A systems genetics approach identifies CXCL14, ITGAX, and LPCAT2 as novel aggressive prostate cancer susceptibility genes

Abstract

Although prostate cancer typically runs an indolent course, a subset of men develop aggressive, fatal forms of this disease. We hypothesize that germline variation modulates susceptibility to aggressive prostate cancer. The goal of this work is to identify susceptibility genes using the C57BL/6-Tg(TRAMP)8247Ng/J (TRAMP) mouse model of neuroendocrine prostate cancer. Quantitative trait locus (QTL) mapping was performed in transgene-positive (TRAMPxNOD/ShiLtJ) F2 intercross males (n = 228), which facilitated identification of 11 loci associated with aggressive disease development. Microarray data derived from 126 (TRAMPxNOD/ShiLtJ) F2 primary tumors were used to prioritize candidate genes within QTLs, with candidate genes deemed as being high priority when possessing both high levels of expression-trait correlation and a proximal expression QTL. This process enabled the identification of 35 aggressive prostate tumorigenesis candidate genes. The role of these genes in aggressive forms of human prostate cancer was investigated using two concurrent approaches. First, logistic regression analysis in two human prostate gene expression datasets revealed that expression levels of five genes (CXCL14, ITGAX, LPCAT2, RNASEH2A, and ZNF322) were positively correlated with aggressive prostate cancer and two genes (CCL19 and HIST1H1A) were protective for aggressive prostate cancer. Higher than average levels of expression of the five genes that were positively correlated with aggressive disease were consistently associated with patient outcome in both human prostate cancer tumor gene expression datasets. Second, three of these five genes (CXCL14, ITGAX, and LPCAT2) harbored polymorphisms associated with aggressive disease development in a human GWAS cohort consisting of 1,172 prostate cancer patients. This study is the first example of using a systems genetics approach to successfully identify novel susceptibility genes for aggressive prostate cancer. Such approaches will facilitate the identification of novel germline factors driving aggressive disease susceptibility and allow for new insights into these deadly forms of prostate cancer.

Figure 1. Experimental strategy for identifying novel susceptibility genes for aggressive prostate cancer.

Candidate aggressive disease modifier genes were identified in an F2 intercross population involving the TRAMP mouse model of prostate tumorigenesis and the NOD/ShiLtJ strain of mouse, which is highly susceptible to aggressive disease development (A). This strategy involved QTL mapping to identify genomic regions associated with aggressive disease traits, followed by eQTL mapping and gene expression-trait correlation analyses to nominate candidate modifiers. Following this, a strategy involving two types of data derived from human prostate patients was used to nominate the highest priority candidate genes: (B) human prostate cancer primary tumor gene expression datasets; and (C) a human prostate cancer GWAS dataset. Only those genes designated as being associated with aggressive disease development in both the tumor gene expression and GWAS datasets were designated as being high priority candidate genes (D).

Figure 2. Genomic locations of eQTLs relative to their cognate transcript.

The chromosomal locations for all statistically significant eQTLs identified in (TRAMP × NOD/ShiLtJ) F2 tumors (FDR <0.05) are illustrated relative to their associated transcript.

Figure 3. Higher levels of five QTL candidate genes are associated with poor DFS in TCGA (Provisional) and GSE21032 prostate cancer gene expression datasets.

(A) ‘Oncoprint’ analysis demonstrates that 45/246 (18%) of cases in TCGA (Provisional) gene expression dataset have exclusively higher than average expression levels of five QTL candidate genes. (B) These higher levels of expression are associated with a reduced DFS in TCGA (Provisional) cohort. (C). Oncoprint' analysis demonstrates that 16/131 (12%) of cases in the GSE21032 gene expression dataset have exclusively higher than average expression levels of the same five QTL candidate genes. (D) As was the case with TCGA (Provisional) dataset, higher levels of expression of these genes is associated with a reduced DFS in the GSE21032 cohort.