Contested result

MuSE and NeuSomatic: A benchmarking study of individual somatic variant callers and voting-based ensembles for whole-exome sequencing reverses the order

Low severity
Not yet reviewed
Ordering reversal
Different tasks across studies

A benchmarking study of individual somatic variant callers and voting-based ensembles for whole-exome sequencing ranks MuSE above NeuSomatic in 3 of 3 comparisons; other studies rank NeuSomatic above MuSE in 86 of 100.

An automatic lead, not a finding of error. The results below are shown as published, everywhere on the site, until a reviewer decides otherwise.

Which studies agree

2 papers rank NeuSomatic above MuSE in 86 of their 101 comparisons and MuSE higher in 14; 1 is a tie. A benchmarking study of individual… ranks MuSE above NeuSomatic in all 3 comparisons that are not ties (3 are ties).

Rank NeuSomatic higher (1): Achieving robust somatic mutation…
Rank MuSE higher (1): A benchmarking study of individual… (disagrees)
Mixed (1): SomaticCombiner

Each paper sits where at least two thirds of its comparisons point; Mixed means neither model reaches two thirds. The larger, outlined dot is the paper that disagrees.

NeuSomatic higherTieMuSE higherNumbers are counts of comparisons; the outlined bar is the paper that disagrees.

Papers compared (3)
Paper	Role	Ranks NeuSomatic higher	Ranks MuSE higher	Ties
A benchmarking study of individual somatic variant callers and voting-based ensembles for whole-exome sequencing and 1 more record · DOI	Disagrees	0	3	3
Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample and 1 more record · DOI	Agrees	77	0	0
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach and 1 more record · DOI	Agrees	9	14	1

Comparisons in A benchmarking study of individual… (6)

Protocol	Dataset	Metric	NeuSomatic	MuSE	Higher
SEQC2 HCC1395 WES validation sample, somatic SNVs (Guille et al. 2025 Table S7)	SEQC2 HCC1395/HCC1395BL WES, Fudan replicate (WES_FD_T_1), high-confidence regions	F1 (SNV only), fraction	0.835	0.84	Tie
SEQC2 HCC1395 WES validation sample, somatic SNVs (Guille et al. 2025 Table S7)	SEQC2 HCC1395/HCC1395BL WES, Fudan replicate (WES_FD_T_1), high-confidence regions	False positives (SNV only), count	21	6	MuSE
SEQC2 HCC1395 WES validation sample, somatic SNVs (Guille et al. 2025 Table S7)	SEQC2 HCC1395/HCC1395BL WES, Fudan replicate (WES_FD_T_1), high-confidence regions	False positive rate (SNV only), fraction	1.39e-7	3.98e-8	MuSE
SEQC2 HCC1395 WES validation sample, somatic SNVs (Guille et al. 2025 Table S7)	SEQC2 HCC1395/HCC1395BL WES, Fudan replicate (WES_FD_T_1), high-confidence regions	Precision (SNV only), fraction	0.976	0.993	MuSE
SEQC2 HCC1395 WES validation sample, somatic SNVs (Guille et al. 2025 Table S7)	SEQC2 HCC1395/HCC1395BL WES, Fudan replicate (WES_FD_T_1), high-confidence regions	Recall (SNV only), fraction	0.729	0.728	Tie
SEQC2 HCC1395 WES validation sample, somatic SNVs (Guille et al. 2025 Table S7)	SEQC2 HCC1395/HCC1395BL WES, Fudan replicate (WES_FD_T_1), high-confidence regions	True positives (SNV only), count	846	844	Tie

Comparisons in Achieving robust somatic mutation… (77)

