The genes controlling normal function of citrate and spermine secretion are lost in aggressive prostate cancer and prostate model systems

Abstract

High secretion of the metabolites citrate and spermine is a unique hallmark for normal prostate epithelial cells, and is reduced in aggressive prostate cancer. However, the identity of the genes controlling this biological process is mostly unknown. In this study, we have created a gene signature of 150 genes connected to citrate and spermine secretion in the prostate. We have computationally integrated metabolic measurements with multiple transcriptomics datasets from the public domain, including 3826 tissue samples from prostate and prostate cancer. The accuracy of the signature is validated by its unique enrichment in prostate samples and prostate epithelial tissue compartments. The signature highlights genes AZGP1, ANPEP and metallothioneins with zinc-binding properties not previously studied in the prostate, and the expression of these genes are reduced in more aggressive cancer lesions. However, the absence of signature enrichment in common prostate model systems can make it challenging to study these genes mechanistically.

Keywords: Bioinformatics; Cancer; Transcriptomics.

Graphical abstract

Figure 1

Correlations between metabolites citrate and spermine (A) Correlations between all 23 metabolite measurements across 129 prostate normal and cancer samples from the Bertilsson dataset (Dataset ID 1). The correlation is particularly strong for metabolites citrate and spermine. (B) Correlations between citrate and spermine across 129 prostate normal and cancer samples from Bertilsson. The correlation is high also when extreme values are excluded (highlighted inside the green boundary). (C) Similarity between the citrate, spermine and the average citrate-spermine metabolite profiles across 129 prostate normal and cancer samples from Bertilsson.

Figure 2

Integrity of initial and refined citrate – spermine (CS) gene signatures (A) CMS (Correlation Module Scores) for the 150 genes most positively correlated with the CS metabolite profile for cancer samples in the Bertilsson dataset (Dataset ID 1). The CMS for was statistically significant when compared to CMSs using random metabolite profiles (lognorm test) (B) CMS for the initial cancer CS gene module from Bertilsson (red dots) evaluated in prostate cancer (red circles) and normal (blue circles) samples from 11 additional datasets. The CMS was statistically significant in all datasets (lognorm test, Tables S1 and S2). (C) Fraction of new genes in the refined CS gene signature that replaced genes in the initial CS gene signature. The genes is sorted by importance (rank) on the bottom axis. Of the 150 top ranked genes in the initial CS signature, 74 were replaced in the refined CS signature. (D) Increase in CMS after refinement of the initial CS signature for prostate normal and cancer samples in 11 datasets. The CMS increased in the normal samples, even though the normal samples were not used to create or refine the signature. Cohort ID 4, 5 and 8 did not include normal samples. See also Figure S1 and Tables S1–S4.

Figure 3

Validation of citrate – spermine (CS) gene signature (A) CS signature ssGSEA scores for 11,093 cancer and normal samples in 33 tumor types from the TCGA-complete dataset. We have used standard TCGA cancer type abbreviations [https://gdc.cancer.gov/resources-tcga-users/tcga-code-tables/tcga-study-abbreviations] where PRAD is the abbreviation for prostate cancer. (B) CS signature ssGSEA scores for 53 averaged human normal tissue profiles from the GTex dataset. (C) CS ssGSEA signature scores for 1829 human cell-line and tissue samples, including one prostate adult tissue sample, from the FANTOM dataset. (D) Correlations between CS signature and stroma signature ssGSEA scores for cancer and normal samples in prostate cancer tissue datasets 1–12. The negative correlations in the normal samples are stronger due to less confounding from cancer tissue. Data from Mortensen (dataset ID 9) contains laser dissected prostate normal epithelium and cancer, which probably lack significant amounts of stroma. (E) CS signature ssGSEA scores on spatial transcriptomics data from tissue slice 3.2 in Berglund (dataset ID 20). The colorbar indicates enrichment of the ssGSEA score in each pixel. The corresponding pathological tissue image can be found for image 3.2 in Supplementary Information –Figure S1B from Berglund et al. (Berglund et al., 2018), and comparison shows a strong overlap of high and low CS signature scores with epithelial/lumen and stroma tissue compartments, respectively. Results from all 12 images in Berglund are shown in Figure S2.

