Evaluation of postmortem microarray data in bipolar disorder using traditional data comparison and artificial intelligence reveals novel gene targets

Abstract

Large-scale microarray studies on post-mortem brain tissues have been utilized to investigate the complex molecular pathology of bipolar disorder. However, a major challenge in characterizing the dysregulation of gene expression in patients with bipolar disorder includes the lack of convergence between different studies, limiting comprehensive understanding from individual results. In this study, we aimed to identify genes that are both validated in published literature and are important classification features of unsupervised machine learning analysis of Stanley Brain Bank microarray database, followed by augmented intelligence method to identify distinct patient molecular subgroups. Through combining traditional literature approaches and machine learning, we identified TBL1XR1, SMARCA2, and CHMP5 to be replicated in 3 of the 4 studies included our analysis. The expression of these genes segregated unique subgroups of patients with bipolar disorder. Our study suggests the involvement of PPARγ pathway regulation in patients with bipolar disorder.