Discovery of driver non-coding splice-site-creating mutations in cancer

Abstract

Non-coding mutations can create splice sites, however the true extent of how such somatic non-coding mutations affect RNA splicing are largely unexplored. Here we use the MiSplice pipeline to analyze 783 cancer cases with WGS data and 9494 cases with WES data, discovering 562 non-coding mutations that lead to splicing alterations. Notably, most of these mutations create new exons. Introns associated with new exon creation are significantly larger than the genome-wide average intron size. We find that some mutation-induced splicing alterations are located in genes important in tumorigenesis (ATRX, BCOR, CDKN2B, MAP3K1, MAP3K4, MDM2, SMAD4, STK11, TP53 etc.), often leading to truncated proteins and affecting gene expression. The pattern emerging from these exon-creating mutations suggests that splice sites created by non-coding mutations interact with pre-existing potential splice sites that originally lacked a suitable splicing pair to induce new exon formation. Our study suggests the importance of investigating biological and clinical consequences of noncoding splice-inducing mutations that were previously neglected by conventional annotation pipelines. MiSplice will be useful for automatically annotating the splicing impact of coding and non-coding mutations in future large-scale analyses.

Fig. 1. Benchmark test of MiSplice pipeline and sample set.

a Sensitivity curves derived by simulating various coverage levels and mutation distances plotted as a function of splice allele fraction (ratio of non-canonical junction reads over canonical junction reads). b Required junction read coverage to achieve sufficient power. c Sample data set processed by MiSplice pipeline. Source data are provided as a Source Data file.

Fig. 2. Category and distribution of nc-SCMs from TCGA WGS data.

a Schematics and counts of mutation-induced splicing events in seven different classifications. The new exon category is subdivided into first, middle, and last, depending on the location of the new exon. The complex event is a combination of multiple events, for example, exon extension and new exon. b Types and counts of splice forms in different non-coding regions. c Distribution of intron sizes (log 10 scale) across different categories. The p value is from the Wilcoxon’s rank-sum test, two-sided. Source data are provided as a Source Data file.

Fig. 3. Characterization of nc-SCMs from TCGA WGS data.

a Frequency distribution of the distance from mutations to splice sites and splicing score comparison between the reference and mutant primary splice sites for donors and acceptors. Blue and red colors represent introns and exons, respectively. b Splice score distribution of new exon splice sites. Red arrows represent negative changes in score, blue arrows represent positive changes in score, and dots represent little to no changes in score (change <0.5). Arrow length is proportional to the magnitude of the change. c Comparison of primary splice score before and after mutation, the activated mate score in new exons, and the score of 300 random control sites. Source data are provided as a Source Data file.

Fig. 4. IGV schematics of MDM2, NFE2L2, and STK11 splicing patterns.

Sequence reads visualized in IGV supporting the junctions of exon-creating events for MDM2, NFE2L2, and STK11. Red vertical lines indicate mutation positions. Source data are provided as a Source Data file.

Fig. 5. Characterization of nc-SCMs from TCGA WES data.

a Comparison of splice scores between the reference and mutant for donors and acceptors. The color indicates the mutation distance to the junction. b nc-SCMs found in cancer-related genes across different cancer types. Source data are provided as a Source Data file.

Fig. 6. Experimental validation of nc-SCMs by the mini-gene splicing assay.

a Validation of non-coding splice-site-creating mutation candidates by the mini-gene splicing assay (“Methods”). All experiments were performed by three replicates and gave similar results (see Source Data file for the full scans). b Integrative Genomics Viewer (IGV) screenshot of four validated mutation-induced exon extension or shrinkage events. Red vertical lines indicate the mutation positions. Source data are provided as a Source Data file.