Deep Learning Deciphers the Related Role of Master Regulators and G-Quadruplexes in Tissue Specification

G-quadruplexes (GQs) are non-canonical DNA structures encoded by G-flipons that may play critical roles in gene regulation and chromatin structure. Here, we explore the role of G-flipons in tissue specification. We present a deep learning-based framework for the genome-wide G-flipon predictions across 14 human tissue types. The model was trained with high confidence experimental maps of GQ forming sequences and ATAC-seq peaks, conjoined with the location of RNA polymerase, histones, and transcription factor binding sites. The training set was based on level 4-6 Endoquad GQ annotated sequences with predictions validated using the complete level 1-6 dataset. To identify tissue-specific regulatory patterns, we classified GQ promoter predictions as either 'core' or ‘tissue-specific’. The predicted GQ-dependent, tissue-specific expression of genes was confirmed using DAVID gene ontology tools and validated using the TissueEnrich and GTEx datasets. We further explored interactions between GQ structures and master regulator genes (MRGs) in promoter regions, revealing a notable overlap of MRGs and predicted sites of GQ formation, with colocation of both features within the same tissue-specific DNase hypersensitivity site and with proteins that modulate R-loop formation. Collectively, the findings highlight the transactions between G-flipons with MRG during development that underlie tissue specification.