A Genome-Wide Association Study and Complex Network Identify Four Core Hub Genes in Bipolar Disorder

Abstract

Bipolar disorder is a common and severe mental illness with unsolved pathophysiology. A genome-wide association study (GWAS) has been used to find a number of risk genes, but it is difficult for a GWAS to find genes indirectly associated with a disease. To find core hub genes, we introduce a network analysis after the GWAS was conducted. Six thousand four hundred fifty eight single nucleotide polymorphisms (SNPs) with p < 0.01 were sifted out from Wellcome Trust Case Control Consortium (WTCCC) dataset and mapped to 2045 genes, which are then compared with the protein-protein network. One hundred twelve genes with a degree >17 were chosen as hub genes from which five significant modules and four core hub genes (FBXL13, WDFY2, bFGF, and MTHFD1L) were found. These core hub genes have not been reported to be directly associated with BD but may function by interacting with genes directly related to BD. Our method engenders new thoughts on finding genes indirectly associated with, but important for, complex diseases.

Keywords: GWAS; bipolar disorder; functional enrichment analysis; network analysis.

Figure 1

Results of the genome wide association study (GWAS). The horizontal axis represents 22 chromosomes and the vertical axis represents the negative logarithm with base 10 of GWAS p-value for each SNP. Red line: canonical 5 × 10⁻⁸ cutoff. Blue line: 0.01 cutoff used in this study.

Figure 2

Overlapped genes associated with four mental illnesses.

Figure 3

BD risk gene interaction network. Only the nodes with a degree ≥4 are shown. Green balls are BD risk genes identified in the GWAS with p < 0.01.

Figure 4

The topology properties of the network. (a) The distribution of number of nodes with different degrees. (b) Frequency distribution of shortest paths. (c) The relationship between topological coefficients and the number of node neighbors. (d) The relationship between betweenness and the number of node neighbors.

Figure 5

Gene clusters identified with Cytoscape. Yellow nodes are core hub genes. No core hub gene is found in Cluster 4 (d). (a) Cluster 1; (b) Cluster 2; (c) Cluster 3; (d) Cluster 4; (e) Cluster 5.