Identification of Differentially Expressed Genes in Cervical Cancer Patients by Comparative Transcriptome Analysis

Abstract

Cervical cancer is one of the most malignant reproductive diseases seen in women worldwide. The identification of dysregulated genes in clinical samples of cervical cancer may pave the way for development of better prognostic markers and therapeutic targets. To identify the dysregulated genes (DEGs), we have retrospectively collected 10 biopsies, seven from cervical cancer patients and three from normal subjects who underwent a hysterectomy. Total RNA isolated from biopsies was subjected to microarray analysis using the human Clariom D Affymetrix platform. Based on the results of principal component analysis (PCA), only eight samples are qualified for further studies; GO and KEGG were used to identify the key genes and were compared with TCGA and GEO datasets. Identified genes were further validated by quantitative real-time PCR and receiver operating characteristic (ROC) curves, and the highest Youden index was calculated in order to evaluate cutoff points (COPs) that allowed distinguishing of tissue samples of cervical squamous carcinoma patients from those of healthy individuals. By comparative microarray analysis, a total of 108 genes common across the six patients' samples were chosen; among these, 78 genes were upregulated and 26 genes were downregulated. The key genes identified were SPP1, LYN, ARRB2, COL6A3, FOXM1, CCL21, TTK, and MELK. Based on their relative expression, the genes were ordered as follows: TTK > ARRB2 > SPP1 > FOXM1 > LYN > MELK > CCL21 > COL6A3; this generated data is in sync with the TCGA datasets, except for ARRB2. Protein-protein interaction network analysis revealed that TTK and MELK are closely associated with SMC4, AURKA, PLK4, and KIF18A. The candidate genes SPP1, FOXM1, LYN, COL6A3, CCL21, TTK and MELK at mRNA level, emerge as promising candidate markers for cervical cancer prognosis and also emerge as potential therapeutic drug targets.

Figure 1

Identification of gene signatures using microarray data analysis in cervical cancer. (a) Principal component analysis (PCA) of transcriptome data. Three-dimensional scatter plot represents the gene expression patterns between patients' and control samples. (b) Hierarchical clustering displays differentially expressed genes in cervical squamous cell carcinoma. Red color indicates a high-level expression of genes (fold change > 2), and green color indicates the low-level expression of genes (fold change < 2) with p value < 0.05. (c) Distance plot shows frequencies of up- and downregulated genes in patients' samples.

Figure 2

Identification of common deregulated genes in cervical cancer patients. (a) Venn diagram representing the total number of common upregulated (left panel) and downregulated (right panel) DEGs in patients' samples. (b) A set of key genes involved in molecular signaling pathway based on the GO and KEGG pathway analysis. (c) Relative expression of dysregulated genes validated by qPCR. Statistical analysis revealed that the difference in expression between normal and tumor was significant (p ≤ 0.05).

Figure 3

ROC curve for DEGs based on the RT-qPCR data. The figure represents a plot of the sensitivity (true positive rate) vs. 1 − specificity (false positive rate) for all the ΔCT values. The AUC values indicate that the two groups may be distinguished by expression analysis of these markers. The point on the dotted line shows the highest Youden (Y) indices associated with the COP. The resolute values of AUC, Y, and COP for the examined DEGs are listed in Table 2.

Figure 4

Schematic work flow (with inclusion and exclusion criteria) for GEO datasets analysis.

Figure 5

Data mining based on GEO and TCGA datasets. (a) Gene expression profile of selected DEGS in GEO datasets GSE63514 and GSE9750. (b) Box plot representing relative expression patterns of dysregulated genes in cervical squamous cell carcinoma (CESC) using the TCGA database.

Figure 6

PPI network and CytoHubba. (a) STRING creates PPI network of dysregulated genes; each circle represents the node (gene). (b, c) Based on the ranking of the highly interconnected dysregulated top 10 hub proteins predicted by CytoHubba.