Configuration

Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)

Clair3 v1.0.8, tumour-only, ONT: Germline caller run on the tumour BAM (ONT model r1041_e82_400bps_sup_v420); calls tagged by ClairS-TO's panels of normals removed, the rest treated as somatic.

4 evaluations · 84 results

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

4 evaluations · 84 results. Different protocols are not a single leaderboard.

Sorted by AUPRC (indel only, tumour-only, 25x 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	Protocol and dataset	AUPRC (indel only, tumour-only, 25x tumour coverage)	AUPRC (indel only, tumour-only, 50x tumour coverage)	AUPRC (indel only, tumour-only, 75x tumour coverage)	AUPRC (SNV only, tumour-only, 25x tumour coverage)	AUPRC (SNV only, tumour-only, 50x tumour coverage)	AUPRC (SNV only, tumour-only, 75x tumour coverage)	F1 (indel only, tumour-only, 25x tumour coverage, at the best-F1 threshold)	F1 (indel only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	F1 (indel only, tumour-only, 75x tumour coverage, at the best-F1 threshold)	F1 (SNV only, tumour-only, 25x tumour coverage, at the best-F1 threshold)	F1 (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	F1 (SNV only, tumour-only, 75x tumour coverage, at the best-F1 threshold)	False negatives (indel only, tumour-only, 25x tumour coverage, at the best-F1 threshold)	False negatives (indel only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	False negatives (indel only, tumour-only, 75x tumour coverage, at the best-F1 threshold)	False negatives (SNV only, tumour-only, 25x tumour coverage, at the best-F1 threshold)	False negatives (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	False negatives (SNV only, tumour-only, 75x tumour coverage, at the best-F1 threshold)	False positives (indel only, tumour-only, 25x tumour coverage, at the best-F1 threshold)	False positives (indel only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	False positives (indel only, tumour-only, 75x tumour coverage, at the best-F1 threshold)	False positives (SNV only, tumour-only, 25x tumour coverage, at the best-F1 threshold)	False positives (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	False positives (SNV only, tumour-only, 75x tumour coverage, at the best-F1 threshold)	Precision (indel only, tumour-only, 25x tumour coverage, at the best-F1 threshold)	Precision (indel only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	Precision (indel only, tumour-only, 75x tumour coverage, at the best-F1 threshold)	Precision (SNV only, tumour-only, 25x tumour coverage, at the best-F1 threshold)	Precision (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	Precision (SNV only, tumour-only, 75x tumour coverage, at the best-F1 threshold)	Recall (indel only, tumour-only, 25x tumour coverage, at the best-F1 threshold)	Recall (indel only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	Recall (indel only, tumour-only, 75x tumour coverage, at the best-F1 threshold)	Recall (SNV only, tumour-only, 25x tumour coverage, at the best-F1 threshold)	Recall (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	Recall (SNV only, tumour-only, 75x tumour coverage, at the best-F1 threshold)	True positives (indel only, tumour-only, 25x tumour coverage, at the best-F1 threshold)	True positives (indel only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	True positives (indel only, tumour-only, 75x tumour coverage, at the best-F1 threshold)	True positives (SNV only, tumour-only, 25x tumour coverage, at the best-F1 threshold)	True positives (SNV only, tumour-only, 50x tumour coverage, at the best-F1 threshold)	True positives (SNV only, tumour-only, 75x tumour coverage, at the best-F1 threshold)
Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)Evaluation	ONT HCC1395 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2b), HCC1395 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.225 (best in column)	0.289 (best in column)	0.291 (best in column)	Not reported	Not reported	Not reported	0.325 (best in column)	0.367 (best in column)	0.372 (best in column)	Not reported	Not reported	Not reported	832	763	724	Not reported	Not reported	Not reported	1,347 (best in column)	1,286 (best in column)	1,409	Not reported	Not reported	Not reported	0.28 (best in column)	0.316 (best in column)	0.31 (best in column)	Not reported	Not reported	Not reported	0.386 (best in column)	0.437 (best in column)	0.466 (best in column)	Not reported	Not reported	Not reported	524 (best in column)	593 (best in column)	632 (best in column)	Not reported	Not reported	Not reported
Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)Evaluation	ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a), COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.0675	0.104	0.106	Not reported	Not reported	Not reported	0.141	0.191	0.196	Not reported	Not reported	Not reported	376 (best in column)	373 (best in column)	392 (best in column)	Not reported	Not reported	Not reported	2,161	1,419	1,189 (best in column)	Not reported	Not reported	Not reported	0.0882	0.13	0.14	Not reported	Not reported	Not reported	0.357	0.362	0.33	Not reported	Not reported	Not reported	209	212	193	Not reported	Not reported	Not reported
Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)Evaluation	ONT COLO829 tumour-only, 25x to 75x, somatic SNVs (Chen et al. 2025 Supplementary Table 2a), COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	Not reported	Not reported	Not reported	0.554 (best in column)	0.569 (best in column)	0.559 (best in column)	Not reported	Not reported	Not reported	0.683 (best in column)	0.713 (best in column)	0.703 (best in column)	Not reported	Not reported	Not reported	7,056 (best in column)	6,342 (best in column)	7,087 (best in column)	Not reported	Not reported	Not reported	21,236	18,804	18,647	Not reported	Not reported	Not reported	0.589 (best in column)	0.624 (best in column)	0.62 (best in column)	Not reported	Not reported	Not reported	0.812 (best in column)	0.831 (best in column)	0.811 (best in column)	Not reported	Not reported	Not reported	30,477 (best in column)	31,191 (best in column)	30,446 (best in column)
Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)Evaluation	ONT HCC1395 tumour-only, 25x to 75x, somatic SNVs (Chen et al. 2025 Supplementary Table 2b), HCC1395 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	Not reported	Not reported	Not reported	0.43	0.48	0.482	Not reported	Not reported	Not reported	0.594	0.631	0.634	Not reported	Not reported	Not reported	12,414	10,560	10,838	Not reported	Not reported	Not reported	14,673 (best in column)	14,723 (best in column)	13,824 (best in column)	Not reported	Not reported	Not reported	0.574	0.595	0.607	Not reported	Not reported	Not reported	0.615	0.672	0.663	Not reported	Not reported	Not reported	19,798	21,652	21,374

