From enrichment to interpretation: PS4-driven reclassification in Taiwanese inherited retinal degeneration

Abstract Background Inherited retinal degeneration (IRD) comprises a diverse group of monogenic disorders characterized by marked genetic and phenotypic heterogeneity. Although next-generation sequencing (NGS) enables the identification of candidate variants, many remain classified as variants of uncertain significance (VUS). Ancestry-matched population data can strengthen comparative evidence, and the emergence of national biobanks provides new opportunities to operationalize ACMG/AMP criterion PS4 through case–control analyses. Methods We integrated an IRD cohort of 802 probands with whole-genome allele frequency data from 1, 492 individuals in the Taiwan Biobank. An allele-based case–control framework was applied, assigning PS4 when the Haldane–Anscombe–corrected odds ratio was ≥ 5 and the 95% confidence interval excluded 1. Post-PS4 triage required variants to: (i) reside in IRD-associated genes, (ii) be rare in East Asian populations in gnomAD v4. 1, and (iii) be annotated in RefSeq as exonic, untranslated regions, or splicing (± 20 bp). Baseline ACMG/AMP classifications were generated using GeneBe and finalized through expert curation. Results Incorporation of PS4 substantially refined variant interpretation, upgrading two variants from Likely Pathogenic to Pathogenic and six from VUS to Likely Pathogenic. Homozygous exemplar variants, including CNGB1 (NM₀01297. 5): c. 2921T > G and CFAP410 (NM₀04928. 3): c. 340₃51dup, demonstrated strong genotype–phenotype concordance with confirmatory sequencing, illustrating an end-to-end workflow from statistical enrichment to clinical reporting. Conclusion An ancestry-aware case–control framework enables effective implementation of PS4 and improves the accuracy of IRD variant classification. This reproducible strategy supports the integration of population-specific genomic data into clinical workflows and is applicable to other monogenic disorders.