Progress and promise in understanding the genetic basis of common diseases

Abstract

Susceptibility to common human diseases is influenced by both genetic and environmental factors. The explosive growth of genetic data, and the knowledge that it is generating, are transforming our biological understanding of these diseases. In this review, we describe the technological and analytical advances that have enabled genome-wide association studies to be successful in identifying a large number of genetic variants robustly associated with common disease. We examine the biological insights that these genetic associations are beginning to produce, from functional mechanisms involving individual genes to biological pathways linking associated genes, and the identification of functional annotations, some of which are cell-type-specific, enriched in disease associations. Although most efforts have focused on identifying and interpreting genetic variants that are irrefutably associated with disease, it is increasingly clear that--even at large sample sizes--these represent only the tip of the iceberg of genetic signal, motivating polygenic analyses that consider the effects of genetic variants throughout the genome, including modest effects that are not individually statistically significant. As data from an increasingly large number of diseases and traits are analysed, pleiotropic effects (defined as genetic loci affecting multiple phenotypes) can help integrate our biological understanding. Looking forward, the next generation of population-scale data resources, linking genomic information with health outcomes, will lead to another step-change in our ability to understand, and treat, common diseases.

Keywords: common diseases; genome-wide association studies; human genetics.

Figure 1.

The NHGRI GWA catalogue. Published associations are displayed by chromosome and colour-coded by class of phenotype. As of December 2013, the catalogue included 11 912 SNPs that were significant at p < 10⁻⁵ and 6400 SNPs that were genome-wide significant (p < 5 × 10⁻⁸) [5]. Currently, the catalogue includes approximately 9400 genome-wide significant SNPs.

Figure 2.

Manhattan plots from dense imputed data. A Manhattan plot for chromosome 4 for a GWAS of height in the UK Biobank imputed dataset of approximately 73 000 000 genetic variants (genome-wide) in approximately 150 000 individuals. The plot is adapted from fig. 3 in the document ‘UK Biobank phasing and imputation documentation’, written by J. Marchini (see Web resources).

Figure 3.

Genes involved in pleiotropy. Barplot of the 40 genes in the NHGRI GWAS catalogue (www.genome.gov/gwastudies, accessed 23 October 2014) that have the highest number of associations where they are listed as the reported gene. Genes in the MHC region have been excluded. Colours show the number of associations that are attributed to each different category of study phenotypes.