Genomic landscape of colitis-associated cancer indicates the impact of chronic inflammation and its stratification by mutations in the Wnt signaling

Abstract

Inflammatory bowel disease (IBD) increases the risk of colorectal cancer, known as colitis-associated cancer (CAC). It is still unclear what driver mutations are caused by chronic inflammation and lead to CAC development. To get insight into this issue, we investigated somatic alterations in CAC. We performed exome sequencing of 22 fresh CACs and targeted sequencing of 43 genes on 90 archive specimens from Japanese CAC patients, of which 58 were ulcerative colitis (UC) and 32 were Crohn's disease (CD). Consistently with the previous reports, TP53 was commonly mutated (66%) whereas APC, KRAS and SMAD4 were mutated less frequently (16%, 11% and 11%, respectively). Mucinous CD-CACs in the anus, an Asian-specific subtype of CD-CAC, had less somatic mutations in our target genes. We also found that RNF43, a negative regulator of the Wnt signaling, was somatically mutated in a significant fraction of CACs (10 of 90; 11%). Two lines of evidence indicated that somatic mutations of RNF43 were related to chronic inflammation. First, somatic mutations of RNF43 were significantly associated with longer duration of IBD. Second, clinico-pathological features suggested many of the APC-mutated CACs were actually sporadic colorectal cancer whereas RNF43-mutated CACs did not have this tendency. RNA-Seq analysis showed that RNF43-mutated CACs had elevated expression of c-Myc and its target genes, suggesting that RNF43 is a bona fide driver of CAC development. This study provides evidence that somatic mutation of RNF43 is the driver genetic alteration that links chronic inflammation and cancer development in about 10% of CACs.

Keywords: APC; RNF43; colitis-associated cancer; inflammatory bowel disease; next-generation sequencing.

Figure 1. Recurrent somatic mutations in targeted sequencing of 90 CACs

Genes mutated in 3 or more cases were shown.

Figure 2. Comparison of somatic mutations between CAC and sporadic CRC

(A) The frequency of somatic mutations in 90 CACs and 619 sporadic CRCs. Only genes that were captured in both studies and had a significant difference between them were shown. ^**q-value < 0.01; ^*q-value < 0.05 using Fisher’s exact test and the Benjamini-Hochberg procedure. (B) Distribution of somatic TP53 mutations in CAC and sporadic CRC. TAD, transactivation domain; DBD, DNA-binding domain; Tetramer, tetramerization domain. (C) Distribution of somatic RNF43 mutations in CAC and sporadic CRC.

Figure 3. Somatic mutations of APC and RNF43 and clinico-pathological features

(A) Somatic mutations of APC, RNF43, and other two genes related to the Wnt pathway. (B) Somatic mutations and the duration of IBD. The statistical test was performed using Wilcoxon rank sum test. (C, D) Association of somatic mutations with histological type and the extent of disease. The extent of disease was available only in 58 UC cases. The statistical test was performed using Fisher’s exact test. (C) APC mutations. (D) RNF43 mutations. ^**p-value < 0.01; ^*p-value < 0.05.

Figure 4

(A) Two-way clustering of transcriptome profiles in 17 UC-CAC samples with an annotation for somatic mutations. The clustering was performed by applying Ward’s method to log₁₀(1+FPKM) values. (B–D) Gene fusion of GOLIM4 and RSPO3. (B) A schematic gene structure. (C) Domain structure of the fusion protein. FU: Furin-like repeat; TSP1: Thrombospondin type-1 (TSP1) repeat. (D) RT-PCR of the junction site. A chromatogram of capillary sequencing for the lower band is shown at the bottom of (B). (E, F) Gene set enrichment analysis. (E) Two gene sets regulated by MYC were more expressed in the cluster A than the cluster B. (F) A gene set involved in allograft rejection were more expressed in the cluster B than the cluster A.

Figure 5. Trinucleotide context of base substitutions in CACs and sporadic CRCs

(A) Number of trinucleotide substitution patterns in non-hypermutated colorectal cancers. Six possible substitutions from pyrimidine bases were further subdivided into 96 patterns based on the neighboring nucleotides. The four panels represent 21 CACs, 11 sporadic CRCs sequenced in this study, 500 sporadic CRCs in a previous study, and 209 sporadic CRCs in TCGA. (B) Methylation levels and somatic C-to-T mutation rate at CpG dinucleotides. Methylation levels were obtained from the ENCODE sigmoid colon data. (C) The number of SNVs from TpT to GpT in CAC and sporadic CRC. TS, this study; GNK, Giannakis et al., 2016.