Evaluation

DeepSomatic on illumina-colo829 tumour-only SNV (Chen et al. 2025)

Published comparison transcribed from the pinned source; not reproduced.

Evaluation results

1 evaluation · 7 results. Different protocols are not a single leaderboard.

Protocol: Illumina COLO829 tumour-only, 50x, somatic SNVs (Chen et al. 2025 Supplementary Table 7b) · Dataset: COLO829 tumour Illumina NovaSeq 6000 WGS (ClairS-TO benchmark)

Sorted by AUPRC (SNV only, tumour-only, 50x tumour coverage) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	AUPRC (SNV only, tumour-only, 50x tumour coverage)	F1 (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	False negatives (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	False positives (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	Precision (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	Recall (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	True positives (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold)
DeepSomatic v1.7.0, tumour-only, Illumina (Chen et al. 2025)Evaluation	0.504	0.619	14,968	16,151	0.61	0.628	25,264

All 7 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: DeepSomatic v1.7.0, tumour-only, Illumina (Chen et al. 2025)	Protocol: Illumina COLO829 tumour-only, 50x, somatic SNVs (Chen et al. 2025 Supplementary Table 7b) Dataset: COLO829 tumour Illumina NovaSeq 6000 WGS (ClairS-TO benchmark)	0.504 AUPRC (SNV only, tumour-only, 50x tumour coverage) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DeepSomatic on illumina-colo829 tumour-only SNV (Chen et al. 2025) somatic-clairs-to-20261011-protocol-illumina-colo829-snv Aggregation: Not reported ClairS-TO: a deep-learning method for long-read tumor-only somatic small variant calling; ClairS-TO Supplementary Information (Supplementary Tables 1-8 and command lines); ClairS-TO Source Data workbook · Supplementary Table 7b, Dataset 'COLO829', Caller 'DeepSomatic', Tumor coverage '50x', Type 'SNV', column 'AUPRC'
Configuration: DeepSomatic v1.7.0, tumour-only, Illumina (Chen et al. 2025)	Protocol: Illumina COLO829 tumour-only, 50x, somatic SNVs (Chen et al. 2025 Supplementary Table 7b) Dataset: COLO829 tumour Illumina NovaSeq 6000 WGS (ClairS-TO benchmark)	0.619 F1 (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DeepSomatic on illumina-colo829 tumour-only SNV (Chen et al. 2025) somatic-clairs-to-20261011-protocol-illumina-colo829-snv Aggregation: Not reported ClairS-TO: a deep-learning method for long-read tumor-only somatic small variant calling; ClairS-TO Supplementary Information (Supplementary Tables 1-8 and command lines); ClairS-TO Source Data workbook · Supplementary Table 7b, Dataset 'COLO829', Caller 'DeepSomatic', Tumor coverage '50x', Type 'SNV', column 'F1-score'
Configuration: DeepSomatic v1.7.0, tumour-only, Illumina (Chen et al. 2025)	Protocol: Illumina COLO829 tumour-only, 50x, somatic SNVs (Chen et al. 2025 Supplementary Table 7b) Dataset: COLO829 tumour Illumina NovaSeq 6000 WGS (ClairS-TO benchmark)	14,968 False negatives (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold) count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DeepSomatic on illumina-colo829 tumour-only SNV (Chen et al. 2025) somatic-clairs-to-20261011-protocol-illumina-colo829-snv Aggregation: Not reported ClairS-TO: a deep-learning method for long-read tumor-only somatic small variant calling; ClairS-TO Supplementary Information (Supplementary Tables 1-8 and command lines); ClairS-TO Source Data workbook · Supplementary Table 7b, Dataset 'COLO829', Caller 'DeepSomatic', Tumor coverage '50x', Type 'SNV', column 'FN'
Configuration: DeepSomatic v1.7.0, tumour-only, Illumina (Chen et al. 2025)	Protocol: Illumina COLO829 tumour-only, 50x, somatic SNVs (Chen et al. 2025 Supplementary Table 7b) Dataset: COLO829 tumour Illumina NovaSeq 6000 WGS (ClairS-TO benchmark)	16,151 False positives (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold) count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DeepSomatic on illumina-colo829 tumour-only SNV (Chen et al. 2025) somatic-clairs-to-20261011-protocol-illumina-colo829-snv Aggregation: Not reported ClairS-TO: a deep-learning method for long-read tumor-only somatic small variant calling; ClairS-TO Supplementary Information (Supplementary Tables 1-8 and command lines); ClairS-TO Source Data workbook · Supplementary Table 7b, Dataset 'COLO829', Caller 'DeepSomatic', Tumor coverage '50x', Type 'SNV', column 'FP'
Configuration: DeepSomatic v1.7.0, tumour-only, Illumina (Chen et al. 2025)	Protocol: Illumina COLO829 tumour-only, 50x, somatic SNVs (Chen et al. 2025 Supplementary Table 7b) Dataset: COLO829 tumour Illumina NovaSeq 6000 WGS (ClairS-TO benchmark)	0.61 Precision (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DeepSomatic on illumina-colo829 tumour-only SNV (Chen et al. 2025) somatic-clairs-to-20261011-protocol-illumina-colo829-snv Aggregation: Not reported ClairS-TO: a deep-learning method for long-read tumor-only somatic small variant calling; ClairS-TO Supplementary Information (Supplementary Tables 1-8 and command lines); ClairS-TO Source Data workbook · Supplementary Table 7b, Dataset 'COLO829', Caller 'DeepSomatic', Tumor coverage '50x', Type 'SNV', column 'Precision'
Configuration: DeepSomatic v1.7.0, tumour-only, Illumina (Chen et al. 2025)	Protocol: Illumina COLO829 tumour-only, 50x, somatic SNVs (Chen et al. 2025 Supplementary Table 7b) Dataset: COLO829 tumour Illumina NovaSeq 6000 WGS (ClairS-TO benchmark)	0.628 Recall (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DeepSomatic on illumina-colo829 tumour-only SNV (Chen et al. 2025) somatic-clairs-to-20261011-protocol-illumina-colo829-snv Aggregation: Not reported ClairS-TO: a deep-learning method for long-read tumor-only somatic small variant calling; ClairS-TO Supplementary Information (Supplementary Tables 1-8 and command lines); ClairS-TO Source Data workbook · Supplementary Table 7b, Dataset 'COLO829', Caller 'DeepSomatic', Tumor coverage '50x', Type 'SNV', column 'Recall'
Configuration: DeepSomatic v1.7.0, tumour-only, Illumina (Chen et al. 2025)	Protocol: Illumina COLO829 tumour-only, 50x, somatic SNVs (Chen et al. 2025 Supplementary Table 7b) Dataset: COLO829 tumour Illumina NovaSeq 6000 WGS (ClairS-TO benchmark)	25,264 True positives (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold) count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DeepSomatic on illumina-colo829 tumour-only SNV (Chen et al. 2025) somatic-clairs-to-20261011-protocol-illumina-colo829-snv Aggregation: Not reported ClairS-TO: a deep-learning method for long-read tumor-only somatic small variant calling; ClairS-TO Supplementary Information (Supplementary Tables 1-8 and command lines); ClairS-TO Source Data workbook · Supplementary Table 7b, Dataset 'COLO829', Caller 'DeepSomatic', Tumor coverage '50x', Type 'SNV', column 'TP'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-10-22-1b7cf027e4f6 · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Metrics are recomputed from the saved predictions: not yet verified

