Identifying non-coding variant effects at scale via machine learning models of cis-regulatory reporter assays

Supplemental data and resources for "Identifying non-coding variant effects at scale via machine learning models of cis-regulatory reporter assays" Including: MPAC and comparison model predictions for: Siraj 2026 (UKBB/BBJ/GTEx) MPRA DNase allele specific effects ClinVar (20260104) COSMIC (v98) GWAS tag SNVs + LD variants Haplotype analyses gnomAD (v3.1.2 SNPs and and small indels) Saturation mutagenesis of human promoters Saturation mutagenesis ENCODE dELSs Supplemental Tables for: Recurrent COSMIC v98 emVar candidate drivers Promoter level function x constraint relationships Functional enrichments for promoter level function x constraint relationships GTEx phenocopying results All promoter and dELS seqlets Model hyperparameters All MPAC model artifacts