Protocol	Dataset	Metric	NeuSomatic	MuSE	Higher
SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	F1 (SNVs, average over the 6 library pairs as printed), percent	85.8	76.2	NeuSomatic
SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	F1 (SNVs, tumour LBP_Nextera_T_100ng with normal LBP_Nextera_N_100ng), percent	95.3	89	NeuSomatic
SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	F1 (SNVs, tumour LBP_Nextera_T_10ng with normal LBP_Nextera_N_10ng), percent	95.5	90	NeuSomatic
SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	F1 (SNVs, tumour LBP_Nextera_T_1ng with normal LBP_Nextera_N_1ng), percent	92.3	86.4	NeuSomatic
SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	F1 (SNVs, tumour LBP_TruSeq_T_100ng with normal LBP_TruSeq_N_100ng), percent	93.1	86.3	NeuSomatic
SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	F1 (SNVs, tumour LBP_TruSeq_T_10ng with normal LBP_TruSeq_N_10ng), percent	89	82.2	NeuSomatic
SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	SEQC2 HCC1395/HCC1395BL library-preparation replicates (TruSeq-Nano and Nextera Flex, 1-100 ng DNA)	F1 (SNVs, tumour LBP_TruSeq_T_1ng with normal LBP_TruSeq_N_1ng), percent	51.3	23.1	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, average over the 47 purity-coverage pairs as printed), percent	70.8	51.7	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_100x_10%T with normal SPP_100x_100%N), percent	63.8	25	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_100x_100%T with normal SPP_100x_100%N), percent	98.2	92.6	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_100x_20%T with normal SPP_100x_100%N), percent	84.5	59.4	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_100x_5%T with normal SPP_100x_100%N), percent	34	3.7	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_100x_50%T with normal SPP_100x_100%N), percent	94.1	85.5	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_100x_75%T with normal SPP_100x_100%N), percent	96.9	90.1	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_10x_10%T with normal SPP_10x_100%N), percent	6.8	3.8	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_10x_100%T with normal SPP_10x_100%N), percent	71.2	49.6	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_10x_20%T with normal SPP_10x_100%N), percent	18.5	12.3	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_10x_5%T with normal SPP_10x_100%N), percent	2.3	1.1	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_10x_50%T with normal SPP_10x_100%N), percent	51.4	36.9	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_10x_75%T with normal SPP_10x_100%N), percent	65.4	47	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_200x_10%T with normal SPP_200x_100%N), percent	80.1	40.4	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_200x_100%T with normal SPP_200x_100%N), percent	98.8	95	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_200x_20%T with normal SPP_200x_100%N), percent	90.7	72	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_200x_5%T with normal SPP_200x_100%N), percent	58.8	8.3	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_200x_50%T with normal SPP_200x_100%N), percent	96.6	88.7	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_200x_75%T with normal SPP_200x_100%N), percent	97.9	92.5	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_300x_10%T with normal SPP_300x_100%N), percent	86	46.9	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_300x_100%T with normal SPP_300x_100%N), percent	98.9	96.7	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_300x_20%T with normal SPP_300x_100%N), percent	93.1	76.8	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_300x_5%T with normal SPP_300x_100%N), percent	72.1	13.2	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_300x_50%T with normal SPP_300x_100%N), percent	97.6	90.2	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_300x_75%T with normal SPP_300x_100%N), percent	98.6	93.8	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_30x_10%T with normal SPP_30x_100%N), percent	27	10	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_30x_100%T with normal SPP_30x_100%N), percent	92	84.5	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_30x_20%T with normal SPP_30x_100%N), percent	56.1	34.1	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_30x_5%T with normal SPP_30x_100%N), percent	9.2	1.9	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_30x_50%T with normal SPP_30x_100%N), percent	83.8	71.8	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_30x_75%T with normal SPP_30x_100%N), percent	89.6	81.2	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_50x_10%T with normal SPP_50x_100%N), percent	42.1	14.7	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_50x_100%T with normal SPP_50x_100%N), percent	95	88.6	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_50x_20%T with normal SPP_50x_100%N), percent	70.5	44.7	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_50x_5%T with normal SPP_50x_100%N), percent	16.2	2.3	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_50x_50%T with normal SPP_50x_100%N), percent	89.9	79.3	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_50x_75%T with normal SPP_50x_100%N), percent	93.3	85.9	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_80x_10%T with normal SPP_80x_100%N), percent	57	20.8	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_80x_10%T with normal SPP_80x_95%N), percent	37.7	2.2	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_80x_100%T with normal SPP_80x_100%N), percent	97.7	91.6	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_80x_100%T with normal SPP_80x_95%N), percent	97	59.5	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_80x_20%T with normal SPP_80x_100%N), percent	80	55	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_80x_20%T with normal SPP_80x_95%N), percent	67.8	12.2	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_80x_5%T with normal SPP_80x_100%N), percent	27.5	3.3	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_80x_50%T with normal SPP_80x_100%N), percent	93.4	83.9	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_80x_50%T with normal SPP_80x_95%N), percent	91	39.8	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_80x_75%T with normal SPP_80x_100%N), percent	95.9	88.9	NeuSomatic
SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS	F1 (SNVs, tumour SPP_80x_75%T with normal SPP_80x_95%N), percent	94.8	52.3	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, average over the 21 replicate pairs as printed), percent	94.7	88.1	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_EA_T_1 with normal WGS_EA_N_1), percent	96.1	90.2	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_FD_T_1 with normal WGS_FD_N_1), percent	93.7	88	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_FD_T_2 with normal WGS_FD_N_2), percent	94.1	88.6	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_FD_T_3 with normal WGS_FD_N_3), percent	93.9	88.4	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_IL_T_1 with normal WGS_IL_N_1), percent	96.8	90.6	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_IL_T_2 with normal WGS_IL_N_2), percent	95.3	89	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_IL_T_3 with normal WGS_IL_N_3), percent	95.2	88.7	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_LL_T_1 with normal WGS_LL_N_1), percent	88.8	80.6	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_NC_T_1 with normal WGS_NC_N_1), percent	93.7	88	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_NS_T_1 with normal WGS_NS_N_1), percent	95.7	88.4	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_NS_T_2 with normal WGS_NS_N_2), percent	92.7	85.9	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_NS_T_3 with normal WGS_NS_N_3), percent	93.9	87.6	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_NS_T_4 with normal WGS_NS_N_4), percent	95.6	87.6	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_NS_T_5 with normal WGS_NS_N_5), percent	93.4	84.8	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_NS_T_6 with normal WGS_NS_N_6), percent	95.9	88.4	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_NS_T_7 with normal WGS_NS_N_7), percent	95.3	84.9	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_NS_T_8 with normal WGS_NS_N_8), percent	92.6	86.2	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_NS_T_9 with normal WGS_NS_N_9), percent	93.5	87.2	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_NV_T_1 with normal WGS_NV_N_1), percent	97.8	92.2	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_NV_T_2 with normal WGS_NV_N_2), percent	97.8	92.3	NeuSomatic
SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	SEQC2 HCC1395/HCC1395BL WGS replicate pairs from multiple sequencing centres	F1 (SNVs, tumour WGS_NV_T_3 with normal WGS_NV_N_3), percent	97.8	92.2	NeuSomatic

