Application of aiAtlas Version 1.2 to Simulate Variant Gene Function Restoration and Rescue Thresholds in Rare Diseases: Validation Case Study

Xeroderma pigmentosum group D (XPD), caused by ERCC2 gene dysfunction, leads to defective nucleotide excision repair and hypersensitivity to UV radiation. Robust experimental models for variant-level functional assessment remain limited.

This study aimed to use aiAtlas version 1.2, a mechanistic large-concept simulation model, to evaluate the functional consequences of ERCC2 (XPD) variants and identify quantitative thresholds for functional rescue under graded gene function restoration.

We simulated 136 virtual artificially induced pluripotent stem cell-derived cell lines spanning wild-type, single-mutation, multi-mutation, human tumor-derived, and gene fusion ERCC2 states. Twenty-five features encompassing DNA damage and repair, replication stress, pluripotency, and epigenetic remodeling were analyzed using nonparametric statistics with Bonferroni correction, Hodges-Lehmann estimates, and Cliff δ with bootstrap CIs. Graded ERCC2 restoration (0%-100%) was simulated to evaluate rescue thresholds. Cross-validation, bagging, and bootstrap resampling tested robustness.

Simulations identified 3 nonlinear ERCC2 (XPD) rescue thresholds: approximately 20% to 30% (initial stabilization of repair), approximately 50% (near normalization), and more than 80% (full convergence). Reduced-function variants required substantially less restoration than strict loss-of-function variants to cross each threshold. Group comparisons across variant classes showed consistent differences in DNA repair, replication stress, and epigenetic remodeling features supported by effect size metrics and CIs.

aiAtlas version 1.2 provides a simulation-based mechanistic framework for variant-level functional modeling in ERCC2 (XPD). The simulations identified quantitative thresholds that support mechanistic hypothesis generation regarding variant-dependent restoration of function. These findings provide a computational basis for future studies and require independent validation before clinical application.