Protocol

ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3)

Run each tool on the 3,031 CNVs and compare its five-category output (benign, likely benign, VUS, likely pathogenic, pathogenic) with the expert classification; report accuracy, sensitivity, specificity, PPV, FPR, F1 and MCC.

5 evaluations · 35 results

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.

5 recorded evaluations, 35 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

5 evaluations · 35 results. Different protocols are not a single leaderboard.

Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) · Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)

Sorted by Accuracy (ACMG five-category classification; averaging across classes not stated) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Accuracy (ACMG five-category classification; averaging across classes not stated)	F1 (ACMG five-category classification; averaging across classes not stated)	False positive rate (ACMG five-category classification; averaging across classes not stated)	MCC (ACMG five-category classification; averaging across classes not stated)	Precision (ACMG five-category classification; averaging across classes not stated)	Recall (ACMG five-category classification; averaging across classes not stated)	Specificity (ACMG five-category classification; averaging across classes not stated)
MarCNV-ISV (Zhang et al. 2026)Evaluation	69.8% (best in column)	43.9%	9.56%	0.55 (best in column)	46.8%	45%	90.4%
ClassifyCNV (Zhang et al. 2026)Evaluation	67.8%	45.1% (best in column)	10.3%	0.54	52.3% (best in column)	44%	89.7%
dbCNV (Zhang et al. 2026)Evaluation	66.6%	41%	9.4% (best in column)	0.51	40.9%	45.7% (best in column)	90.6% (best in column)
AnnotSV (Zhang et al. 2026)Evaluation	60.2%	38.1%	11.2%	0.43	40%	43.5%	88.8%
X-CNV (Zhang et al. 2026)Evaluation	48.8%	34.5%	12.7%	0.34	37%	43.6%	87.3%

All 35 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: AnnotSV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	60.2% Accuracy (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AnnotSV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'AnnotSV', column 'Accuracy (%)'
Configuration: AnnotSV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	38.1% F1 (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AnnotSV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'AnnotSV', column 'F1(%)'
Configuration: AnnotSV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	11.2% False positive rate (ACMG five-category classification; averaging across classes not stated) percent · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AnnotSV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'AnnotSV', column 'FPR*(%)'
Configuration: AnnotSV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	0.43 MCC (ACMG five-category classification; averaging across classes not stated) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AnnotSV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'AnnotSV', column 'MCC*'
Configuration: AnnotSV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	40% Precision (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AnnotSV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'AnnotSV', column 'PPV*(%)'
Configuration: AnnotSV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	43.5% Recall (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AnnotSV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'AnnotSV', column 'Sensitivity (%)'
Configuration: AnnotSV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	88.8% Specificity (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AnnotSV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'AnnotSV', column 'Specificity (%)'
Configuration: ClassifyCNV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	67.8% Accuracy (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ClassifyCNV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'ClassifyCNV', column 'Accuracy (%)'
Configuration: ClassifyCNV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	45.1% F1 (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ClassifyCNV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'ClassifyCNV', column 'F1(%)'
Configuration: ClassifyCNV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	10.3% False positive rate (ACMG five-category classification; averaging across classes not stated) percent · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ClassifyCNV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'ClassifyCNV', column 'FPR*(%)'
Configuration: ClassifyCNV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	0.54 MCC (ACMG five-category classification; averaging across classes not stated) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ClassifyCNV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'ClassifyCNV', column 'MCC*'
Configuration: ClassifyCNV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	52.3% Precision (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ClassifyCNV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'ClassifyCNV', column 'PPV*(%)'
Configuration: ClassifyCNV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	44% Recall (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ClassifyCNV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'ClassifyCNV', column 'Sensitivity (%)'
Configuration: ClassifyCNV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	89.7% Specificity (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ClassifyCNV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'ClassifyCNV', column 'Specificity (%)'
Configuration: dbCNV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	66.6% Accuracy (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source dbCNV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'dbCNV', column 'Accuracy (%)'
Configuration: dbCNV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	41% F1 (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source dbCNV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'dbCNV', column 'F1(%)'
Configuration: dbCNV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	9.4% False positive rate (ACMG five-category classification; averaging across classes not stated) percent · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source dbCNV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'dbCNV', column 'FPR*(%)'
Configuration: dbCNV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	0.51 MCC (ACMG five-category classification; averaging across classes not stated) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source dbCNV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'dbCNV', column 'MCC*'
Configuration: dbCNV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	40.9% Precision (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source dbCNV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'dbCNV', column 'PPV*(%)'
Configuration: dbCNV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	45.7% Recall (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source dbCNV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'dbCNV', column 'Sensitivity (%)'
Configuration: dbCNV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	90.6% Specificity (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source dbCNV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'dbCNV', column 'Specificity (%)'
Configuration: MarCNV-ISV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	69.8% Accuracy (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MarCNV-ISV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'MarCNV-ISV', column 'Accuracy (%)'
Configuration: MarCNV-ISV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	43.9% F1 (ACMG five-category classification; averaging across classes not stated) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MarCNV-ISV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'MarCNV-ISV', column 'F1(%)'
Configuration: MarCNV-ISV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	9.56% False positive rate (ACMG five-category classification; averaging across classes not stated) percent · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MarCNV-ISV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'MarCNV-ISV', column 'FPR*(%)'
Configuration: MarCNV-ISV (Zhang et al. 2026)	Protocol: ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) Dataset: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)	0.55 MCC (ACMG five-category classification; averaging across classes not stated) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MarCNV-ISV on the expert-classified ACMG CNV benchmark (five category) cnv-20261011-zhang2026-protocol-five-category Aggregation: Not reported Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Table 3, row 'MarCNV-ISV', column 'MCC*'

Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

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: 1
External evaluations: 4

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

Null control

Proposed control: requires review

Training-set class prior where supervised fitting is permitted

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

Regularised classifier on simple permitted features, or protocol's conventional reference

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 2026-11-02-a7f03c9e55a5. 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.

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 2026-11-02-a7f03c9e55a5
Property and statement	Original source and location	Review and provenance

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

How to read the evidence

Sources and history

Release 2026-11-02-a7f03c9e55a5 · Record review: source checked

1 source record and release history

Can automated copy number variation pathogenicity prediction tools replace manual review under the ACMG framework? A clinical validation (Zhang, Zhang and Chen, Global Medical Genetics 2026) · Original source · Global Medical Genetics 13:100096 (2026), published online 2026-03-06; PMC13018948 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: cnv-20261011-zhang2026-protocol-five-category

areas: dna-genomes
contexts: clinical_research
protocol: Run each tool on the 3,031 CNVs and compare its five-category output (benign, likely benign, VUS, likely pathogenic, pathogenic) with the expert classification; report accuracy, sensitivity, specificity, PPV, FPR, F1 and MCC.
version: Table 3
source locator: Table 3; Methods 'Data analysis'; Results 'Comparative analysis of clinical metrics'
limitations: How the five-class metrics are averaged across classes is not stated.; Reference labels are expert ACMG classifications, a semi-quantitative standard with known inter-reviewer variability (Discussion paragraph 5).; The set is enriched for pregnancy-loss and prenatal cases and is imbalanced (benign is about half of the duplications), which the authors say affects the metrics (Discussion paragraphs 5 and 6).; Classification of already detected CNVs from their coordinates; no read data or detection step is evaluated.; Some training sets of the evaluated tools (ClinVar, ClinGen, DGV) may overlap the published cohorts used as reference; the paper does not test this.; Two of the three authors (X. Zhang and D. Chen) are authors of dbCNV (reference 24), developed in the same laboratory, so the dbCNV rows are author_reported. dbCNV's original test set was that laboratory's internal dataset, and this benchmark includes the laboratory's internal CNV-seq cases (December 2019 to November 2025); overlap is not tested. The paper declares no competing interests.

Related records

uses data: Expert-classified ACMG CNV benchmark (Zhang et al. 2026, 3,031 CNVs)
assessment: AnnotSV on the expert-classified ACMG CNV benchmark (five category)
assessment: ClassifyCNV on the expert-classified ACMG CNV benchmark (five category)
assessment: dbCNV on the expert-classified ACMG CNV benchmark (five category)
assessment: MarCNV-ISV on the expert-classified ACMG CNV benchmark (five category)
assessment: X-CNV on the expert-classified ACMG CNV benchmark (five category)
assessed by: Select a copy-number variant detection and characterisation workflow

Suggest a correction