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Metrics are recomputed from the saved predictions: not yet verified
Sample annotations are recorded: not yet verified
Dependence between samples is assessed: not yet verified

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
A pinned run recipe exists: not yet verified
Compute requirements are estimated: not yet verified

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Independent validation data exist: not yet verified
Overlap with training data is checked: not yet verified

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Evaluation procedure

Illumina COLO829 tumour-only, 50x, somatic SNVs (Chen et al. 2025 Supplementary Table 7b)

Configuration: DeepSomatic v1.7.0, tumour-only, Illumina (Chen et al. 2025)
Protocol: Illumina COLO829 tumour-only, 50x, somatic SNVs (Chen et al. 2025 Supplementary Table 7b)
Dataset: COLO829 tumour Illumina NovaSeq 6000 WGS (ClairS-TO benchmark)

origin: Independent external evaluation
configuration: Primary source as retrieved 2026-10-11
protocol id: somatic-clairs-to-20261011-protocol-illumina-colo829-snv
dataset version: Not reported
split: Held-out cell line
population: COLO829 tumour sample
inputs: Illumina tumour reads only
adaptation: Not reported
metric implementation: som.py (hap.py 0.3.12) and ClairS-TO compare_vcf; precision, recall and F1 at the best-F1 quality threshold
aggregation: Single sample per coverage level
budget: Not reported

Metadata review: source checked. Unreported conditions prevent automatic comparisons.

