rewirebio.iobenchmarks
← Browse all evaluations
Evaluation

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

Published somatic caller comparison; transcribed, not reproduced.

Evaluation results

1 evaluation · 22 results. Different protocols are not a single leaderboard.

Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2) · Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres

Sorted by F1 (SNVs, average over the 21 replicate pairs as printed) (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 configurationF1 (SNVs, average over the 21 replicate pairs as printed)F1 (SNVs, tumour WGS_EA_T_1 with normal WGS_EA_N_1)F1 (SNVs, tumour WGS_FD_T_1 with normal WGS_FD_N_1)F1 (SNVs, tumour WGS_FD_T_2 with normal WGS_FD_N_2)F1 (SNVs, tumour WGS_FD_T_3 with normal WGS_FD_N_3)F1 (SNVs, tumour WGS_IL_T_1 with normal WGS_IL_N_1)F1 (SNVs, tumour WGS_IL_T_2 with normal WGS_IL_N_2)F1 (SNVs, tumour WGS_IL_T_3 with normal WGS_IL_N_3)F1 (SNVs, tumour WGS_LL_T_1 with normal WGS_LL_N_1)F1 (SNVs, tumour WGS_NC_T_1 with normal WGS_NC_N_1)F1 (SNVs, tumour WGS_NS_T_1 with normal WGS_NS_N_1)F1 (SNVs, tumour WGS_NS_T_2 with normal WGS_NS_N_2)F1 (SNVs, tumour WGS_NS_T_3 with normal WGS_NS_N_3)F1 (SNVs, tumour WGS_NS_T_4 with normal WGS_NS_N_4)F1 (SNVs, tumour WGS_NS_T_5 with normal WGS_NS_N_5)F1 (SNVs, tumour WGS_NS_T_6 with normal WGS_NS_N_6)F1 (SNVs, tumour WGS_NS_T_7 with normal WGS_NS_N_7)F1 (SNVs, tumour WGS_NS_T_8 with normal WGS_NS_N_8)F1 (SNVs, tumour WGS_NS_T_9 with normal WGS_NS_N_9)F1 (SNVs, tumour WGS_NV_T_1 with normal WGS_NV_N_1)F1 (SNVs, tumour WGS_NV_T_2 with normal WGS_NV_N_2)F1 (SNVs, tumour WGS_NV_T_3 with normal WGS_NV_N_3)
NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Evaluation90.8%93.4%89.5%90.1%90.2%93.3%91.4%90.7%80.5%89.1%92.6%87.6%89.8%92.3%89.2%93%91.7%87.3%88.6%95.5%95.6%95.6%
All 22 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		90.8% F1 (SNVs, average over the 21 replicate pairs as printed)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'Average', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		93.4% F1 (SNVs, tumour WGS_EA_T_1 with normal WGS_EA_N_1)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_EA_T_1 vs WGS_EA_N_1', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		89.5% F1 (SNVs, tumour WGS_FD_T_1 with normal WGS_FD_N_1)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_FD_T_1 vs WGS_FD_N_1', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		90.1% F1 (SNVs, tumour WGS_FD_T_2 with normal WGS_FD_N_2)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_FD_T_2 vs WGS_FD_N_2', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		90.2% F1 (SNVs, tumour WGS_FD_T_3 with normal WGS_FD_N_3)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_FD_T_3 vs WGS_FD_N_3', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		93.3% F1 (SNVs, tumour WGS_IL_T_1 with normal WGS_IL_N_1)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_IL_T_1 vs WGS_IL_N_1', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		91.4% F1 (SNVs, tumour WGS_IL_T_2 with normal WGS_IL_N_2)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_IL_T_2 vs WGS_IL_N_2', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		90.7% F1 (SNVs, tumour WGS_IL_T_3 with normal WGS_IL_N_3)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_IL_T_3 vs WGS_IL_N_3', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		80.5% F1 (SNVs, tumour WGS_LL_T_1 with normal WGS_LL_N_1)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_LL_T_1 vs WGS_LL_N_1', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		89.1% F1 (SNVs, tumour WGS_NC_T_1 with normal WGS_NC_N_1)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_NC_T_1 vs WGS_NC_N_1', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		92.6% F1 (SNVs, tumour WGS_NS_T_1 with normal WGS_NS_N_1)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_NS_T_1 vs WGS_NS_N_1', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		87.6% F1 (SNVs, tumour WGS_NS_T_2 with normal WGS_NS_N_2)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_NS_T_2 vs WGS_NS_N_2', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		89.8% F1 (SNVs, tumour WGS_NS_T_3 with normal WGS_NS_N_3)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_NS_T_3 vs WGS_NS_N_3', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		92.3% F1 (SNVs, tumour WGS_NS_T_4 with normal WGS_NS_N_4)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_NS_T_4 vs WGS_NS_N_4', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		89.2% F1 (SNVs, tumour WGS_NS_T_5 with normal WGS_NS_N_5)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_NS_T_5 vs WGS_NS_N_5', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		93% F1 (SNVs, tumour WGS_NS_T_6 with normal WGS_NS_N_6)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_NS_T_6 vs WGS_NS_N_6', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		91.7% F1 (SNVs, tumour WGS_NS_T_7 with normal WGS_NS_N_7)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_NS_T_7 vs WGS_NS_N_7', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		87.3% F1 (SNVs, tumour WGS_NS_T_8 with normal WGS_NS_N_8)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_NS_T_8 vs WGS_NS_N_8', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		88.6% F1 (SNVs, tumour WGS_NS_T_9 with normal WGS_NS_N_9)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_NS_T_9 vs WGS_NS_N_9', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		95.5% F1 (SNVs, tumour WGS_NV_T_1 with normal WGS_NV_N_1)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_NV_T_1 vs WGS_NV_N_1', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		95.6% F1 (SNVs, tumour WGS_NV_T_2 with normal WGS_NV_N_2)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_NV_T_2 vs WGS_NV_N_2', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)Protocol: SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset: SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres		95.6% F1 (SNVs, tumour WGS_NV_T_3 with normal WGS_NV_N_3)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