Comparisons in SomaticCombiner (24)

Protocol	Dataset	Metric	NeuSomatic	MuSE	Higher
AML tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Acute myeloid leukaemia tumour-normal WGS with platinum somatic list	F1 (SNV only), fraction	0.799	0.786	NeuSomatic
AML tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Acute myeloid leukaemia tumour-normal WGS with platinum somatic list	Precision (SNV only), fraction	0.705	0.713	MuSE
AML tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Acute myeloid leukaemia tumour-normal WGS with platinum somatic list	Recall (SNV only), fraction	0.931	0.876	NeuSomatic
CLL tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Chronic lymphocytic leukaemia tumour-normal WGS with curated somatic calls	F1 (SNV only), fraction	0.24	0.647	MuSE
CLL tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Chronic lymphocytic leukaemia tumour-normal WGS with curated somatic calls	Precision (SNV only), fraction	0.137	0.549	MuSE
CLL tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Chronic lymphocytic leukaemia tumour-normal WGS with curated somatic calls	Recall (SNV only), fraction	0.982	0.788	NeuSomatic
COLO829 cell line somatic SNVs, WGS (Wang et al. 2020 Table S1)	COLO829 metastatic melanoma cell line tumour-normal WGS with curated somatic calls	F1 (SNV only), fraction	0.881	0.931	MuSE
COLO829 cell line somatic SNVs, WGS (Wang et al. 2020 Table S1)	COLO829 metastatic melanoma cell line tumour-normal WGS with curated somatic calls	Precision (SNV only), fraction	0.8	0.89	MuSE
COLO829 cell line somatic SNVs, WGS (Wang et al. 2020 Table S1)	COLO829 metastatic melanoma cell line tumour-normal WGS with curated somatic calls	Recall (SNV only), fraction	0.982	0.976	Tie
DREAM synthetic set 1 somatic SNVs, WGS (Wang et al. 2020 Table S1)	ICGC-TCGA DREAM synthetic set 1 (WGS)	F1 (SNV only), fraction	0.733	0.911	MuSE
DREAM synthetic set 1 somatic SNVs, WGS (Wang et al. 2020 Table S1)	ICGC-TCGA DREAM synthetic set 1 (WGS)	Precision (SNV only), fraction	0.584	0.855	MuSE
DREAM synthetic set 1 somatic SNVs, WGS (Wang et al. 2020 Table S1)	ICGC-TCGA DREAM synthetic set 1 (WGS)	Recall (SNV only), fraction	0.987	0.975	NeuSomatic
DREAM synthetic set 2 somatic SNVs, WGS (Wang et al. 2020 Table S1)	ICGC-TCGA DREAM synthetic set 2 (WGS)	F1 (SNV only), fraction	0.705	0.938	MuSE
DREAM synthetic set 2 somatic SNVs, WGS (Wang et al. 2020 Table S1)	ICGC-TCGA DREAM synthetic set 2 (WGS)	Precision (SNV only), fraction	0.548	0.907	MuSE
DREAM synthetic set 2 somatic SNVs, WGS (Wang et al. 2020 Table S1)	ICGC-TCGA DREAM synthetic set 2 (WGS)	Recall (SNV only), fraction	0.991	0.971	NeuSomatic
DREAM synthetic set 3 somatic SNVs, WGS (Wang et al. 2020 Table S1)	ICGC-TCGA DREAM synthetic set 3 (WGS)	F1 (SNV only), fraction	0.848	0.918	MuSE
DREAM synthetic set 3 somatic SNVs, WGS (Wang et al. 2020 Table S1)	ICGC-TCGA DREAM synthetic set 3 (WGS)	Precision (SNV only), fraction	0.758	0.959	MuSE
DREAM synthetic set 3 somatic SNVs, WGS (Wang et al. 2020 Table S1)	ICGC-TCGA DREAM synthetic set 3 (WGS)	Recall (SNV only), fraction	0.966	0.88	NeuSomatic
DREAM synthetic set 4 somatic SNVs, WGS (Wang et al. 2020 Table S1)	ICGC-TCGA DREAM synthetic set 4 (WGS)	F1 (SNV only), fraction	0.859	0.673	NeuSomatic
DREAM synthetic set 4 somatic SNVs, WGS (Wang et al. 2020 Table S1)	ICGC-TCGA DREAM synthetic set 4 (WGS)	Precision (SNV only), fraction	0.849	0.869	MuSE
DREAM synthetic set 4 somatic SNVs, WGS (Wang et al. 2020 Table S1)	ICGC-TCGA DREAM synthetic set 4 (WGS)	Recall (SNV only), fraction	0.881	0.55	NeuSomatic
MB brain tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Malignant paediatric cerebellar brain tumour (MB) tumour-normal WGS with curated somatic calls	F1 (SNV only), fraction	0.558	0.806	MuSE
MB brain tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Malignant paediatric cerebellar brain tumour (MB) tumour-normal WGS with curated somatic calls	Precision (SNV only), fraction	0.389	0.773	MuSE
MB brain tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Malignant paediatric cerebellar brain tumour (MB) tumour-normal WGS with curated somatic calls	Recall (SNV only), fraction	0.987	0.842	NeuSomatic

What disagrees

Other studies: rank NeuSomatic above MuSE in 86 of 100 comparisons
This study: ranks MuSE above NeuSomatic in 3 of 3 comparisons

Compared: MuSE, NeuSomatic
Study that disagrees: A benchmarking study of individual somatic variant callers and voting-based ensembles for whole-exome sequencing, Guille et al. 2025, Supplementary Table S7 (validation dataset)
Other studies: SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach, Wang et al. 2020, Supplementary Tables (somatic caller performance), 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)
Rule: Ordering reversal; different tasks across studies
Model identity: Matched across studies partly through links not yet reviewed

The compared numbers

Each value links to its result record and source. Compare values within one protocol; the rule compares rankings, not raw values across protocols.

