Pathway analysis in attention deficit hyperactivity disorder: An ensemble approach

Abstract

Despite a wealth of evidence for the role of genetics in attention deficit hyperactivity disorder (ADHD), specific and definitive genetic mechanisms have not been identified. Pathway analyses, a subset of gene-set analyses, extend the knowledge gained from genome-wide association studies (GWAS) by providing functional context for genetic associations. However, there are numerous methods for association testing of gene sets and no real consensus regarding the best approach. The present study applied six pathway analysis methods to identify pathways associated with ADHD in two GWAS datasets from the Psychiatric Genomics Consortium. Methods that utilize genotypes to model pathway-level effects identified more replicable pathway associations than methods using summary statistics. In addition, pathways implicated by more than one method were significantly more likely to replicate. A number of brain-relevant pathways, such as RhoA signaling, glycosaminoglycan biosynthesis, fibroblast growth factor receptor activity, and pathways containing potassium channel genes, were nominally significant by multiple methods in both datasets. These results support previous hypotheses about the role of regulation of neurotransmitter release, neurite outgrowth and axon guidance in contributing to the ADHD phenotype and suggest the value of cross-method convergence in evaluating pathway analysis results. © 2016 Wiley Periodicals, Inc.

Keywords: ADHD; GWAS; pathway analyses.

FIG. 1

Pathway analysis workflow. Pathways tested were retrieved from the Pathway Commons database. Genotyped (and imputed) SNPs were mapped to genes in the pathways, and six pathway analysis algorithms were used to test for association with ADHD. A random pathway permutation procedure was used to adjust pathway significance for pathway size. Finally, pathways were ranked based on the number of methods reporting significance and the median P-value across methods. [Color figure can be seen in the online version of this article, available at http://wileyonlinelibrary.com/journal/ajmgb]

FIG. 2

Q–Q plots for seven pathways found nominally significant in both cohorts. Each pathway shows an excess of small SNP effects consistent with a polygenic model of disease risk. [Color figure can be seen in the online version of this article, available at http://wileyonlinelibrary.com/journal/ajmgb]

FIG. 3

(A) The Potassium Channels pathway genes overlaid onto the STRING protein–protein interaction network (low confidence interactions, STRING score <0.5, were removed). Node size is proportion to the IMAGE2 gene P-value, while label size is proportional to the German ADHD GWAS gene P-value. Green node border indicates a gene P-value ≤0.05 in the IMAGE2 dataset, and a green label indicates the same in the German ADHD GWAS dataset. Gray border or label indicates no SNPs present in a particular gene. (B and C) Pathway of Distinction Analysis (PoDA) S scores showing a difference in the distribution between cases and controls in both the IMAGE2 and German ADHD GWAS datasets, respectively. [Color figure can be seen in the online version of this article, available at http://wileyonlinelibrary.com/journal/ajmgb]