NeuSomatic-S SEQC-WGS-GT-50 on SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres, SNVs (Sahraeian et al. 2022)

somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv

Aggregation: Not reported

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S2, SNVs section, row 'WGS_NV_T_3 vs WGS_NV_N_3', column 'NeuSomatic-S SEQC-WGS-GT-50'

Source checking is not independent reproduction. Release 2026-10-10-cbb3da59bc08.

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 2026-10-10-cbb3da59bc08 · 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

SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)

Configuration
NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)
Protocol
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)
Dataset
SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres
origin
Author-reported evaluation
configuration
Primary source as retrieved 2026-10-10
protocol id
somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv
dataset version
Not reported
split
Held-out 50% of the high-confidence genome
population
21 tumour-normal WGS replicate pairs (labels WGS_<site>_T/N_<n>, site codes EA, FD, IL, LL, NC, NS, NV) on HiSeq X Ten, HiSeq 4000 and NovaSeq
inputs
Tumour and matched normal WGS BAM files (BWA-MEM)
adaptation
Not reported
metric implementation
F1 (%) of PASS calls against the SEQC2 truth set, exact match
aggregation
Per replicate pair, plus the printed average over 21
budget
Not reported

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

Reproduction

Split
Held-out 50% of the high-confidence genome
Adaptation
Not reported
Scoring implementation
F1 (%) of PASS calls against the SEQC2 truth set, exact match

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.

38 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-10-cbb3da59bc08
Property and statementOriginal source and locationReview and provenance
Comparison: adaptation
Not reported
Context-only references		Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample

Original source ↗

Additional file 2 Table S2, column 'NeuSomatic-S SEQC-WGS-GT-50', SNVs section

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Genome Biology 23:12, published 2022-01-07; PMC8740374 full-text XML
Retrieved: 2026-10-10T06:04:11Z

missing or unspecified

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: 78dbe540c2558585bc7537e0e6563706fdaa329b2708e5dc82b77074379b4a6e

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Comparison: adaptation
Not reported
Context-only references		Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf)

Original source ↗

Additional file 2 Table S2, column 'NeuSomatic-S SEQC-WGS-GT-50', SNVs section

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 13059_2021_2592_MOESM2_ESM.pdf
Retrieved: 2026-10-10T06:04:16Z

missing or unspecified

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: 10a109d80f6f49446ea84bd9f7f6b31c20d634516c8666376ac8a8f51f3236d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Comparison: aggregation
Per replicate pair, plus the printed average over 21
Context-only references		Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample

Original source ↗

Additional file 2 Table S2, column 'NeuSomatic-S SEQC-WGS-GT-50', SNVs section

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Genome Biology 23:12, published 2022-01-07; PMC8740374 full-text XML
Retrieved: 2026-10-10T06:04:11Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: 78dbe540c2558585bc7537e0e6563706fdaa329b2708e5dc82b77074379b4a6e

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Comparison: aggregation
Per replicate pair, plus the printed average over 21
Context-only references		Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf)

Original source ↗

Additional file 2 Table S2, column 'NeuSomatic-S SEQC-WGS-GT-50', SNVs section

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 13059_2021_2592_MOESM2_ESM.pdf
Retrieved: 2026-10-10T06:04:16Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: 10a109d80f6f49446ea84bd9f7f6b31c20d634516c8666376ac8a8f51f3236d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Comparison: budget
Not reported
Context-only references		Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample

Original source ↗

Additional file 2 Table S2, column 'NeuSomatic-S SEQC-WGS-GT-50', SNVs section

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Genome Biology 23:12, published 2022-01-07; PMC8740374 full-text XML
Retrieved: 2026-10-10T06:04:11Z

missing or unspecified

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.budget

Source artifact SHA-256: 78dbe540c2558585bc7537e0e6563706fdaa329b2708e5dc82b77074379b4a6e

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Comparison: budget
Not reported
Context-only references		Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf)

Original source ↗

Additional file 2 Table S2, column 'NeuSomatic-S SEQC-WGS-GT-50', SNVs section

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 13059_2021_2592_MOESM2_ESM.pdf
Retrieved: 2026-10-10T06:04:16Z

missing or unspecified

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.budget

Source artifact SHA-256: 10a109d80f6f49446ea84bd9f7f6b31c20d634516c8666376ac8a8f51f3236d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Comparison: dataset version
Not reported
Context-only references		Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample

Original source ↗

Additional file 2 Table S2, column 'NeuSomatic-S SEQC-WGS-GT-50', SNVs section

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Genome Biology 23:12, published 2022-01-07; PMC8740374 full-text XML
Retrieved: 2026-10-10T06:04:11Z

missing or unspecified

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.dataset_version

Source artifact SHA-256: 78dbe540c2558585bc7537e0e6563706fdaa329b2708e5dc82b77074379b4a6e

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Comparison: dataset version
Not reported
Context-only references		Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf)

Original source ↗

Additional file 2 Table S2, column 'NeuSomatic-S SEQC-WGS-GT-50', SNVs section

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 13059_2021_2592_MOESM2_ESM.pdf
Retrieved: 2026-10-10T06:04:16Z

missing or unspecified

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.dataset_version

Source artifact SHA-256: 10a109d80f6f49446ea84bd9f7f6b31c20d634516c8666376ac8a8f51f3236d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Comparison: inputs
Tumour and matched normal WGS BAM files (BWA-MEM)
Context-only references		Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample

Original source ↗

Additional file 2 Table S2, column 'NeuSomatic-S SEQC-WGS-GT-50', SNVs section

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Genome Biology 23:12, published 2022-01-07; PMC8740374 full-text XML
Retrieved: 2026-10-10T06:04:11Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.inputs

Source artifact SHA-256: 78dbe540c2558585bc7537e0e6563706fdaa329b2708e5dc82b77074379b4a6e

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Comparison: inputs
Tumour and matched normal WGS BAM files (BWA-MEM)
Context-only references		Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf)

Original source ↗

Additional file 2 Table S2, column 'NeuSomatic-S SEQC-WGS-GT-50', SNVs section

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 13059_2021_2592_MOESM2_ESM.pdf
Retrieved: 2026-10-10T06:04:16Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.inputs

Source artifact SHA-256: 10a109d80f6f49446ea84bd9f7f6b31c20d634516c8666376ac8a8f51f3236d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

All evidence (JSONL) (gzip)How to read the evidence

Sources and history

Release 2026-10-10-cbb3da59bc08 · Record review: source checked

2 source records and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: somatic-neusomatic-20261010-eval-sahraeian2022-neusomatic-s-seqc-wgs-gt-50-wgs-snv

areas
dna-genomes
contexts
clinical_research
origin
author_reported
protocol
somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv
version
Primary source as retrieved 2026-10-10
comparison
protocol id: somatic-neusomatic-20261010-protocol-sahraeian2022-wgs-snv; dataset version: Not reported; split: Held-out 50% of the high-confidence genome; population: 21 tumour-normal WGS replicate pairs (labels WGS_<site>_T/N_<n>, site codes EA, FD, IL, LL, NC, NS, NV) on HiSeq X Ten, HiSeq 4000 and NovaSeq; inputs: Tumour and matched normal WGS BAM files (BWA-MEM); adaptation: Not reported; metric implementation: F1 (%) of PASS calls against the SEQC2 truth set, exact match; aggregation: Per replicate pair, plus the printed average over 21; budget: Not reported
source locator
Additional file 2 Table S2, column 'NeuSomatic-S SEQC-WGS-GT-50', SNVs section
missing metadata
comparison.dataset version: reason: unreported
evidence overlap
Trained on the test cell line: the SEQC-WGS-GT-50 model was trained on HCC1395/HCC1395BL WGS replicates with the SEQC2 truth set in the other 50% of the high-confidence genome (Methods). The scored region is held out, but the cell line, truth set and possibly the replicate pairs are the same. Scored on WGS replicate pairs from the set the SEQC2 models were trained on (seven pairs from six centres plus a merged NovaSeq pair; spike-in models on HCC1395BL replicates from four sites); the paper does not say which of the 21 pairs.
Related records

Suggest a correction