Deep graph convolutional network-based multi-omics integration for cancer driver gene identification

Abstract

Cancer driver genes play a pivotal role in understanding cancer development, progression, and therapeutic discovery. The plenty of accumulation of multi-omics data and biological networks provides a data foundation for graph neural network (GNN) frameworks. However, most existing methods directly concatenate multi-omics data as features, which may lead to limited performance. To address this limitation, we propose deepCDG, a deep graph convolutional network (GCN)-based multi-omics integration model for cancer driver gene identification. The model first employs shared-parameter GCN encoders to extract representations from three omics perspectives, followed by feature integration through an attention layer, and finally utilizes a residual-connected GCN predictor for cancer driver gene identification. Additionally, deepCDG employs GNNExplainer for cancer driver gene module identification. Experimental results demonstrate the effective predictive performance, model robustness, and computational efficiency of deepCDG. Additionally, biological interpretability analysis further validates the reliability of the identification of cancer driver genes of our framework, and the identified gene modules provide profound insights into complex inter-gene relationships and interactions. We believe our method offers enhanced applicability for cancer driver gene identification and could be extended to other biological research fields in future studies.

Keywords: cancer driver genes; gene modules; graph convolutional networks; multi-omics data.

Figure 1

Overview of deepCDG. (a) deepCDG employs weight-shared GCN encoders to learn gene representations, followed by a MLP-based feature aggregation extractor to fuse the two embeddings from the gene expression omic. Subsequently, an attention layer is used to generate cross-omic integrated gene representations. Finally, a residual GCN classifier is applied to the cancer driver gene prediction. (b) GNNExplainer is introduced to identify cancer gene modules.

Figure 2

PR curve comparison of deepCDG and other baseline models on different PPI networks. (a) PR-curve for CPDB. (b) PR-curve for STRINGdb. (c) PR-curve for MULTINET. (d) PR-curve for PCNet. (e) PR-curve for IRefIndex. (f) PR-curve for IRefIndex_2015.

Figure 3

Feature robustness, network removed and rewired robustness analysis of deepCDG and other baseline methods. (a) Feature robustness analysis. (b) Network removed robustness analysis.(c) Network rewired robustness analysis.

Figure 4

Time overhead analysis of deepCDG and other baseline methods.

Figure 5

Performance of deepCDG and baseline models across two independent sets based on OncoKB and ONGene.

Figure 6

Upset diagram of the overlap of cancer driver genes identified by deepCDG and other identification methods.

Figure 7

GO biological process, cellular component and molecular function enrichment analysis of top predicted genes.

Figure 8

KEGG pathway enrichment analysis of top predicted genes.

Figure 9

Correlation between drug sensitivity and mRNA expression for the top 10 predicted cancer driver genes on CPDB.

Figure 10

Cancer gene module analysis between known cancer driver genes ATRX and ATM.