F1 (SNVs, tumour SPP_100x_20%T with normal SPP_100x_100%N) of NeuSomatic-S SEQC-WGS-GT50-SpikeWGS10 model (Sahraeian et al. 2022) on SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS
74.4% F1 (SNVs, tumour SPP_100x_20%T with normal SPP_100x_100%N)
Methods
- Tested configuration
- NeuSomatic-S SEQC-WGS-GT50-SpikeWGS10 model (Sahraeian et al. 2022)
- Protocol
- SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)
- Dataset
- SEQC2 tumour-normal titration: HCC1395 gDNA mixed with HCC1395BL gDNA at 5-100% tumour purity, 10x-300x WGS
- Procedure
- SEQC2 HCC1395 tumour purity, coverage and normal contamination, SNV F1 (Sahraeian et al. 2022 Table S3)
- Evaluation
- NeuSomatic-S SEQC-WGS-GT50-SpikeWGS10 on SEQC2 tumour-normal titration, SNVs (Sahraeian et al. 2022)
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- Not reported by the source
- Evidence
- Author-reported evaluation · source checkedAchieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample; Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Additional file 2 Table S3, SNVs section, row 'SPP_100x_20%T vs SPP_100x_100%N', column 'NeuSomatic-S SEQC-WGS-GT50-SpikeWGS10'
A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.
Reproduction
- Split
- Held-out 50% of the high-confidence genome
- Adaptation
- Not reported
- Scoring implementation
- F1 (%) of PASS calls against the SEQC2 truth set, exact match
No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.
Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
2 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Reported result 74.4 Individual claims | Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample Additional file 2 Table S3, SNVs section, row 'SPP_100x_20%T vs SPP_100x_100%N', column 'NeuSomatic-S SEQC-WGS-GT50-SpikeWGS10' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Genome Biology 23:12, published 2022-01-07; PMC8740374 full-text XML | source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-10 author reported Audit detailsParsed from the pinned PDF word boxes (pdftotext -bbox, pdftotext version 26.08.0) by extract/extract_neusomatic.py; columns fixed by position (see retrieval-log.md); column means match the printed Average row. Pending independent review. Independent review 2026-10-10: value, row and column match the source. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record Extraction artifact SHA-256: |
| Reported result 74.4 Individual claims | Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) Additional file 2 Table S3, SNVs section, row 'SPP_100x_20%T vs SPP_100x_100%N', column 'NeuSomatic-S SEQC-WGS-GT50-SpikeWGS10' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 13059_2021_2592_MOESM2_ESM.pdf | source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-10 author reported Audit detailsParsed from the pinned PDF word boxes (pdftotext -bbox, pdftotext version 26.08.0) by extract/extract_neusomatic.py; columns fixed by position (see retrieval-log.md); column means match the printed Average row. Pending independent review. Independent review 2026-10-10: value, row and column match the source. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record Extraction artifact SHA-256: |
Sources and history
Release 2026-10-10-457d7eaef7d6 · Record review: source checked
2 source records and release history
- Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample · Original source · Genome Biology 23:12, published 2022-01-07; PMC8740374 full-text XML
- Sahraeian et al. 2022, Additional file 2: Supplementary Tables S1-S10 (13059_2021_2592_MOESM2_ESM.pdf) · Original source · 13059_2021_2592_MOESM2_ESM.pdf
Technical metadata and extraction receipts
Stable ID: somatic-neusomatic-20261010-result-sahraeian2022-neusomatic-s-seqc-wgs-gt50-spikewgs10-titration-snv-spp-100x-20-t-spp-100x-100-n
- metric
- f1-score
- metric direction
- higher
- unit
- percent
- metric qualifier
- SNVs, tumour SPP_100x_20%T with normal SPP_100x_100%N
- printed value
- 74.4
- numeric value
- 74.4
- source locator
- Additional file 2 Table S3, SNVs section, row 'SPP_100x_20%T vs SPP_100x_100%N', column 'NeuSomatic-S SEQC-WGS-GT50-SpikeWGS10'
- missing metadata
- uncertainty: reason: unreported
- review
- method: source-hash-verification; deterministic-table-parse; independent-cell-check; method note: Re-downloaded the PDF and matched its SHA-256. Read the word boxes (pdftotext -bbox) with a parser written for this review: columns fixed from the x-centres of the numbers, each rotated header assigned to the nearest column, and the NeuSomatic-S and NeuSomatic model groups split at the second DREAM3 header; the extractor's scripts were not run. Column identity was then checked independently against the article prose (Table S2 NeuSomatic SEQC-WGS-GT50-SpikeWGS10 averages 94.6 and 87.9, the 3.7-point indel lead over Octopus-RF, the Table S3 normal-contamination drops for MuTect2, MuSE, Lancet and Strelka2, and the Table S4 indel order and 0.6-point SNV lead) and against the SNV-only columns. Every printed Average equals the mean of its rows within 0.05.; reviewer: claude; reviewer note: Separate Claude review agent, independent of the extractor; no human review claimed; date: 2026-10-10; artifact sha256: 10a109d80f6f49446ea84bd9f7f6b31c20d634516c8666376ac8a8f51f3236d0; retrieval url: https://static-content.springer.com/esm/art%3A10.1186%2Fs13059-021-02592-9/MediaObjects/13059_2021_2592_MOESM2_ESM.pdf; note: Parsed from the pinned PDF word boxes (pdftotext -bbox, pdftotext version 26.08.0) by extract/extract_neusomatic.py; columns fixed by position (see retrieval-log.md); column means match the printed Average row. Pending independent review. Independent review 2026-10-10: value, row and column match the source.