-calling runtime, memory and I/O, Clair3 versus DeepVariant in GPU mode (Zheng et al. 2026) to "Select an execution workflow for large-scale diagnostic genomics": Assessed by HG003 ONT WGS variant-calling runtime, memory and I/O, Clair3 versus DeepVariant in GPU mode (Zheng et al. 2026 Supplementary Table 2) (model-execution-20261011-source-zheng2026-clair3-supplement: Supplementary Table 2; Supplementary Notes; model-execution-20261011-source-zheng2026-clair3: Results 3.1-3.2; Conflict of interests; Data availability)
• Relevance of HG003 PacBio Revio WGS small-variant accuracy against GIAB v4.2.1, Clair3 versus DeepVariant (Zheng et al. 2026) to "Select an execution workflow for large-scale diagnostic genomics": Assessed by HG003 PacBio Revio WGS small-variant accuracy against GIAB v4.2.1, Clair3 versus DeepVariant (Zheng et al. 2026 Supplementary Table 3) (model-execution-20261011-source-zheng2026-clair3-supplement: Supplementary Table 3; Supplementary Notes; model-execution-20261011-source-zheng2026-clair3: Results 3.1-3.2; Conflict of interests; Data availability)
• Relevance of HG003 PacBio Revio WGS variant-calling runtime, memory and I/O, Clair3 versus DeepVariant in GPU mode (Zheng et al. 2026) to "Select an execution workflow for large-scale diagnostic genomics": Assessed by HG003 PacBio Revio WGS variant-calling runtime, memory and I/O, Clair3 versus DeepVariant in GPU mode (Zheng et al. 2026 Supplementary Table 2) (model-execution-20261011-source-zheng2026-clair3-supplement: Supplementary Table 2; Supplementary Notes; model-execution-20261011-source-zheng2026-clair3: Results 3.1-3.2; Conflict of interests; Data availability)
• version: DeepVariant runs (Zheng et al. 2026): Version Supplementary Table 2 and the Supplementary Notes command lines give DeepVariant v1.10-beta (google/deepvariant:v1.10-beta and v1.10-beta-gpu); Results 3.1 compare 'DeepVariant v1.8 in CPU and GPU modes'. Supplementary Table 3 prints no version. (Supplementary Table 2 caller column; Supplementary Notes 'Running DeepVariant GPU version (v1.10-beta)' and 'Running DeepVariant CPU (v1.10-beta)'; Results 3.1.1 paragraph 1)

Models, benchmarks and other records

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.