Network-based survival analysis reveals subnetwork signatures for predicting outcomes of ovarian cancer treatment

Abstract

Cox regression is commonly used to predict the outcome by the time to an event of interest and in addition, identify relevant features for survival analysis in cancer genomics. Due to the high-dimensionality of high-throughput genomic data, existing Cox models trained on any particular dataset usually generalize poorly to other independent datasets. In this paper, we propose a network-based Cox regression model called Net-Cox and applied Net-Cox for a large-scale survival analysis across multiple ovarian cancer datasets. Net-Cox integrates gene network information into the Cox's proportional hazard model to explore the co-expression or functional relation among high-dimensional gene expression features in the gene network. Net-Cox was applied to analyze three independent gene expression datasets including the TCGA ovarian cancer dataset and two other public ovarian cancer datasets. Net-Cox with the network information from gene co-expression or functional relations identified highly consistent signature genes across the three datasets, and because of the better generalization across the datasets, Net-Cox also consistently improved the accuracy of survival prediction over the Cox models regularized by L(2) or L(1). This study focused on analyzing the death and recurrence outcomes in the treatment of ovarian carcinoma to identify signature genes that can more reliably predict the events. The signature genes comprise dense protein-protein interaction subnetworks, enriched by extracellular matrix receptors and modulators or by nuclear signaling components downstream of extracellular signal-regulated kinases. In the laboratory validation of the signature genes, a tumor array experiment by protein staining on an independent patient cohort from Mayo Clinic showed that the protein expression of the signature gene FBN1 is a biomarker significantly associated with the early recurrence after 12 months of the treatment in the ovarian cancer patients who are initially sensitive to chemotherapy. Net-Cox toolbox is available at http://compbio.cs.umn.edu/Net-Cox/.

Figure 1. Overview of Net-Cox.

The patient gene expression data and the survival information specified by followup times and event indicators are illustrated on the left. The cost function of Net-Cox given in the box combines the total likelihood of Cox regression with a network regularization. The gene network shown is used as a constraint to encourage smoothness among correlated genes, i.e. the coefficients of the genes connected with edges of large weights are similarly weighted.

Figure 2. Consistency of signature genes (Sloan-Kettering cancer genes).

The x-axis is the number of selected signature genes ranked by each method. The y-axis is the percentage of the overlapped genes between the selected genes across the ovarian cancer datasets. The plots show the results for the death outcome (A) and the tumor recurrence outcome (B).

Figure 3. Cross-dataset survival prediction (Sloan Kettering cancer genes).

The first four columns of plots show the Kaplan-Meier survival curves for the two risk groups defined by Net-Cox (co-expression network), Net-Cox (functional linkage network), and . The fifth column of plots compare the time-dependent area under the ROC curves based on the estimated risk scores (PIs). The plots show the results for the death outcome by training with TCGA dataset and test on Tothill Dataset (A), the death outcome by training with TCGA dataset and test on Bonome Dataset (B), the tumor recurrence outcome by training with TCGA dataset and test on Tothill Dataset (C).

Figure 4. Consistency of signature genes on randomized co-expression networks.

The x-axis is the number of selected signature genes ranked by each method. The y-axis is the percentage of the overlapped genes between the selected genes across the ovarian cancer datasets. The red curve reports the mean and the standard deviation of the percentages averaged over the experiments of 50 randomized networks. The plots show the results for the death outcome (A) and the tumor recurrence outcome (B).

Figure 5. Statistical analysis of log-partial likelihood.

The optimal was fixed and is set to allow better evaluation of the network information. The log-partial likelihood computed by Net-Cox on the real co-expression network and on the randomized co-expression network are reported against tumor recurrence in the TCGA and Tothill datasets. The stars represent the results with the real co-expression networks, and the boxplots represent the results with the randomized networks.

Figure 6. Statistical analysis of cross-validation log-partial likelihood (CVPL).

The optimal was fixed and is varied from to . The CVPL of five-fold cross-validation on the real co-expression network and on the randomized co-expression network are reported against tumor recurrence in TCGA dataset (A) and Tothill dataset (B). The stars represent the results with the real co-expression networks, and the boxplots represent the results with the randomized networks.

Figure 7. Protein-Protein interaction subnetworks of signature genes identified by Net-Cox on the TCGA dataset.

(A) The PPI subnetworks identified by Net-Cox on the co-expression network. (B) The PPI subnetworks identified by Net-Cox on the functional linkage network.

Figure 8. Representative photomicrographs showing various levels of FBN1 expression in ovarian tumor arrays.

The brown regions are stromal area showing expression of FBN1.

Figure 9. Kaplan-Meier survival plots on FBN1 expression groups.

(A) Kaplan-Meier survival curve of recurrence between 14 to 72 month by FBN1 staining groups on Mayo Clinic dataset. (B) Kaplan-Meier survival curve of recurrence between 20 to 72 month by the expression of FBN1 on Tothill dataset. (C)–(E) Kaplan-Meier survival curves of recurrence between 20 to 72 month by the expression of FBN1 on TCGA dataset with AgilentG4502A platform, HuEx-1_0-st-v2 platform, and Affymetrix HG-U133A platform, respectively. In plot(A), the groups with FBN1 staining score 1 and 2 are combined into the high-expression group. In plots(B)–(E), the patients are divided into two groups of the same size by the expression of FBN1.