In the study that disagrees (6)
Study	Tool	Protocol or benchmark	Metric	Value
A benchmarking study of individual somatic variant callers and voting-based ensembles for whole-exome sequencing; Guille et al. 2025, Supplementary Table S7 (validation dataset)	Muse 2.0 (Guille et al. 2025)	SEQC2 HCC1395 WES validation sample, somatic SNVs (Guille et al. 2025 Table S7)	False positives (SNV only)	6
A benchmarking study of individual somatic variant callers and voting-based ensembles for whole-exome sequencing; Guille et al. 2025, Supplementary Table S7 (validation dataset)	Muse 2.0 (Guille et al. 2025)	SEQC2 HCC1395 WES validation sample, somatic SNVs (Guille et al. 2025 Table S7)	False positive rate (SNV only)	3.98e-8
A benchmarking study of individual somatic variant callers and voting-based ensembles for whole-exome sequencing; Guille et al. 2025, Supplementary Table S7 (validation dataset)	Muse 2.0 (Guille et al. 2025)	SEQC2 HCC1395 WES validation sample, somatic SNVs (Guille et al. 2025 Table S7)	Precision (SNV only)	0.993
A benchmarking study of individual somatic variant callers and voting-based ensembles for whole-exome sequencing; Guille et al. 2025, Supplementary Table S7 (validation dataset)	NeuSomatic 0.2.1 (Guille et al. 2025)	SEQC2 HCC1395 WES validation sample, somatic SNVs (Guille et al. 2025 Table S7)	False positives (SNV only)	21
A benchmarking study of individual somatic variant callers and voting-based ensembles for whole-exome sequencing; Guille et al. 2025, Supplementary Table S7 (validation dataset)	NeuSomatic 0.2.1 (Guille et al. 2025)	SEQC2 HCC1395 WES validation sample, somatic SNVs (Guille et al. 2025 Table S7)	False positive rate (SNV only)	1.39e-7
A benchmarking study of individual somatic variant callers and voting-based ensembles for whole-exome sequencing; Guille et al. 2025, Supplementary Table S7 (validation dataset)	NeuSomatic 0.2.1 (Guille et al. 2025)	SEQC2 HCC1395 WES validation sample, somatic SNVs (Guille et al. 2025 Table S7)	Precision (SNV only)	0.976

In the other studies (209 results)

