Collecting duct carcinoma of the kidney is associated with CDKN2A deletion and SLC family gene up-regulation

Abstract

The genetic landscape and molecular features of collecting duct carcinoma (CDC) of the kidney remain largely unknown. Herein, we performed whole exome sequencing (WES) and transcriptome sequencing (RNASeq) on 7 CDC samples (CDC1 -7). Among the 7 samples, 4 samples with matched non-tumor tissue were used for copy number analysis by SNP array data. No recurrent somatic SNVs were observed except for MLL, which was found to be mutated (p.V297I and p.F407C) in 2 samples. We identified somatic SNVs in 14 other cancer census genes including: ATM, CREBBP, PRDM1, CBFB, FBXW7, IKZF1, KDR, KRAS, NACA, NF2, NUP98, SS18, TP53, and ZNF521. SNP array data identified a CDKN2A homozygous deletion in 3 samples and SNV analysis showed a non-sense mutation of the CDKN2A gene with unknown somatic status. To estimate the recurrent rate of CDKN2A abnormalities, we performed FISH screening of additional samples and confirmed the frequent loss (62.5%) of CDKN2A expression. Since cisplatin based therapy is the common treatment option for CDC, we investigated the expression of solute carrier (SLC) family transporters and found 45% alteration. In addition, SLC7A11 (cystine transporter, xCT), a cisplatin resistance associated gene, was found to be overexpressed in 4 out of 5 (80%) cases of CDC tumors tested, as compared to matched non-tumor tissue. In summary, our study provides a comprehensive genomic analysis of CDC and identifies potential pathways suitable for targeted therapies.

Keywords: CDKN2A; collecting duct carcinoma; solute carrier family genes.

Figure 1. Somatic alterations in kidney CDC

a. A representative Circos plot of CDC samples. The plot shows (from outer to inner circle) genes with somatic amino acid changes (red genes are in Cancer Census Genes), chromosomes, allele frequencies of mutations, copy number aberration (orange for gain and blue for loss), and LOH (red means LOH and grey means no LOH). b. Somatic CNV in 7 CDC samples and summary of CNVs in CDC, ccRCC, chRCC, and pRCC. Red color represents copy number gain and blue copy number loss. c. Somatic SNVs in 4 CDC samples and significantly mutated genes in ccRCC and chRCC. Green means missense mutation, red means non-sense, frameshift mutations, and orange means both. TCGA data of ccRCC and pRCC, including clinical information, somatic mutations, SNP array CNV calls, and normalized RNASeqV2, were downloaded from the TCGA data portal. Alternation status of CDKN2A was determined by somatic mutation calls and CNV segmentation results. If a segment overlapped with CDKN2A and had a logR ratio less than −0.4, CDKN2A was considered a loss in this sample. For gene expression data, the RSEM quantified and normalized data were first log2 transferred, followed by significant test. All statistical tests were performed using R statistical program followed by a significance test.

Figure 2. CDKN2A losses in CDC

a. Copy number data show biallelic loss of CDKN2A in CDC1, CDC2, and CDC4 with negative log R ratios and normal like B allele frequencies. SNP array data log2 ratios were calculated by comparing the tumor sample signals with pooled non-tumor samples from Illumina. b. Representative tumor sample slides and fluorescence in situ hybridization (FISH) results of normal, single copy loss, and biallelic loss of CDKN2A loci. I, II, III: H&Es of cases CDC2, CDC9, CDC15, respectively, with infiltrating pleomorphic collecting duct carcinoma. IV, CDC2, p16 FISH with no copies each of p16 and with preserved reference probe. V, CDC9, p16 FISH with two copies each of p16 and reference probe. VI, CDC15, p16 FISH with one copy of p16 and two copies of reference probe. c. Tabulation of p16 loss according to NGS and FISH data. Cases CDC6-CDC16 were not sequenced by NGS, noted as NA.

Figure 3. RNASeq profiles of CDC gene expression

a. Kidney specific genes were down-regulated in all CDC tumor samples. b. Selected top up- and down-regulated genes that have been associated with cancer prognosis. c. Gene expression changes (log2 fold changes) of a five-gene signature defined by a study of genomic alterations in non-clear cell RCC (http://www.nature.com/ng/journal/v47/n1/full/ng.3146.html) to classify non-ccRCCs. CDC shows a distinct pattern for those five genes compared with three subtypes of non-ccRCC. d. Four down-steam genes (CDK4, E2F1, EZH2, and TP53) of CDKN2A were all found to be significantly up-regulated by RNASeq analysis.

