Layers of epistasis: genome-wide regulatory networks and network approaches to genome-wide association studies

Abstract

The conceptual foundation of the genome-wide association study (GWAS) has advanced unchecked since its conception. A revision might seem premature as the potential of GWAS has not been fully realized. Multiple technical and practical limitations need to be overcome before GWAS can be fairly criticized. But with the completion of hundreds of studies and a deeper understanding of the genetic architecture of disease, warnings are being raised. The results compiled to date indicate that risk-associated variants lie predominantly in noncoding regions of the genome. Additionally, alternative methodologies are uncovering large and heterogeneous sets of rare variants underlying disease. The fear is that, even in its fulfillment, the current GWAS paradigm might be incapable of dissecting all kinds of phenotypes. In the following text, we review several initiatives that aim to overcome these limitations. The overarching theme of these studies is the inclusion of biological knowledge to both the analysis and interpretation of genotyping data. GWAS is uninformed of biology by design and although there is some virtue in its simplicity, it is also its most conspicuous deficiency. We propose a framework in which to integrate these novel approaches, both empirical and theoretical, in the form of a genome-wide regulatory network (GWRN). By processing experimental data into networks, emerging data types based on chromatin immunoprecipitation are made computationally tractable. This will give GWAS re-analysis efforts the most current and relevant substrates, and root them firmly on our knowledge of human disease.

Figure 1

A proposed computational approach for estimating the ramifications of variation. 1A) A variant on chromosome A has been found to associate with TraitX. The association is a property of all variants in strong LD with the initial variant. The first list of candidate variant nodes is obtained by following LD edges. 1B) An LD edge brings us to the E1 enhancer node. Enhancers impinge on the transcription of genes. In order to compile a list of candidate gene nodes, we follow Long-range edges. 1C) A Long-range edge takes us to the P1 promoter node and the Gene1 gene node. This means that empiric evidence exists in favor of a regulatory interaction between E1 and Gene1 via P1. Gene1 is a transcription factor, but is not known to affect TraitX. Stronger evidence might exist and the search continues. In order to find candidate targets of Gene1, cistromic edges are followed. 1D) A cistromic edge reaches the E2 enhancer node on chromosome B. This means that empiric evidence exists supporting binding events of the Gene1 product at E2. Long-range edges are followed in the search for genes. 1E) A long-range edge reveals an interaction between E2 and Gene2 via P2. Gene2 is known to affect TraitX. A circular path closed by a trait node through the the GWRN has now been found. Through this path, each node and edge is supported by some form of empiric evidence. Additionally, the states of all or some of nodes an edges in the path might be validated for the system under study. The variant associated with TraitX, affects the transcriptional output of a gene potentially regulating another gene underlying TraitX. The path is not intended as supporting evidence for the causality of the variant, but directs the investigator to the most likely explanation given available data. The investigator can then choose among the reported paths how to best invest his resources on further experimental validation.

Figure 2

A meagre sliver of the GWRN for the K562 cell line. The two outermost circles show chromosome numbers and ideograms. The following two circles show all genes in orange followed by all active enhancers in red. Edges within the circle show the cistromes for three arbitrary transcription factors. The genomic locations of the genes are marked with text in the innermost circle. These locations act as tethers from which cistromic edges extend towards all positions in the genome where the gene product is bound. Xrcc4, highlighted in red, illustrates the one to many relationship that cistromic edges encode. The figure is intended to glean some insight into the scale and complexity of the GWRN, but also into its feasibility. The technology is currently available, but many cistromes and cell types remain to be assayed. The relation between what remains to be done and what has already been achieved does not exceed a couple of orders of magnitude. Larger technological hurdles have been overcome within the last ten years. All data shown was produced using the K562 cell line. The binding sites were determined through ChIP-seq and were obtained from the ENCODE DCC at UCSC. Data for active regulatory elements was obtained from the supplementary data in Heintzman et al. 2009 [20]. Chromosome ideograms and gene annotations were obtained from the UCSC Genome Browser. The graphic was generated using an in-house Processing program adhering to the Circos information aesthetic [28].