Configuration

NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)

NeuSomatic-S SEQC-WGS-GT-50 as run in the cited comparison.

Overview

NeuSomatic: Neural-network somatic SNV and indel caller; in one linked comparison it was run in ensemble mode over other callers' output.

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

Evaluations and results

6 evaluations · 154 results. Different protocols are not a single leaderboard.

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: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 library preparation and DNA input, indel F1 (Sahraeian et al. 2022 Table S4) Dataset: SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	63.9% F1 (INDELs, average over the 6 library 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 library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA), INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-indel 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 S4, INDELs 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 library preparation and DNA input, indel F1 (Sahraeian et al. 2022 Table S4) Dataset: SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	74.9% F1 (INDELs, tumour LBP_Nextera_T_100ng with normal LBP_Nextera_N_100ng) 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 library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA), INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-indel 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 S4, INDELs section, row 'LBP_Nextera_T_100ng vs LBP_Nextera_N_100ng', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 library preparation and DNA input, indel F1 (Sahraeian et al. 2022 Table S4) Dataset: SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	76% F1 (INDELs, tumour LBP_Nextera_T_10ng with normal LBP_Nextera_N_10ng) 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 library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA), INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-indel 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 S4, INDELs section, row 'LBP_Nextera_T_10ng vs LBP_Nextera_N_10ng', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 library preparation and DNA input, indel F1 (Sahraeian et al. 2022 Table S4) Dataset: SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	68.4% F1 (INDELs, tumour LBP_Nextera_T_1ng with normal LBP_Nextera_N_1ng) 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 library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA), INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-indel 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 S4, INDELs section, row 'LBP_Nextera_T_1ng vs LBP_Nextera_N_1ng', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 library preparation and DNA input, indel F1 (Sahraeian et al. 2022 Table S4) Dataset: SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	72.1% F1 (INDELs, tumour LBP_TruSeq_T_100ng with normal LBP_TruSeq_N_100ng) 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 library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA), INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-indel 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 S4, INDELs section, row 'LBP_TruSeq_T_100ng vs LBP_TruSeq_N_100ng', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 library preparation and DNA input, indel F1 (Sahraeian et al. 2022 Table S4) Dataset: SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	65.8% F1 (INDELs, tumour LBP_TruSeq_T_10ng with normal LBP_TruSeq_N_10ng) 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 library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA), INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-indel 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 S4, INDELs section, row 'LBP_TruSeq_T_10ng vs LBP_TruSeq_N_10ng', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 library preparation and DNA input, indel F1 (Sahraeian et al. 2022 Table S4) Dataset: SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	26% F1 (INDELs, tumour LBP_TruSeq_T_1ng with normal LBP_TruSeq_N_1ng) 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 library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA), INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-indel 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 S4, INDELs section, row 'LBP_TruSeq_T_1ng vs LBP_TruSeq_N_1ng', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4) Dataset: SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	79.4% F1 (SNVs, average over the 6 library 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 library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA), SNVs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-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 S4, 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 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4) Dataset: SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	91.8% F1 (SNVs, tumour LBP_Nextera_T_100ng with normal LBP_Nextera_N_100ng) 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 library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA), SNVs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-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 S4, SNVs section, row 'LBP_Nextera_T_100ng vs LBP_Nextera_N_100ng', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4) Dataset: SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	93.4% F1 (SNVs, tumour LBP_Nextera_T_10ng with normal LBP_Nextera_N_10ng) 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 library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA), SNVs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-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 S4, SNVs section, row 'LBP_Nextera_T_10ng vs LBP_Nextera_N_10ng', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4) Dataset: SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	90.6% F1 (SNVs, tumour LBP_Nextera_T_1ng with normal LBP_Nextera_N_1ng) 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 library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA), SNVs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-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 S4, SNVs section, row 'LBP_Nextera_T_1ng vs LBP_Nextera_N_1ng', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4) Dataset: SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	89.2% F1 (SNVs, tumour LBP_TruSeq_T_100ng with normal LBP_TruSeq_N_100ng) 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 library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA), SNVs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-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 S4, SNVs section, row 'LBP_TruSeq_T_100ng vs LBP_TruSeq_N_100ng', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4) Dataset: SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	85.5% F1 (SNVs, tumour LBP_TruSeq_T_10ng with normal LBP_TruSeq_N_10ng) 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 library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA), SNVs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-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 S4, SNVs section, row 'LBP_TruSeq_T_10ng vs LBP_TruSeq_N_10ng', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4) Dataset: SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	25.6% F1 (SNVs, tumour LBP_TruSeq_T_1ng with normal LBP_TruSeq_N_1ng) 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 library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA), SNVs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-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 S4, SNVs section, row 'LBP_TruSeq_T_1ng vs LBP_TruSeq_N_1ng', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 tumour purity, coverage and normal contamination, indel F1 (Sahraeian et al. 2022 Table S3) Dataset: SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	50.7% F1 (INDELs, average over the 47 purity-coverage 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 tumour-normal titration, INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-titration-indel 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 S3, INDELs 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 tumour purity, coverage and normal contamination, indel F1 (Sahraeian et al. 2022 Table S3) Dataset: SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	34.4% F1 (INDELs, tumour SPP_100x_10%T with normal SPP_100x_100%N) 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 tumour-normal titration, INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-titration-indel 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 S3, INDELs section, row 'SPP_100x_10%T vs SPP_100x_100%N', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 tumour purity, coverage and normal contamination, indel F1 (Sahraeian et al. 2022 Table S3) Dataset: SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	83.8% F1 (INDELs, tumour SPP_100x_100%T with normal SPP_100x_100%N) 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 tumour-normal titration, INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-titration-indel 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 S3, INDELs section, row 'SPP_100x_100%T vs SPP_100x_100%N', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 tumour purity, coverage and normal contamination, indel F1 (Sahraeian et al. 2022 Table S3) Dataset: SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	61.2% F1 (INDELs, tumour SPP_100x_20%T with normal SPP_100x_100%N) 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 tumour-normal titration, INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-titration-indel 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 S3, INDELs section, row 'SPP_100x_20%T vs SPP_100x_100%N', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 tumour purity, coverage and normal contamination, indel F1 (Sahraeian et al. 2022 Table S3) Dataset: SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	15.8% F1 (INDELs, tumour SPP_100x_5%T with normal SPP_100x_100%N) 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 tumour-normal titration, INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-titration-indel 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 S3, INDELs section, row 'SPP_100x_5%T vs SPP_100x_100%N', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 tumour purity, coverage and normal contamination, indel F1 (Sahraeian et al. 2022 Table S3) Dataset: SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	80.4% F1 (INDELs, tumour SPP_100x_50%T with normal SPP_100x_100%N) 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 tumour-normal titration, INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-titration-indel 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 S3, INDELs section, row 'SPP_100x_50%T vs SPP_100x_100%N', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 tumour purity, coverage and normal contamination, indel F1 (Sahraeian et al. 2022 Table S3) Dataset: SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	84% F1 (INDELs, tumour SPP_100x_75%T with normal SPP_100x_100%N) 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 tumour-normal titration, INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-titration-indel 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 S3, INDELs section, row 'SPP_100x_75%T vs SPP_100x_100%N', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 tumour purity, coverage and normal contamination, indel F1 (Sahraeian et al. 2022 Table S3) Dataset: SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	0.7% F1 (INDELs, tumour SPP_10x_10%T with normal SPP_10x_100%N) 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 tumour-normal titration, INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-titration-indel 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 S3, INDELs section, row 'SPP_10x_10%T vs SPP_10x_100%N', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 tumour purity, coverage and normal contamination, indel F1 (Sahraeian et al. 2022 Table S3) Dataset: SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	31.1% F1 (INDELs, tumour SPP_10x_100%T with normal SPP_10x_100%N) 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 tumour-normal titration, INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-titration-indel 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 S3, INDELs section, row 'SPP_10x_100%T vs SPP_10x_100%N', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 tumour purity, coverage and normal contamination, indel F1 (Sahraeian et al. 2022 Table S3) Dataset: SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	3.5% F1 (INDELs, tumour SPP_10x_20%T with normal SPP_10x_100%N) 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 tumour-normal titration, INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-titration-indel 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 S3, INDELs section, row 'SPP_10x_20%T vs SPP_10x_100%N', column 'NeuSomatic-S SEQC-WGS-GT-50'
Configuration: NeuSomatic-S SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	Protocol: SEQC2 HCC1395 tumour purity, coverage and normal contamination, indel F1 (Sahraeian et al. 2022 Table S3) Dataset: SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	0.3% F1 (INDELs, tumour SPP_10x_5%T with normal SPP_10x_100%N) 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 tumour-normal titration, INDELs (Sahraeian et al. 2022) somatic-neusomatic-20261010-protocol-sahraeian2022-titration-indel 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 S3, INDELs section, row 'SPP_10x_5%T vs SPP_10x_100%N', column 'NeuSomatic-S SEQC-WGS-GT-50'