Figure 4. SLC family genes upregulated in CDC

a. SLC family genes overexpressed in CDC tumors showed as log2 fold change. All the genes overexpressed were significantly different in CDC tumors, compared to matched non-tumor kidney. b. SLC6A7 mRNA expression in 4 matched non-tumor kidney and 5 CDC (1 non-matched) tumors. c. SLC7A11 mRNA expression in 4 matched non-tumor kidney and 5 CDC (1 non-matched) tumors. d. SLC1A3 mRNA expression in 4 matched normal kidney and 5 CDC (1 non-matched) tumors. e. Significant overexpression (log2 fold change) of drug resistance genes SLC6A7, SLC7A11, and SLC1A3 in CDC tumors.

Figure 5. Overexpression of xCT in CDC tumors and the association of xCT (SLC7A11) overexpression with overall poor survival in ccRCC, chRCC and pRCC patients

a.. Immunohistochemical detection of xCT was performed on CDC tumors using xCT antibody (5ug/ml, Abcam, MA). The numbers denoted in the figures are de-identified numbers of CDC tumors in the TMA. CDC1 and CDC2 tumors are included in the genomic profiling studies. Photmicrographs were captured using the Aperio Webscope Spectrum. b. Percent tumors (80%, 12 out of 15) express high levels of xCT. TCGA data analysis revealed the significant poor survival of RCC patients with xCT upregulation: c. ccRCC patients, Logrank Test P-value 0.00464; d. chRCC patients, Logrank Test P-value:0.00211, e. pRCC patients, Logrank Test P-value: 7.668e-5.

Figure 6. Significant upregulation of SLC7A11 in 3 subtypes of RCC (ccRCC, chRCC and pRCC) tumors compared to normal tissue

TCGA data analysis revealed the differential expression of SLC7A11, SLC6A7 and SLC1A3 among the 3 subtypes of RCC tumors. Left panel showing the SLC7A11 expression in ccRCC, chRCC and pRCC; middle panel with SLC6A7, right panel with SLC1A3. N = Normal tissue, T = Tumor tissue

Figure 7. Overall poor survival in RCC patients with overexpression of HMGA2 and CTHRC1 which were found highly upregulated (top two genes) in CDC tumors

The available TCGA data were downloaded and utilized to determine the survival probability in ccRCC patients in order to determine the significance of overexpression of these genes in CDC tumors. a. HMGA2 expression in ccRCC and pRCC. b. Overall survival probability of ccRCC and pRCC patients with high expression of HMGA2. c. CTHRC1 expression in ccRCC and pRCC. d. Overall survival probability of ccRCC and pRCC patients with high expression of CTHRC1.

Figure 8. Alteration of CDKN2A and renal cancer patients survival

CDKN2A/p16INK4A alteration significantly decreased the survival in ccRCC a. and pRCC patients b.. TCGA data were used to evaluate the survival probability in renal cancer patients.

Figure 9. SLC family genes downregulated in CDC tumors compared to non-tumor kidney

SLC family genes downregulated in CDC tumors showed as log2 fold changes from 8.369 to 3.580 a. and 3.569 to 0.827 b.. All the genes listed are downregulated significantly in CDC tumors compared to matched non-tumor kidney. RNASeq data was used to identify SLC family gene expression levels in CDC tumors. The difference in the expression levels as a log2 fold change in expression levels was observed.

Figure 10. CDKN2A interacting proteins

To determine human CDKN2A interacting proteins, STRING10 (http://string-db.org/) database which provides known and predicted protein interactions was used. Interaction views of confidence a., evidence b. and actions c. are shown using parameters of highest confidence (0.900) and no more than 5 interactions. Protein interaction data show that CDKN2A interacts with CDK4 and TP53 (listed top 5), E2F1 and EZH2, (listed top 20, data not shown), which were found overexpressed by RNASeq analysis (Figure 3d), suggesting the functional significance of CDKN2A deletion in CDC tumors.

Figure 11. Alteration of SLC6A7 and SLC1A3 association with RCC patients survival

Upper panel-TCGA data analysis of SLC6A7 alteration in 3 subtypes of RCC (ccRCC, chRCC and pRCC). Lower panel- SLC1A3 alteration and RCC patients’ survival.