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)

What this source contributed

Records in this release that cite this source. A record can cite several sources.

• 5 methods
• 5 configurations
• 3 protocols
• 1 dataset
• 15 evaluations
• 65 results
• 5 evidence claims

Results

Values as the source printed them. Compare results only under compatible protocols, datasets and metrics.

Claims

Statements this source supports, each with where in the source it was checked.

• Baseline: Select a copy-number variant detection and characterisation workflow: Baseline ExomeDepth, CNVnator, AnnotSV and ClassifyCNV (cnv-20261009-source-gabrielaite2021: Abstract and Results (callers compared and recommended); cnv-20261011-hwang2026-source-article: Abstract and Materials and Methods 2.3 (ExomeDepth among four WES callers); cnv-20261011-zhang2026-source-article: Methods (rule-based and machine-learning tool categories))
• Evidence summary: Select a copy-number variant detection and characterisation workflow: Summary On HG002 deletions, DRAGEN 4.2 with SV-informed CNV calling found 87 to 100% of deletions in every size bin, with precision 0.99 to 1.00; this is the developers' own benchmark. CNVnator matched it above 10 kb but found only 26% of deletions of 1 to 5 kb and 51% of 5 to 10 kb. On NA12878, LUMPY, DELLY and Manta recovered 88 to 94% of known CNVs, but only 20 to 33% of their calls matched; Manta and CNVnator were used to build this truth set, which can favour them. The other callers recovered 1 to 43%. Hwang et al. (2026) compared four exome callers with chromosomal microarray CNVs in 39 clinical exomes, scoring deletion and duplication exons together: sensitivity and PPV were 0.758 and 0.025 for ExomeDepth, 0.662 and 0.096 for CNVkit, 0.768 and 0.239 for CoNIFER and 0.170 and 0.041 for cn.MOPS. The truth set keeps only array CNVs with at least ten probes that overlap exome baits, so any other exon call counts as a false positive. After the authors removed regions where each tool called CNVs in more than 10% of the same 180-exome cohort, ExomeDepth reached 0.903 and 0.102 on a smaller reference set of 2,124 exons (Table 4); this filter is the authors' own method. For characterisation, Zhang et al. (2026) ran five automated ACMG classifiers on 3,031 expert-classified CNVs: five-category accuracy, averaged across classes in a way the paper does not state, ranged from 48.76% (X-CNV) to 69.81% (MarCNV-ISV) (Table 3). With likely and definite classes merged, every tool recognised more pathogenic deletions than pathogenic duplications (AnnotSV 95.16% versus 86.39%) (Table 4). Two of the three authors developed dbCNV and the reference includes their own laboratory's cases, so the dbCNV results are author-reported. None of the comparisons shown reports duplication detection separately, none covers tumour samples or long reads, and none evaluates a foundation model. (amp-source-dragen-supplementary-tables: sheet 'S4 CNV benchmarking' rows 6-10; cnv-20261009-source-gabrielaite2021-table-s2: rows with sample GB-WGS-NA12878; cnv-20261011-hwang2026-source-article: Table 4; Methods 2.2 and 2.5; cnv-20261011-zhang2026-source-article: Tables 3 and 4)
• Relevance of ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) to "Select a copy-number variant detection and characterisation workflow": Assessed by ACMG five-category CNV pathogenicity classification against expert labels (Zhang et al. Table 3) (cnv-20261011-zhang2026-source-article: Table 3; Methods 'Data analysis'; Results 'Comparative analysis of clinical metrics')
• Relevance of Three-category CNV classification, per-class agreement on deletions (Zhang et al. Table 4, DEL) to "Select a copy-number variant detection and characterisation workflow": Assessed by Three-category CNV classification, per-class agreement on deletions (Zhang et al. Table 4, DEL) (cnv-20261011-zhang2026-source-article: Table 4 rows 'DEL' B, VUS, P; Results 'Analysis of three-category performance')
• Relevance of Three-category CNV classification, per-class agreement on duplications (Zhang et al. Table 4, DUP) to "Select a copy-number variant detection and characterisation workflow": Assessed by Three-category CNV classification, per-class agreement on duplications (Zhang et al. Table 4, DUP) (cnv-20261011-zhang2026-source-article: Table 4 rows 'DUP' B, VUS, P; Results 'Analysis of three-category performance')

Models, benchmarks and other records

Evidence

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