In the other studies
Study	Tool	Protocol or benchmark	Metric	Value
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	AML tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.786
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	AML tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.713
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	AML tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Recall (SNV only)	0.876
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	CLL tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.647
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	CLL tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.549
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	CLL tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Recall (SNV only)	0.788
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	COLO829 cell line somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.931
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	COLO829 cell line somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.89
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	DREAM synthetic set 1 somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.911
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	DREAM synthetic set 1 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.855
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	DREAM synthetic set 1 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Recall (SNV only)	0.975
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	DREAM synthetic set 2 somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.938
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	DREAM synthetic set 2 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.907
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	DREAM synthetic set 2 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Recall (SNV only)	0.971
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	DREAM synthetic set 3 somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.918
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	DREAM synthetic set 3 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.959
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	DREAM synthetic set 3 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Recall (SNV only)	0.88
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	DREAM synthetic set 4 somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.673
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	DREAM synthetic set 4 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.869
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	DREAM synthetic set 4 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Recall (SNV only)	0.55
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	MB brain tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.806
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	MB brain tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.773
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	MuSE v1.0rc (Wang et al. 2020)	MB brain tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Recall (SNV only)	0.842
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, all calls (Wang et al. 2020)	AML tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Recall (SNV only)	0.931
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, all calls (Wang et al. 2020)	CLL tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Recall (SNV only)	0.982
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, all calls (Wang et al. 2020)	DREAM synthetic set 1 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Recall (SNV only)	0.987
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, all calls (Wang et al. 2020)	DREAM synthetic set 2 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Recall (SNV only)	0.991
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, all calls (Wang et al. 2020)	DREAM synthetic set 3 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Recall (SNV only)	0.966
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, all calls (Wang et al. 2020)	DREAM synthetic set 4 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Recall (SNV only)	0.881
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, all calls (Wang et al. 2020)	MB brain tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Recall (SNV only)	0.987
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	AML tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.799
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	AML tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.705
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	CLL tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.24
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	CLL tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.137
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	COLO829 cell line somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.881
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	COLO829 cell line somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.8
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	DREAM synthetic set 1 somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.733
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	DREAM synthetic set 1 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.584
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	DREAM synthetic set 2 somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.705
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	DREAM synthetic set 2 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.548
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	DREAM synthetic set 3 somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.848
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	DREAM synthetic set 3 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.758
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	DREAM synthetic set 4 somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.859
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	DREAM synthetic set 4 somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.849
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	MB brain tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	F1 (SNV only)	0.558
