Profiles of overall survival-related gene expression-based risk signature and their prognostic implications in clear cell renal cell carcinoma

Abstract

The present work aimed to evaluate the prognostic value of overall survival (OS)-related genes in clear cell renal cell carcinoma (ccRCC) and to develop a nomogram for clinical use. Transcriptome data from The Cancer Genome Atlas (TCGA) were collected to screen differentially expressed genes (DEGs) between ccRCC patients with OS > 5 years (149 patients) and those with <1 year (52 patients). In TCGA training set (265 patients), seven DEGs (cytochrome P450 family 3 subfamily A member 7 (CYP3A7), contactin-associated protein family member 5 (CNTNAP5), adenylate cyclase 2 (ADCY2), TOX high mobility group box family member 3 (TOX3), plasminogen (PLG), enamelin (ENAM), and collagen type VII α 1 chain (COL7A1)) were further selected to build a prognostic risk signature by the least absolute shrinkage and selection operator (LASSO) Cox regression model. Survival analysis confirmed that the OS in the high-risk group was dramatically shorter than their low-risk counterparts. Next, univariate and multivariate Cox regression revealed the seven genes-based risk score, age, and Tumor, lymph Node, and Metastasis staging system (TNM) stage were independent prognostic factors to OS, based on which a novel nomogram was constructed and validated in both TCGA validation set (265 patients) and the International Cancer Genome Consortium cohort (ICGC, 84 patients). A decent predictive performance of the nomogram was observed, the C-indices and corresponding 95% confidence intervals of TCGA training set, validation set, and ICGC cohort were 0.78 (0.74-0.82), 0.75 (0.70-0.80), and 0.70 (0.60-0.80), respectively. Moreover, the calibration plots of 3- and 5 years survival probability indicated favorable curve-fitting performance in the above three groups. In conclusion, the proposed seven genes signature-based nomogram is a promising and robust tool for predicting the OS of ccRCC, which may help tailor individualized therapeutic strategies.

Keywords: bioinformatic analysis; clear cell renal carcinoma; prognosis.

Figure 1. Flow chart of study design

Abbreviation: KIRC, kidney renal clear cell carcinoma.

Figure 2. Identification and function enrichment analyses of the survival-related DEGs in the TCGA ccRCC cohort

(A) Top 15 enriched GO terms of DEGs. (B) Top 15 enriched KEGG pathways of DEGs. (C) Volcano plot of DEGs: the abscissa represents |log2FC| and the ordinate represents −log10(FDR). The blue and red spots represent significantly down-regulated and up-regulated hub DEGs, respectively. (D) Cluster heatmap of the 33 hub DEGs.

Figure 3. Risk score formula construction based on a seven-gene signature

(A) The LASSO coefficient profiles of the 33 hub DEGs selected by Univariate Cox regression analysis. (B) Partial likelihood deviance for the LASSO coefficient profiles. (C) Forest plot based on Multivariate Cox regression results displays the HRs with corresponding 95% CIs of the seven genes selected by the LASSO model.

Figure 4. Preliminary evaluation of the predictive ability of the seven-gene signature in the training set

(A) The seven-gene-based risk score distribution: using the median risk score as a cut-off point, patients were divided into a low-risk group (blue spots) and high-risk group (red spots). (B) The vital status of 265 patients: yellow and black spots represent alive and dead patients, respectively. (C–E) K–M survival curves of all patients’ OS (n=265), Stage I/II patients’ OS (n=161), Stage III/IV patients’ OS (n=104), respectively. (F,G) ROC curves for OS prediction based on the seven-gene signature within 3- and 5-years, respectively.

Figure 5. The establishment and assessment of a novel nomogram

(A) A nomogram integrating clinical features with a seven-gene risk score for predicting of 3- and 5- years OS in patients with ccRCC. Calibration plots of the nomogram for 3- and 5- years OS prediction in the training set (B,C), internal validation set (D,E), and ICGC cohort (F,G), respectively. The abscissa represents the nomogram-predicted survival probability and the ordinate represents the actual survival.