Prognostic Biomarker Identification Through Integrating the Gene Signatures of Hepatocellular Carcinoma Properties

Abstract

Many molecular classification and prognostic gene signatures for hepatocellular carcinoma (HCC) patients have been established based on genome-wide gene expression profiling; however, their generalizability is unclear. Herein, we systematically assessed the prognostic effects of these gene signatures and identified valuable prognostic biomarkers by integrating these gene signatures. With two independent HCC datasets (GSE14520, N=242 and GSE54236, N=78), 30 published gene signatures were evaluated, and 11 were significantly associated with the overall survival (OS) of postoperative HCC patients in both datasets. The random survival forest models suggested that the gene signatures were superior to clinical characteristics for predicting the prognosis of the patients. Based on the 11 gene signatures, a functional protein-protein interaction (PPI) network with 1406 nodes and 10,135 edges was established. With tissue microarrays of HCC patients (N=60), we determined the prognostic values of the core genes in the network and found that RAD21, CDK1, and HDAC2 expression levels were negatively associated with OS for HCC patients. The multivariate Cox regression analyses suggested that CDK1 was an independent prognostic factor, which was validated in an independent case cohort (N=78). In cellular models, inhibition of CDK1 by siRNA or a specific inhibitor, RO-3306, reduced cellular proliferation and viability for HCC cells. These results suggest that the prognostic predictive capacities of these gene signatures are reproducible and that CDK1 is a potential prognostic biomarker or therapeutic target for HCC patients.

Keywords: Biomarker; Gene signature; Hepatocellular carcinoma; Network; Overall survival.

Fig. 1

Nearest template prediction (NTP) results and their concordance with gene signatures in the GSE14520 and GSE54236 datasets. (a) NTP results in dataset GSE14520 (N = 242), with each column representing the prediction results for individual patients. Gene signatures suggesting poorer overall survival (OS) are labeled in blue, and signatures that suggest better OS are labeled in yellow (FDR, P < 0.05). The gray column indicates the presence of an unclassified group of patients (FDR, P > 0.05). The left label indicates the gene signature name, as listed in Table 1. (b) Heat map of Cramer's V coefficient values for pair-wise gene signatures in GSE14520; the signatures are clustered according to their degree of correlation. (c) NTP results in dataset GSE54236 (N = 78), with each column representing the prediction result for individual patients. Poorer (FDR, P < 0.05), better (FDR, P < 0.05), or unclassified (FDR > 0.05) outcomes for each patient are labeled in blue, yellow, or gray, respectively. The left label indicates the gene signature name as listed in Table 1. (d) Heat map of Cramer's V coefficient values for pair-wise gene signatures in GSE54236; the signatures are clustered according to their degree of correlation. Gene signatures that are significantly associated with the OS of HCC patients are labeled in red, and those not associated with OS are labeled in blue.

Fig. 2

Kaplan-Meier plots and log-rank tests for the 15 gene signatures that are associated with the overall survival of HCC patients in GSE14520.

Fig. 3

Kaplan-Meier plots and log-rank tests for the 12 gene signatures that are associated with the overall survival of HCC patients in GSE54236.

Fig. 4

Random survival forests and the corresponding VIMP values for gene signatures in prediction of overall survival for HCC patients in datasets GSE14520 (N = 242) and GSE54236 (N = 78). The error rates according to the number of trees generated in the random survival forest analyses in GSE14520 (a) and GSE54236 and (c). The mean VIMP values for each variable after 100 runs are provided in GSE14520 (b) and GSE54236 (d).

Fig. 5

The core functional PPI network derived from the 11 gene signatures that were significantly associated with the overall survival of HCC patients (genes with node degree > 60). The red nodes are genes included in the gene signature, and degree nodes are linker genes in the network construction derived from the Reactome FI plugin of Cytoscape. The size of the node correlates with the degree of the indicated gene in the network. CDK1, HDAC2, RAD21, EP300, RPS27A and RPS27 were genes with the top-ranked degrees.

Fig. 6

The protein expression levels of RAD21, CDK1, and HDAC2 in tumor and adjacent normal HCC tissues and their associations with overall survival (OS) for HCC patients. (a)CDK1, HDAC2, and RAD21 were significantly increased in HCC tissues compared with adjacent normal tissues (Wilcoxon signed rank test, P < 0.001). (b) Higher expression levels of CDK1 (log-rank test, P = 0.001), HDAC2 (log-rank test, P = 0.014), and RAD21 (log-rank test, P = 0.027) in the HCC tissues were associated with worse OS of the patients compared with lower expression levels.