Suicide candidate genes associated with bipolar disorder and schizophrenia: an exploratory gene expression profiling analysis of post-mortem prefrontal cortex

Abstract

Background: Suicide is an important and potentially preventable consequence of serious mental disorders of unknown etiology. Gene expression profiling technology provides an unbiased approach to identifying candidate genes for mental disorders. Microarray studies with post-mortem prefrontal cortex (Brodmann's Area 46/10) tissue require larger sample sizes. This study poses the question: to what extent are differentially expressed genes for suicide a diagnostic specific set of genes (bipolar disorder vs. schizophrenia) vs. a shared common pathway?

Results: In a reanalysis of a large set of Affymetrix Human Genome U133A microarray data, gene expression levels were compared between suicide completers vs. non-suicide groups within a diagnostic group, namely Bipolar disorder (N = 45; 22 suicide completers; 23 non-suicide) or Schizophrenia (N = 45; 10 suicide completers ; 35 non-suicide). Among bipolar samples, 13 genes were found and among schizophrenia samples, 70 genes were found as differentially expressed. Two genes, PLSCR4 (phospholipid scramblase 4) and EMX2 (empty spiracles homolog 2 (Drosophila)) were differentially expressed in suicide groups of both diagnostic groups by microarray analysis. By qRT-PCR, PLSCR4 and EMX2 were significantly down-regulated in the schizophrenia suicide completers, but could not be confirmed in bipolar disorder.

Conclusion: This molecular level analysis suggests that diagnostic specific genes predominate to shared genes in common among suicide vs. non-suicide groups. These differentially expressed, candidate genes are neural correlates of suicide, not necessarily causal. While suicide is a complex endpoint with many pathways, these candidate genes provide entry points for future studies of molecular mechanisms and genetic association studies to test causality.

Figure 1

Differentially expressed genes between suicide completer vs. non-suicide group in bipolar disorder and schizophrenia cohorts. (A) Venn diagram of differentially expressed genes between suicide completer vs. non-suicide groups within bipolar and schizophrenia. (B) Mean expression levels of PLSCR4 (phospholipid scramblase 4) and EMX2 (empty spiracles homolog 2 (Drosophila)) mRNA transcripts were determined for suicide completers vs. non-suicide groups within both bipolar disorder and schizophrenia in prefrontal cortex by qRT-PCR. The bars represent mean ± SEM. In schizophrenia, the mean expression levels of both genes were significantly down-regulated in the suicide group (n = 5) relative to the non-suicide cases (n = 25) by one-tailed, t-tests for unequal variances (EMX2 t(9) = 2.42, p = 0.02; PLSCR4 t(18) = 3.77, p = 0.0005). The estimated fold changes in the suicide group were -1.51 for EMX2 and -2.16 for PLSCR4 relative to the non-suicide group, consistent with our microarray data. In the bipolar disorder samples, no significant differences in mean expression levels for either gene were found between the suicide (n = 14 for EMX2; n = 12 for PLSCR4) vs. non-suicide cases (n = 15 for EMX2 ; n = 11 for PLSCR4) by unequal variance t-tests. * p < .05 ; *** p < .001.

Figure 2

Distribution of gene ontology groups for biological process at level 4 of differentially expressed genes between suicide vs. non-suicide in schizophrenia cohorts.

Figure 3

Ingenuity pathway analysis of EMX2 and differentially expressed suicide candidate genes in bipolar disorder (A) and schizophrenia (B).