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

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 2026-10-10-cbb3da59bc08
Property and statement	Original source and location	Review and provenance

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

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 history

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample · Original source · Genome Biology 23:12, published 2022-01-07; PMC8740374 full-text XML
Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Original source · 13059_2021_2592_MOESM2_ESM.pdf

Download this release (gzip)

Technical metadata and extraction receipts

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

areas: dna-genomes
contexts: clinical_research
method types: supervised_machine_learning
reported name: NeuSomatic-S SEQC-WGS-GT-50
foundation model eligible: false
version: 0.1.4
checkpoint: SEQC-WGS-GT-50 model (standalone mode), as named in Additional file 2 Table S1
training overlap: Real HCC1395/HCC1395BL WGS replicate pairs with the SEQC2 truth set: seven pairs from six centres (HiSeq and NovaSeq, 40x-95x) and one pair of about 390x merged from nine Illumina NovaSeq replicates, each also as 95% pure normal and 10% tumour purity mixtures; 24 pairs, in 50% of the high-confidence genome. The other 50% is the evaluation region.
protocol: Standalone mode: alignment-scanning candidates only; preprocessing -scan_maf 0.01 -min_mapq 10 -snp_min_af 0.03 -snp_min_bq 15 -snp_min_ao 3 -ins_min_af 0.02 -del_min_af 0.02
source locator: Methods 'Somatic mutation detection algorithms'; Additional file 2 Table S1 and Tables S2-S4 column headers

Related records

Suggest a correction