Prioritization of enhancer mutations by combining allele-specific chromatin accessibility with motif analysis and deep learning

Genomic sequence variation within enhancers and promoters can have a significant impact on the cellular state and phenotype. However, sifting through the millions of candidate variants in a personal genome or cancer genome, to identify only those variants that impact enhancer function, remains a major challenge. Prioritization of non-coding genome variation benefits from explainable AI to predict and interpret the impact of a mutation on gene regulation. Here we apply a specialized deep learning model to 10 phased melanoma genomes and identify functional enhancer mutations with allelic imbalance of chromatin accessibility and gene expression. Accessible chromatin profile of A375 and MM047 lines with ATAC-seq. ChIP-seq against cFos, cJun, Fra-1 and JunB in MM099 line. Please note that processed data file generated from both ATAC-seq replicates is linked to the corresponding *ATAC-seq A sample records.