Figure 4

Citrate – spermine (CS) signature, tumor grade and metastasis (A) CS signature ssGSEA scores for high-grade (Gleason higher or equal to 4 + 3) and low-grade (Gleason less than or equal to 3 + 4) cancers in 9 datasets. The samples compared correspond to the HG1 and LG1 groups in Table 1. The scores were centered in each cohort before plotting to visualize similarities between datasets better. See also Table S7B. (B) CS signature ssGSEA scores for metastatic, cancer and normal samples in 7 datasets. The scores were centered and normalized to range 0-1 before plotting to visualize similarities between datasets better. The low scores in normal samples is due to the higher content of stroma in normal samples (see Figure S3). (C) CS signature ssGSEA scores from five laser dissected prostate and prostate cancer tissue types from Tomlins (datasets Id 18). The GSEA scores illustrate the loss in CS secretion from normal epithelium through PIN, Cancer and finally Metastasis. The CS signature scores from metastatic samples are comparable to the non-secreting stroma tissue. (D) CS signature ssGSEA scores in 96 metastatic samples (9 from prostate and 87 from other organs) from the Hsu (dataset ID 19). Metastatic samples from prostate origin are more enriched for the CS signature than metastatic samples originating from other sites.

Figure 5

Genes and ontologies (A) Principal Component Analysis (PCA) for Gene Ontology terms associated with CS signature genes. The GO terms are based on a consensus analysis over datasets 1–12 (see STAR Methods). The only observable cluster is formed by the six Metallothioneins from the CS signature. (B) Correlation of ssGSEA signature with four gene signatures from distinct cell types in a single cell sequencing dataset (basal and luminal from the prostate epithelium, fibroblasts and smooth muscle cells from stroma) (Henry et al., 2018) in 9 datasets with normal prostate samples. The CS gene signature correlates with luminal epithelial cells (the cell-type mainly responsible for secreting citrate and spermine) whereas the correlation to stroma tissue types is negative. Dataset 9 is from laser dissected epithelium, which lack stroma tissue. See also Figure S4–S6 and Table S5. Table of the 150 Citrate-spermine signature genes with manually curated functional annotations, related to Figure 5, Table S6. Top 20 Gene Ontology terms for all citrate-spermine signature genes, the six Metallothioneins and the 10 network Hub-genes, related to Figure 5, Table S7. Differential expression results for citrate-spermine target genes, related to Figures 4 and 5.

Figure 6

Model systems (A) CS signature ssGSEA scores for all sample types in Prensner (dataset ID 10), including 58 prostate normal and cancer cell-line samples. Cell-line samples, in general, have very low CS signatures scores. (B) Average CS signature ssGSEA scores for different cell-types in Prensner. The ssGSEA scores were highly reproducable within samples from the same cell-type. Androgen responsive cell-types (MDA-Pca-2b, LNCaP and VCaP) have somewhat higher ssGSEA scores than androgen resistant cell-types (DU145 and PC3). Prostate normal cell-types are similar to cancer cell-types. Number of samples of each cell-type are: MDA-Pca-2b (1), DU145(10), PC3(2), LNCaP(7), VCaP(10), RWPE(9), PrEC(4). (C) CS signature ssGSEA scores in 1019 cancer cell-types from CCLE (dataset ID 24). Androgen responsive prostate cancer cell-types score higher than cancer cell-types from other cancers whereas androgen resistant cell-lines score similar to cell-types from other cancers. (D) CS Signature ssGSEA scores in four datasets with prostate and prostate cancer derived organoids and model systems (dataset IDs 27–30) and one dataset with prostate tumors from mouse models (Aytes, dataset ID 31). The ssGSEA scores were adapted and normalized to CS signature GSEA scores from Prensner. All model systems have consistently low GSEA scores, similar to prostate cancer cell-lines. In total 64 model system samples and 384 mouse tumor samples were analyzed. Dataset descriptions: 27: 2D and 3D cultures derived from prostate cancer cell-line LNCaP (9 samples) and normal cell-line RWPE (9 samples), in total 18 samples. 28: Organoids from primary prostate epithelial cells in mono and co-culture with stromal cells (7 samples), stromal cells in co-culture (4 samples) and macrodissected tumor tissue (2 samples), in total 13 samples. 29: Cells from benign prostatic bulk (3 + 3 samples), basal (3 + 3 samples) and luminal (3 + 3 samples) tissue cultured in two different media, in total 18 samples. 30: Mouse prostate organoids with WT (6 samples) and mutated (6 samples) gene SPOP, in total 12 samples. 31: Prostate tumor tissue from mouse models with different genetic modifications, in total 384 samples. See also Figures S7–S10.

Module refinement procedure and Correlation Module Score (CMS) (A) Flowchart of the module refinement procedure. Each stage 1-3 are explained in the main text. (B) Example of a correlation table used to calculate the Correlation Module Score (CMS). This gene module has four genes (G1-G4) and a CMS of 0.32. See also Figures S11–S18 for performance of the module refinement procedure.