SomaticCombiner: improving the performance of somatic variant calling based on evaluation tests and a consensus approach; Wang et al. 2020, Supplementary Tables (somatic caller performance)	NeuSomatic v0.2.1 ensemble mode, DREAM3 model, PASS calls (Wang et al. 2020)	MB brain tumour somatic SNVs, WGS (Wang et al. 2020 Table S1)	Precision (SNV only)	0.389
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, average over the 6 library pairs as printed)	76.2
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, tumour LBP_Nextera_T_100ng with normal LBP_Nextera_N_100ng)	89
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, tumour LBP_Nextera_T_10ng with normal LBP_Nextera_N_10ng)	90
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, tumour LBP_Nextera_T_1ng with normal LBP_Nextera_N_1ng)	86.4
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, tumour LBP_TruSeq_T_100ng with normal LBP_TruSeq_N_100ng)	86.3
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, tumour LBP_TruSeq_T_10ng with normal LBP_TruSeq_N_10ng)	82.2
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, tumour LBP_TruSeq_T_1ng with normal LBP_TruSeq_N_1ng)	23.1
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, average over the 47 purity-coverage pairs as printed)	51.7
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_100x_10%T with normal SPP_100x_100%N)	25
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_100x_100%T with normal SPP_100x_100%N)	92.6
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_100x_20%T with normal SPP_100x_100%N)	59.4
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_100x_5%T with normal SPP_100x_100%N)	3.7
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_100x_50%T with normal SPP_100x_100%N)	85.5
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_100x_75%T with normal SPP_100x_100%N)	90.1
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_10x_10%T with normal SPP_10x_100%N)	3.8
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_10x_100%T with normal SPP_10x_100%N)	49.6
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_10x_20%T with normal SPP_10x_100%N)	12.3
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_10x_5%T with normal SPP_10x_100%N)	1.1
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_10x_50%T with normal SPP_10x_100%N)	36.9
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_10x_75%T with normal SPP_10x_100%N)	47
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_200x_10%T with normal SPP_200x_100%N)	40.4
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_200x_100%T with normal SPP_200x_100%N)	95
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_200x_20%T with normal SPP_200x_100%N)	72
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_200x_5%T with normal SPP_200x_100%N)	8.3
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_200x_50%T with normal SPP_200x_100%N)	88.7
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_200x_75%T with normal SPP_200x_100%N)	92.5
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_300x_10%T with normal SPP_300x_100%N)	46.9
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_300x_100%T with normal SPP_300x_100%N)	96.7
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_300x_20%T with normal SPP_300x_100%N)	76.8
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_300x_5%T with normal SPP_300x_100%N)	13.2
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_300x_50%T with normal SPP_300x_100%N)	90.2
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_300x_75%T with normal SPP_300x_100%N)	93.8
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_30x_10%T with normal SPP_30x_100%N)	10
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_30x_100%T with normal SPP_30x_100%N)	84.5
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_30x_20%T with normal SPP_30x_100%N)	34.1
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_30x_5%T with normal SPP_30x_100%N)	1.9
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_30x_50%T with normal SPP_30x_100%N)	71.8
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_30x_75%T with normal SPP_30x_100%N)	81.2
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_50x_10%T with normal SPP_50x_100%N)	14.7
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_50x_100%T with normal SPP_50x_100%N)	88.6
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_50x_20%T with normal SPP_50x_100%N)	44.7
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_50x_5%T with normal SPP_50x_100%N)	2.3
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_50x_50%T with normal SPP_50x_100%N)	79.3
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_50x_75%T with normal SPP_50x_100%N)	85.9
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_10%T with normal SPP_80x_100%N)	20.8
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_10%T with normal SPP_80x_95%N)	2.2
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_100%T with normal SPP_80x_100%N)	91.6
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_100%T with normal SPP_80x_95%N)	59.5
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_20%T with normal SPP_80x_100%N)	55
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_20%T with normal SPP_80x_95%N)	12.2
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_5%T with normal SPP_80x_100%N)	3.3
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_50%T with normal SPP_80x_100%N)	83.9
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_50%T with normal SPP_80x_95%N)	39.8
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_75%T with normal SPP_80x_100%N)	88.9
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_75%T with normal SPP_80x_95%N)	52.3
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, average over the 21 replicate pairs as printed)	88.1
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_EA_T_1 with normal WGS_EA_N_1)	90.2
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_FD_T_1 with normal WGS_FD_N_1)	88
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_FD_T_2 with normal WGS_FD_N_2)	88.6
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_FD_T_3 with normal WGS_FD_N_3)	88.4
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_IL_T_1 with normal WGS_IL_N_1)	90.6
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_IL_T_2 with normal WGS_IL_N_2)	89
