Pan-cancer analysis of expressed somatic nucleotide variants in long intergenic non-coding RNA

Abstract

Long intergenic non-coding RNAs have been shown to play important roles in cancer. However, because lincRNAs are a relatively new class of RNAs compared to protein-coding mRNAs, the mutational landscape of lincRNAs has not been as extensively studied. Here we characterize expressed somatic nucleotide variants within lincRNAs using 12 cancer RNA-Seq datasets in TCGA. We build machine-learning models to discriminate somatic variants from germline variants within lincRNA regions (AUC 0.987). We build another model to differentiate lincRNA somatic mutations from background regions (AUC 0.72) and find several molecular features that are strongly associated with lincRNA mutations, including copy number variation, conservation, substitution type and histone marker features.

SNPs and Somatic Mutation on Long Non-Coding RNA: New Frontier in the Cancer Studies?

“…Owing to recent developments in machine-learning technologies, next generation sequencing of pan-cancer data provides vast resources that aid the discrimination of somatic variants from germline variants, within non-coding regions. Thus, non-coding somatic mutations can be differentiated from background genomic regions, and associated features, such as copy number variations, conservation, substitution types and histone marker features, can be assessed [64]. To date, only a few articles are available in the literature on “somatic mutation”, lncRNA and cancer.…”