Entropy-Driven Machine Learning for Deciphering mRNA rearrangement by splicing in Complex Microorganisms

Abstract

Alternative splicing allows a single gene to produce multiple messenger RNA (mRNA) variants by differential RNA processing, resulting in the translation of distinct protein isoforms. Intron retention (IR) is a specific type of alternative splicing in which introns remain unspliced in the mature mRNA. The exact regulatory code behind intron splicing remains not fully deciphered. Unraveling these mechanisms is critical to uncovering the foundations of genetic disorders: a substantial fraction of disease-causing mutations disrupt intron splicing. In this study, we applied explainable machine learning (xML) models to investigate the mechanism underlying intron retention in mature mRNA. Intronic sequences from species within the ciliate genus Tetrahymena were analyzed, allowing the intron retention process to be analysed without tissue-specific confounders. Several features of the intronic sequences were examined, including the absence of repetitive nucleotide motifs -quantified as entropy - the GC content, and the complexity of the secondary structures as estimated by the Lempel– Ziv (LZ) measure. We found that the key distinguishing features of retained introns include higher entropy and complex secondary structures near the 3' splice sites. These features may weaken splicing signals and impair splice-site recognition, contributing to IR. Our work identifies key sequence-level features predictive of intron retention in Tetrahymena and could provide a generalizable, explainable ML framework for investigating splicing regulation in other eukaryotes.