Abstract
Genome architecture in eukaryotes exhibits a high degree of complexity. Amidst the numerous intricacies, the existence of genes as non-continuous stretches composed of exons and introns has garnered significant attention and curiosity among researchers. Accurate identification of exon-intron boundary junctions is crucial to decipher the molecular biology governing gene expression of regular and aberrant splicing. The currently employed frameworks for genomic signals, which aim to identify exons and introns within a genomic segment, need to be revised primarily due to the lack of a robust consensus sequence and the limitations posed by the training on available experimental data sets. To tackle these challenges and capitalize on the understanding that deoxyribonucleic acid (DNA) exhibits function-dependent local structural and energetic variations, we present ChemEXIN, an innovative method for predicting exon-intron boundaries. The method utilizes a deep-learning (DL) model alongside tri- and tetra-nucleotide-based structural and energy parameters. ChemEXIN surpasses current methods in accuracy and reliability. Our work represents a significant advancement in exon-intron boundary annotations, with potential implications for understanding gene expression, regulation, and biomedical research.