All 84 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: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.0675 AUPRC (indel only, tumour-only, 25x tumour coverage) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '25x', Type 'Indel', column 'AUPRC'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.141 F1 (indel only, tumour-only, 25x tumour coverage, at the best-F1 threshold) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '25x', Type 'Indel', column 'F1-score'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	376 False negatives (indel only, tumour-only, 25x tumour coverage, at the best-F1 threshold) count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '25x', Type 'Indel', column 'FN'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	2,161 False positives (indel only, tumour-only, 25x tumour coverage, at the best-F1 threshold) count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '25x', Type 'Indel', column 'FP'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.0882 Precision (indel only, tumour-only, 25x tumour coverage, at the best-F1 threshold) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '25x', Type 'Indel', column 'Precision'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.357 Recall (indel only, tumour-only, 25x tumour coverage, at the best-F1 threshold) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '25x', Type 'Indel', column 'Recall'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	209 True positives (indel only, tumour-only, 25x tumour coverage, at the best-F1 threshold) count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '25x', Type 'Indel', column 'TP'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.104 AUPRC (indel only, tumour-only, 50x tumour coverage) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '50x', Type 'Indel', column 'AUPRC'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.191 F1 (indel 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	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '50x', Type 'Indel', column 'F1-score'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	373 False negatives (indel 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	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '50x', Type 'Indel', column 'FN'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	1,419 False positives (indel 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	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '50x', Type 'Indel', column 'FP'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.13 Precision (indel 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	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '50x', Type 'Indel', column 'Precision'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.362 Recall (indel 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	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '50x', Type 'Indel', column 'Recall'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	212 True positives (indel 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	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '50x', Type 'Indel', column 'TP'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.106 AUPRC (indel only, tumour-only, 75x tumour coverage) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '75x', Type 'Indel', column 'AUPRC'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.196 F1 (indel only, tumour-only, 75x tumour coverage, at the best-F1 threshold) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '75x', Type 'Indel', column 'F1-score'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	392 False negatives (indel only, tumour-only, 75x tumour coverage, at the best-F1 threshold) count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '75x', Type 'Indel', column 'FN'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	1,189 False positives (indel only, tumour-only, 75x tumour coverage, at the best-F1 threshold) count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '75x', Type 'Indel', column 'FP'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.14 Precision (indel only, tumour-only, 75x tumour coverage, at the best-F1 threshold) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '75x', Type 'Indel', column 'Precision'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.33 Recall (indel only, tumour-only, 75x tumour coverage, at the best-F1 threshold) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '75x', Type 'Indel', column 'Recall'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic indels (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	193 True positives (indel only, tumour-only, 75x tumour coverage, at the best-F1 threshold) count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-colo829-indel 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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '75x', Type 'Indel', column 'TP'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic SNVs (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.554 AUPRC (SNV only, tumour-only, 25x tumour coverage) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only SNV (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '25x', Type 'SNV', column 'AUPRC'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic SNVs (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	0.683 F1 (SNV only, tumour-only, 25x tumour coverage, at the best-F1 threshold) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only SNV (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '25x', Type 'SNV', column 'F1-score'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic SNVs (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	7,056 False negatives (SNV only, tumour-only, 25x tumour coverage, at the best-F1 threshold) count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only SNV (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '25x', Type 'SNV', column 'FN'
Configuration: Clair3 v1.0.8, tumour-only, ONT (Chen et al. 2025)	Protocol: ONT COLO829 tumour-only, 25x to 75x, somatic SNVs (Chen et al. 2025 Supplementary Table 2a) Dataset: COLO829 tumour ONT R10.4.1 WGS (ClairS-TO benchmark)	21,236 False positives (SNV only, tumour-only, 25x tumour coverage, at the best-F1 threshold) count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Clair3 on ont-colo829 tumour-only SNV (Chen et al. 2025) somatic-clairs-to-20261011-protocol-ont-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 2a, Dataset 'COLO829', Caller 'Clair3', Tumor coverage '25x', Type 'SNV', column 'FP'

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

Use this configuration

How it works, versions and access

Strengths, limitations and unresolved questions

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.

0 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

No evidence rows match these filters. Choose another scope or clear the search.

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-config-clair3-ont

areas: dna-genomes
contexts: clinical_research
method types: supervised_machine_learning
reported name: Clair3
version: v1.0.8
foundation model eligible: false
parameters: Germline caller run on the tumour BAM (ONT model r1041_e82_400bps_sup_v420); calls tagged by ClairS-TO's panels of normals removed, the rest treated as somatic
access reuse: Public open-source software and released models
source locator: Supplementary Information 'Command lines used'; Supplementary Tables 2 and 7 row labels
provenance note: Clair3 as run on ONT tumour-only data in the cited comparison.

Related records

configuration of: Clair3
system: Clair3 on ont-colo829 tumour-only Indel (Chen et al. 2025)
system: Clair3 on ont-colo829 tumour-only SNV (Chen et al. 2025)
system: Clair3 on ont-hcc1395 tumour-only Indel (Chen et al. 2025)
system: Clair3 on ont-hcc1395 tumour-only SNV (Chen et al. 2025)

Suggest a correction