Exon Skipping-based Subtyping of Colorectal Cancers

Abstract

The identification of colorectal cancer (CRC) molecular subtypes has prognostic and potentially diagnostic value for patients, yet reliable subtyping remains unavailable in the clinic. The current consensus molecular subtype (CMS) classification in colorectal cancers is based on complex RNA expression patterns quantified at gene level. The clinical application of these methods, however, is challenging due to high uncertainty of single sample classification and associated costs. Alternative splicing (AS), which strongly contributes to transcriptome diversity, has rarely been utilized for tissue type classification. Here, we present an AS-based CRC subtyping framework sensitive to differential exon usage that can be adapted for clinical application. Unsupervised clustering was used to measure the strength of association between different categories of AS and CMS. To build a classifier, the ground-truth for CMS labels was derived from expression data quantified at gene-level. Feature selection was achieved through bootstrapping and L1-penalized estimation. The resulting feature space was used to construct a subtype prediction framework applicable to single and multiple samples. The performance of the models was evaluated on unseen CRCs from two independent sources (Indivumed, n=129; TCGA, n=99). We developed a colorectal cancer subtype identifier (CRCi) based on 29 exon-skipping (ES) events that accurately classifies unseen tumors and enables more precise differentiation of subtypes characterized by distinct biological and prognostic features as compared to classifiers based on gene expression. Here we demonstrate that a small number of ES events can reliably classify colorectal cancer subtypes using individual patient specimen in a manner suitable to clinical application.