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_IL_T_3 with normal WGS_IL_N_3)	88.7
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_LL_T_1 with normal WGS_LL_N_1)	80.6
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NC_T_1 with normal WGS_NC_N_1)	88
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_1 with normal WGS_NS_N_1)	88.4
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_2 with normal WGS_NS_N_2)	85.9
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_3 with normal WGS_NS_N_3)	87.6
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_4 with normal WGS_NS_N_4)	87.6
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_5 with normal WGS_NS_N_5)	84.8
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_6 with normal WGS_NS_N_6)	88.4
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_7 with normal WGS_NS_N_7)	84.9
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_8 with normal WGS_NS_N_8)	86.2
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_9 with normal WGS_NS_N_9)	87.2
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NV_T_1 with normal WGS_NV_N_1)	92.2
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NV_T_2 with normal WGS_NV_N_2)	92.3
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)	MuSE v1.0rc (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NV_T_3 with normal WGS_NV_N_3)	92.2
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)	NeuSomatic DREAM3 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_5%T with normal SPP_80x_100%N)	27.5
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)	NeuSomatic-S DREAM3 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_10x_10%T with normal SPP_10x_100%N)	6.8
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)	NeuSomatic-S DREAM3 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_10x_5%T with normal SPP_10x_100%N)	2.3
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, average over the 6 library pairs as printed)	85.8
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, tumour LBP_Nextera_T_100ng with normal LBP_Nextera_N_100ng)	95.3
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, tumour LBP_Nextera_T_10ng with normal LBP_Nextera_N_10ng)	95.5
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, tumour LBP_Nextera_T_1ng with normal LBP_Nextera_N_1ng)	92.3
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, tumour LBP_TruSeq_T_100ng with normal LBP_TruSeq_N_100ng)	93.1
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, average over the 47 purity-coverage pairs as printed)	70.8
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_100x_100%T with normal SPP_100x_100%N)	98.2
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_100x_20%T with normal SPP_100x_100%N)	84.5
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_100x_50%T with normal SPP_100x_100%N)	94.1
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_100x_75%T with normal SPP_100x_100%N)	96.9
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_10x_100%T with normal SPP_10x_100%N)	71.2
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_10x_20%T with normal SPP_10x_100%N)	18.5
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_10x_50%T with normal SPP_10x_100%N)	51.4
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_10x_75%T with normal SPP_10x_100%N)	65.4
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_200x_100%T with normal SPP_200x_100%N)	98.8
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_200x_75%T with normal SPP_200x_100%N)	97.9
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_300x_100%T with normal SPP_300x_100%N)	98.9
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_300x_50%T with normal SPP_300x_100%N)	97.6
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_300x_75%T with normal SPP_300x_100%N)	98.6
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_30x_100%T with normal SPP_30x_100%N)	92
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_30x_20%T with normal SPP_30x_100%N)	56.1
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_30x_50%T with normal SPP_30x_100%N)	83.8
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_30x_75%T with normal SPP_30x_100%N)	89.6
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_50x_10%T with normal SPP_50x_100%N)	42.1
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_50x_20%T with normal SPP_50x_100%N)	70.5
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_50x_5%T with normal SPP_50x_100%N)	16.2
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_50x_50%T with normal SPP_50x_100%N)	89.9
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_50x_75%T with normal SPP_50x_100%N)	93.3
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_10%T with normal SPP_80x_95%N)	37.7
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_100%T with normal SPP_80x_100%N)	97.7
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_100%T with normal SPP_80x_95%N)	97
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_20%T with normal SPP_80x_95%N)	67.8
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_5%T with normal SPP_80x_100%N)	27.5
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_50%T with normal SPP_80x_100%N)	93.4
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_50%T with normal SPP_80x_95%N)	91
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_75%T with normal SPP_80x_100%N)	95.9
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_75%T with normal SPP_80x_95%N)	94.8
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, average over the 21 replicate pairs as printed)	94.7
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_EA_T_1 with normal WGS_EA_N_1)	96.1
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_FD_T_1 with normal WGS_FD_N_1)	93.7
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_FD_T_3 with normal WGS_FD_N_3)	93.9
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_IL_T_1 with normal WGS_IL_N_1)	96.8
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_IL_T_2 with normal WGS_IL_N_2)	95.3
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_IL_T_3 with normal WGS_IL_N_3)	95.2
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_LL_T_1 with normal WGS_LL_N_1)	88.8
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NC_T_1 with normal WGS_NC_N_1)	93.7
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_1 with normal WGS_NS_N_1)	95.7