Reproduction

Split: Held-out cell line
Adaptation: Not reported
Scoring implementation: som.py (hap.py 0.3.12) and ClairS-TO compare_vcf; precision, recall and F1 at the best-F1 quality threshold

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

Evidence

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

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

54 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance
Comparison: adaptation Not reported Context-only references	ClairS-TO: a deep-learning method for long-read tumor-only somatic small variant calling Original source ↗ Supplementary Table 7b, rows 'DeepSomatic' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Communications, published 2025-10-31; PMC12579226 full-text XML Retrieved: 2026-10-11T21:37:39Z	missing or unspecified No individual claim review recorded independent paper Audit details Field: `attributes.comparison.adaptation` Source artifact SHA-256: `6b5e5262df96467010d539e919c7a52aac3e49c616b3eeb403d1865dcb173b8a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: adaptation Not reported Context-only references	ClairS-TO Source Data workbook Original source ↗ Supplementary Table 7b, rows 'DeepSomatic' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Source Data file (41467_2025_64547_MOESM6_ESM.xlsx) of the published article Retrieved: 2026-10-11T21:38:10Z	missing or unspecified No individual claim review recorded independent paper Audit details Field: `attributes.comparison.adaptation` Source artifact SHA-256: `4347c74fe0ce2ed04b1ac40d28bd4f8885c77f628e911a7027a275b1234828f8` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: adaptation Not reported Context-only references	ClairS-TO Supplementary Information (Supplementary Tables 1-8 and command lines) Original source ↗ Supplementary Table 7b, rows 'DeepSomatic' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Supplementary Information PDF (41467_2025_64547_MOESM1_ESM.pdf) of the published article Retrieved: 2026-10-11T21:37:53Z	missing or unspecified No individual claim review recorded independent paper Audit details Field: `attributes.comparison.adaptation` Source artifact SHA-256: `806cd47423031495bf00543d7e3e3abad3f93fc4ee3ee2a7a570c335227f5603` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: aggregation Single sample per coverage level Context-only references	ClairS-TO: a deep-learning method for long-read tumor-only somatic small variant calling Original source ↗ Supplementary Table 7b, rows 'DeepSomatic' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Communications, published 2025-10-31; PMC12579226 full-text XML Retrieved: 2026-10-11T21:37:39Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.aggregation` Source artifact SHA-256: `6b5e5262df96467010d539e919c7a52aac3e49c616b3eeb403d1865dcb173b8a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: aggregation Single sample per coverage level Context-only references	ClairS-TO Source Data workbook Original source ↗ Supplementary Table 7b, rows 'DeepSomatic' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Source Data file (41467_2025_64547_MOESM6_ESM.xlsx) of the published article Retrieved: 2026-10-11T21:38:10Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.aggregation` Source artifact SHA-256: `4347c74fe0ce2ed04b1ac40d28bd4f8885c77f628e911a7027a275b1234828f8` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: aggregation Single sample per coverage level Context-only references	ClairS-TO Supplementary Information (Supplementary Tables 1-8 and command lines) Original source ↗ Supplementary Table 7b, rows 'DeepSomatic' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Supplementary Information PDF (41467_2025_64547_MOESM1_ESM.pdf) of the published article Retrieved: 2026-10-11T21:37:53Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.aggregation` Source artifact SHA-256: `806cd47423031495bf00543d7e3e3abad3f93fc4ee3ee2a7a570c335227f5603` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: budget Not reported Context-only references	ClairS-TO: a deep-learning method for long-read tumor-only somatic small variant calling Original source ↗ Supplementary Table 7b, rows 'DeepSomatic' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Communications, published 2025-10-31; PMC12579226 full-text XML Retrieved: 2026-10-11T21:37:39Z	missing or unspecified No individual claim review recorded independent paper Audit details Field: `attributes.comparison.budget` Source artifact SHA-256: `6b5e5262df96467010d539e919c7a52aac3e49c616b3eeb403d1865dcb173b8a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: budget Not reported Context-only references	ClairS-TO Source Data workbook Original source ↗ Supplementary Table 7b, rows 'DeepSomatic' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Source Data file (41467_2025_64547_MOESM6_ESM.xlsx) of the published article Retrieved: 2026-10-11T21:38:10Z	missing or unspecified No individual claim review recorded independent paper Audit details Field: `attributes.comparison.budget` Source artifact SHA-256: `4347c74fe0ce2ed04b1ac40d28bd4f8885c77f628e911a7027a275b1234828f8` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: budget Not reported Context-only references	ClairS-TO Supplementary Information (Supplementary Tables 1-8 and command lines) Original source ↗ Supplementary Table 7b, rows 'DeepSomatic' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Supplementary Information PDF (41467_2025_64547_MOESM1_ESM.pdf) of the published article Retrieved: 2026-10-11T21:37:53Z	missing or unspecified No individual claim review recorded independent paper Audit details Field: `attributes.comparison.budget` Source artifact SHA-256: `806cd47423031495bf00543d7e3e3abad3f93fc4ee3ee2a7a570c335227f5603` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Comparison: dataset version Not reported Context-only references	ClairS-TO: a deep-learning method for long-read tumor-only somatic small variant calling Original source ↗ Supplementary Table 7b, rows 'DeepSomatic' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Communications, published 2025-10-31; PMC12579226 full-text XML Retrieved: 2026-10-11T21:37:39Z	missing or unspecified No individual claim review recorded independent paper Audit details Field: `attributes.comparison.dataset_version` Source artifact SHA-256: `6b5e5262df96467010d539e919c7a52aac3e49c616b3eeb403d1865dcb173b8a` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

