Protocol

SEQC2 HCC1395 library preparation and DNA input, indel F1 (Sahraeian et al. 2022 Table S4)

Indel F1 per library pair for nine callers and eight NeuSomatic models.

Overview

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

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

15 recorded evaluations, 105 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

15 evaluations · 105 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

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

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Author-reported evaluations: 9
External evaluations: 6

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Select an upstream conventional reference after reviewing the full protocol

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-10-cbb3da59bc08. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

Strengths, limitations and unresolved questions

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-10-cbb3da59bc08
Property and statement	Original source and location	Review and provenance

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

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

Sources and history

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

2 source records and release history

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

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: somatic-neusomatic-20261010-protocol-sahraeian2022-library-prep-indel

areas: dna-genomes
contexts: clinical_research
protocol: Paired tumour-normal calling of each library pair; PASS calls scored by exact match. All callers and models were scored on the 50% of the SEQC2 high-confidence genome held out from SEQC-WGS-GT-50 training (about 1.4 Gb; about 21K truth SNVs and 1.3K truth indels), against SEQC2 HighConf and MedConf calls (v1.0), LowConf calls blacklisted and ambiguous private calls excluded.
version: Additional file 2 Table S4
metric: f1-score
limitations: Developer paper: the authors developed NeuSomatic (two hold a patent application on it; Competing interests) and trained and selected every NeuSomatic model; NeuSomatic rows are author_reported.; One cell-line pair (HCC1395/HCC1395BL). The SEQC2 truth set (v1.0, 39,536 SNVs and 2,020 indels) was built by the SEQC2 somatic working group, whose reference papers have co-authors W. Xiao and L. T. Fang as first authors, with the SomaticSeq classifier, which co-authors L. T. Fang and M. Mohiyuddin helped develop (references 2, 3 and 20). It has a 5% VAF and 50x depth detection limit, LowConf calls are blacklisted, and ambiguous private calls are excluded from scoring (Methods 'Evaluation process').; Scored on the 50% of the high-confidence genome held out from SEQC-WGS-GT-50 training (about 21K truth SNVs and 1.3K truth indels). The NeuSomatic and NeuSomatic-S SEQC-WGS-Spike, SEQC-WGS-GT-50 and SEQC-WGS-GT50-SpikeWGS10 models were trained on this cell line and are excluded from this judgement, as is Octopus-RF, whose forest is not identified. The DREAM3 models, trained on DREAM Challenge Stage 3 data, are kept.; The NeuSomatic ensemble mode takes calls from MuTect2, SomaticSniper, Strelka2, MuSE and VarDict as input channels.; Only F1 is printed; no precision, recall or uncertainty in these tables.; Caller versions as in Methods (for example MuTect2 4.beta.6, Strelka2 2.8.4, Lancet 1.0.7, NeuSomatic 0.1.4).; The 1 ng TruSeq-Nano libraries had about 7x effective coverage after duplicate removal (Results).; SomaticSniper and MuSE do not call indels ('-' in the table).
source locator: Additional file 2 Table S4 (INDELs section); Methods 'Evaluation process'

Related records

Suggest a correction