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_2 with normal WGS_NS_N_2)	92.7
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_3 with normal WGS_NS_N_3)	93.9
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_4 with normal WGS_NS_N_4)	95.6
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_5 with normal WGS_NS_N_5)	93.4
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_6 with normal WGS_NS_N_6)	95.9
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_7 with normal WGS_NS_N_7)	95.3
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_8 with normal WGS_NS_N_8)	92.6
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NS_T_9 with normal WGS_NS_N_9)	93.5
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NV_T_1 with normal WGS_NV_N_1)	97.8
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NV_T_2 with normal WGS_NV_N_2)	97.8
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)	NeuSomatic SEQC-WGS-GT-50 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NV_T_3 with normal WGS_NV_N_3)	97.8
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)	NeuSomatic SEQC-WGS-GT50-SpikeWGS10 model (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, tumour LBP_Nextera_T_1ng with normal LBP_Nextera_N_1ng)	92.3
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)	NeuSomatic SEQC-WGS-GT50-SpikeWGS10 model (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, tumour LBP_TruSeq_T_10ng with normal LBP_TruSeq_N_10ng)	89
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)	NeuSomatic SEQC-WGS-GT50-SpikeWGS10 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_200x_100%T with normal SPP_200x_100%N)	98.8
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)	NeuSomatic SEQC-WGS-GT50-SpikeWGS10 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_300x_100%T with normal SPP_300x_100%N)	98.9
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)	NeuSomatic SEQC-WGS-GT50-SpikeWGS10 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_50x_100%T with normal SPP_50x_100%N)	95
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)	NeuSomatic SEQC-WGS-GT50-SpikeWGS10 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_50x_75%T with normal SPP_50x_100%N)	93.3
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)	NeuSomatic SEQC-WGS-GT50-SpikeWGS10 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_10%T with normal SPP_80x_100%N)	57
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)	NeuSomatic SEQC-WGS-GT50-SpikeWGS10 model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_20%T with normal SPP_80x_100%N)	80
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)	NeuSomatic SEQC-WGS-GT50-SpikeWGS10 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_FD_T_2 with normal WGS_FD_N_2)	94.1
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)	NeuSomatic SEQC-WGS-GT50-SpikeWGS10 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_FD_T_3 with normal WGS_FD_N_3)	93.9
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)	NeuSomatic SEQC-WGS-GT50-SpikeWGS10 model (Sahraeian et al. 2022)	SEQC2 HCC1395 sequencing centre and platform, SNV F1 (Sahraeian et al. 2022 Table S2)	F1 (SNVs, tumour WGS_NV_T_1 with normal WGS_NV_N_1)	97.8
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)	NeuSomatic SEQC-WGS-Spike model (Sahraeian et al. 2022)	SEQC2 HCC1395 library preparation and DNA input, SNV F1 (Sahraeian et al. 2022 Table S4)	F1 (SNVs, tumour LBP_TruSeq_T_1ng with normal LBP_TruSeq_N_1ng)	51.3
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)	NeuSomatic SEQC-WGS-Spike model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_100x_10%T with normal SPP_100x_100%N)	63.8
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)	NeuSomatic SEQC-WGS-Spike model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_100x_5%T with normal SPP_100x_100%N)	34
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)	NeuSomatic SEQC-WGS-Spike model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_10x_20%T with normal SPP_10x_100%N)	18.5
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)	NeuSomatic SEQC-WGS-Spike model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_200x_10%T with normal SPP_200x_100%N)	80.1
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)	NeuSomatic SEQC-WGS-Spike model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_200x_20%T with normal SPP_200x_100%N)	90.7
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)	NeuSomatic SEQC-WGS-Spike model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_200x_5%T with normal SPP_200x_100%N)	58.8
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)	NeuSomatic SEQC-WGS-Spike model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_200x_50%T with normal SPP_200x_100%N)	96.6
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)	NeuSomatic SEQC-WGS-Spike model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_300x_10%T with normal SPP_300x_100%N)	86
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)	NeuSomatic SEQC-WGS-Spike model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_300x_20%T with normal SPP_300x_100%N)	93.1
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)	NeuSomatic SEQC-WGS-Spike model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_300x_5%T with normal SPP_300x_100%N)	72.1
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)	NeuSomatic SEQC-WGS-Spike model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_30x_10%T with normal SPP_30x_100%N)	27
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)	NeuSomatic SEQC-WGS-Spike model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_30x_5%T with normal SPP_30x_100%N)	9.2
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)	NeuSomatic SEQC-WGS-Spike model (Sahraeian et al. 2022)	SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)	F1 (SNVs, tumour SPP_80x_20%T with normal SPP_80x_100%N)	80

Follow-up

Current state: Not yet reviewed.

No one has reviewed this finding yet.

How to help resolve this

If you know why these studies disagree, for example a different population, metric or preprocessing step, or you have a corrected value, tell us through the contribution form. A reviewer checks every submission against its source before anything changes, and the step is added to the follow-up above.

Finding discrepancy-fd86c4356641363b · All contested results · How findings are made and followed up