Model-based prediction of cis-acting RNA elements regulating tissue-specific alternative splicing

Here we describe a model-based approach to predict cis-acting RNA elements which regulate tissue-specific alternative splicing. The model facilitates the identification of cis-acting elements (or CAE) and the estimation of their activities, considering the splicing variants between two different tissues as the combinatorial functions of multiple elements. We implement this model on a set of differentially expressed exons, between heart and liver, derived from Affymetrix GeneChip^reg Human Exon 1.0 ST Array sample data. Focusing on hexamers, we select top 15 motifs with greatest cumulative exon inclusion (EIC) scores as the potential cis-acting elements. Eight of the total 15 hexamers are validated based on known exonic splicing regulators (ESRs) and predicted ESRs (PESRs). Permutation test demonstrates that the predicted EIC scores are statistically significant. Based on the prediction, we propose that PTB, hnRNP-B, SRp40, as well as other unknown factors are involved in the tissue-specific alternative splicing between heart and liver.