Modifier locus mapping of a transgenic F2 mouse population identifies CCDC115 as a novel aggressive prostate cancer modifier gene in humans

Abstract

Background: It is well known that development of prostate cancer (PC) can be attributed to somatic mutations of the genome, acquired within proto-oncogenes or tumor-suppressor genes. What is less well understood is how germline variation contributes to disease aggressiveness in PC patients. To map germline modifiers of aggressive neuroendocrine PC, we generated a genetically diverse F2 intercross population using the transgenic TRAMP mouse model and the wild-derived WSB/EiJ (WSB) strain. The relevance of germline modifiers of aggressive PC identified in these mice was extensively correlated in human PC datasets and functionally validated in cell lines.

Results: Aggressive PC traits were quantified in a population of 30 week old (TRAMP x WSB) F2 mice (n = 307). Correlation of germline genotype with aggressive disease phenotype revealed seven modifier loci that were significantly associated with aggressive disease. RNA-seq were analyzed using cis-eQTL and trait correlation analyses to identify candidate genes within each of these loci. Analysis of 92 (TRAMP x WSB) F2 prostates revealed 25 candidate genes that harbored both a significant cis-eQTL and mRNA expression correlations with an aggressive PC trait. We further delineated these candidate genes based on their clinical relevance, by interrogating human PC GWAS and PC tumor gene expression datasets. We identified four genes (CCDC115, DNAJC10, RNF149, and STYXL1), which encompassed all of the following characteristics: 1) one or more germline variants associated with aggressive PC traits; 2) differential mRNA levels associated with aggressive PC traits; and 3) differential mRNA expression between normal and tumor tissue. Functional validation studies of these four genes using the human LNCaP prostate adenocarcinoma cell line revealed ectopic overexpression of CCDC115 can significantly impede cell growth in vitro and tumor growth in vivo. Furthermore, CCDC115 human prostate tumor expression was associated with better survival outcomes.

Conclusion: We have demonstrated how modifier locus mapping in mouse models of PC, coupled with in silico analyses of human PC datasets, can reveal novel germline modifier genes of aggressive PC. We have also characterized CCDC115 as being associated with less aggressive PC in humans, placing it as a potential prognostic marker of aggressive PC.

Keywords: CCDC115; DNAJC10; Germline variation; LNCaP; Prostate cancer; Quantitative trait loci; RNF149; STYXL1; TRAMP mouse model.

Fig. 1

Schematic outline of mouse experimental study. a Mouse breeding strategy to produce experimental (TRAMP x WSB) F2 mouse population. WSB male and female mice were bred to generate an F1 population of WSB mice. Male WSB F1 mice were then crossed with SV40 transgene positive TRAMP B6 female mice to generate an F2 population of WSB mice that are SV40 Transgene positive (Tg+). b A total of 307 male (TRAMP x WSB) F2 mice were maintained for 210 days, or until humane endpoints were reached, and sacrificed to quantify phenotypic traits of aggressive PC, including primary tumor and metastasis burden. These phenotypic traits were used further in genomic and transcriptomic analyses to identify loci associated with aggressive disease traits in (TRAMP x WXB) F2 mice

Fig. 2

Summary of phenotypic data collected from n = 307 (TRAMP x WSB) F2 transgene positive mice. At 210 days, or when human end points were reached, mice were scarified and tissues collected and analyzed for primary tumor burden and distant metastases. a Age of death. b Prostate tumor burden. c Seminal vesicle tumor burden. d Visceral and lymph node metastasis (Incidence %). Representative H&E staining. e Lung. f Liver. g Lymph node

Fig. 3

Genome wide QTL plots of significant modifier loci in (TRAMP x WSB) F2 mice. a Prostate tumor burden. b Seminal vesicle tumor burden

Fig. 4

TCGA Cohort of candidate gene expression profiles. a. Comparison of differential expression between normal prostate (PAN) Vs adenocarcinoma tissue (PCa) for five candidate genes. b. Survival plot for cases with dysregulation of all 4 candidate genes CCDC115, DNAJC10, RNF149 and STYXL1 (red) compared to cases with normal expression (blue). c. Survival plot of cases with upregulated DNACJ10 expression (red) compared to cases with normal DNAJC10 expression levels (blue). d. Survival plot of cases with CCDC115 dysregulation (red) compared to all cases without CCDC115 differential expression (blue). e. Survival plot of those cases with dysregulated CCDC115 expression comparing loss of CCDC115 expression (blue) and upregulated CCDC115 expression (red). f. Oncoprint showing prostate tumor expression changes in individual cases for each candidate gene (red = upregulated; blue = down regulated). ***p < 0.001

Fig. 5

Lentiviral ectopic over-expression of candidate genes CCDC115, DNAJC10, RNF149 and STYXL1 in the LNCaP PC cell line and their functional effect in vitro and in vivo. a Cell proliferation rates. b Anchorage independent growth. c Invasion. d Flank xenograft tumor growth over time. e Final tumor weight after 5 weeks growth. *p < 0.05; ** p < 0.01; ***p < 0.001