3 source records and release history

ClairS-TO: a deep-learning method for long-read tumor-only somatic small variant calling · Original source · Nature Communications, published 2025-10-31; PMC12579226 full-text XML
ClairS-TO Supplementary Information (Supplementary Tables 1-8 and command lines) · Original source · Supplementary Information PDF (41467_2025_64547_MOESM1_ESM.pdf) of the published article
ClairS-TO Source Data workbook · Original source · Source Data file (41467_2025_64547_MOESM6_ESM.xlsx) of the published article

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: somatic-clairs-to-20261011-eval-deepsomatic-illumina-colo829-snv

areas: dna-genomes
contexts: clinical_research
origin: independent_paper
protocol: somatic-clairs-to-20261011-protocol-illumina-colo829-snv
version: Primary source as retrieved 2026-10-11
comparison: protocol id: somatic-clairs-to-20261011-protocol-illumina-colo829-snv; dataset version: Not reported; split: Held-out cell line; population: COLO829 tumour sample; inputs: Illumina tumour reads only; adaptation: Not reported; metric implementation: som.py (hap.py 0.3.12) and ClairS-TO compare_vcf; precision, recall and F1 at the best-F1 quality threshold; aggregation: Single sample per coverage level; budget: Not reported
source locator: Supplementary Table 7b, rows 'DeepSomatic'
missing metadata: comparison.adaptation: reason: inapplicable; note: Pre-trained models used without retraining on the test cell line; comparison.budget: reason: unreported; comparison.dataset version: reason: unreported

Related records

system: DeepSomatic v1.7.0, tumour-only, Illumina (Chen et al. 2025)
assessment: Illumina COLO829 tumour-only, 50x, somatic SNVs (Chen et al. 2025 Supplementary Table 7b)
data: COLO829 tumour Illumina NovaSeq 6000 WGS (ClairS-TO benchmark)
evaluation: DeepSomatic illumina-colo829 SNV 50x auprc
evaluation: DeepSomatic illumina-colo829 SNV 50x f1-score
evaluation: DeepSomatic illumina-colo829 SNV 50x false-negative-count
evaluation: DeepSomatic illumina-colo829 SNV 50x false-positive-count
evaluation: DeepSomatic illumina-colo829 SNV 50x precision
evaluation: DeepSomatic illumina-colo829 SNV 50x recall
evaluation: DeepSomatic illumina-colo829 SNV 50x true-positive-count

Suggest a correction