Genes and (common) pathways underlying drug addiction

Abstract

Drug addiction is a serious worldwide problem with strong genetic and environmental influences. Different technologies have revealed a variety of genes and pathways underlying addiction; however, each individual technology can be biased and incomplete. We integrated 2,343 items of evidence from peer-reviewed publications between 1976 and 2006 linking genes and chromosome regions to addiction by single-gene strategies, microrray, proteomics, or genetic studies. We identified 1,500 human addiction-related genes and developed KARG (http://karg.cbi.pku.edu.cn), the first molecular database for addiction-related genes with extensive annotations and a friendly Web interface. We then performed a meta-analysis of 396 genes that were supported by two or more independent items of evidence to identify 18 molecular pathways that were statistically significantly enriched, covering both upstream signaling events and downstream effects. Five molecular pathways significantly enriched for all four different types of addictive drugs were identified as common pathways which may underlie shared rewarding and addictive actions, including two new ones, GnRH signaling pathway and gap junction. We connected the common pathways into a hypothetical common molecular network for addiction. We observed that fast and slow positive feedback loops were interlinked through CAMKII, which may provide clues to explain some of the irreversible features of addiction.

Figure 1. Pipeline for Collection of Data and Identification of (Common) Molecular Networks for Drug Addiction

Strategies used to study the genetic and environmental influences underlying addiction were divided into two types. Candidate gene-based strategies identified a list of genes related to addiction, including candidate genes identified in classical animal models, significantly differentially expressed genes identified in microarray or proteomics assays, and OMIM annotations. Strategies focused on genetic factors identified a list of addiction-vulnerable regions through animal QTL studies, genetic linkage studies, and population association studies. We integrated these datasets and obtained a list of human addiction-related genes. This dataset was then divided into four subsets based on addictive drugs, and analyzed using KOBAS, a statistical method to identify enriched molecular pathways. Molecular pathways enriched for all subsets were considered to be common pathways for drug addiction, which were further connected to construct a common molecular network underlying different types of addiction.

Figure 2. Hypothetical Common Molecular Network for Drug Addiction

The network was constructed manually based on the common pathways identified in our study and protein interaction data. Addiction-related genes were represented as white boxes while neurotransmitters and secondary massagers were highlighted in purple. The common pathways are highlighted in green boxes. Related functional modules such as “regulation of cytoskeleton”, “regulation of cell cycle”, “regulation of gap junction”, and “gene expression and secretion of gonadotropins” were highlighted in carmine boxes. Several positive feedback loops were identified in this network. Fast positive feedback loops were highlighted in red lines and slow ones were highlighted in blue lines.