Epigenetic epidemiology of common complex disease: prospects for prediction, prevention, and treatment

Abstract

As part of the PLoS Epigenetics Collection, Caroline Relton and George Davey Smith discuss the potential of epigenetics for the treatment and prevention of common complex diseases, including cancer.

Figure 1. Epigenetic modifications.

Chromosomes are composed of chromatin, consisting of DNA wrapped around eight histone protein units. Each DNA-bound histone octamer is a nucleosome. Histone tails protruding from histone proteins are decorated with modifications, including phosphorylation (Ph), methylation (Me), and acetylation (Ac). DNA molecules are methylated by the addition of a methyl group to carbon position 5 on cytosine bases when positioned adjacent to a guanine base (CpG sites), a reaction catalyzed by DNA methyltransferase enzymes. DNA methylation maintains repressed gene activity. Transcription involves the conversion of DNA to messenger RNA (mRNA), which is usually repressed by DNA methylation and histone deacetylation. mRNA is translated into a protein product, but this process can be repressed by binding of microRNA (miRNA) to mRNA. Each miRNA binds to the mRNA of up to 200 gene targets. miRNAs can also be involved in establishing DNA methylation and may influence chromatin structure by regulating histone modifiers.

Figure 2. Defining the causal relationship between epigenetic patterns and phenotype.

Analysis of the respective relationships between DNA methylation (CpG), body mass index (BMI), and cardiovascular disease (CVD) can help to inform the direction of causality. An observed association between BMI and CpG and CpG and CVD will not decipher which of the depicted scenarios apply.

Figure 3. Applying Mendelian randomization to define the causal relationship between phenotype and disease.

An example based upon the report of Lintel-Nietschke et al. (2008) reporting the association between a gene variant in the LDLR gene with decreased low density lipoprotein-cholesterol (LDL-C) levels and with a reduced risk of coronary artery disease (CAD). The variant can be used in a Mendelian randomization approach to test the causal relationship between LDL-C and CAD. If LDL-C has a causal role in CAD, an association between the LDLR gene variant and disease risk would be seen (red dashed arrow). If LDL-C levels are correlated with CAD risk but not causal, then the gene variant will not show an association with CAD risk. This will establish whether reverse causation is at play and remove the potential confounding influence of factors such as smoking and nutritional status.

Figure 4. Incorporating epigenetic information in a Mendelian randomization framework.

(A) Alcohol exposure is associated with risk of head and neck squamous cell carcinoma (HNSCC) and this may be mediated by altered DNA methylation (CpG). The relationship between alcohol exposure and HNSCC is potentially confounded by factors such as socio-economic position, which correlate with both exposure and disease. A common variant in ADH1B can be used as an unconfounded, genetic proxy for alcohol exposure, and if this SNP is associated with CpG (either locally or more widely across the genome), it would lend support to the hypothesis that alcohol intake causally influences DNA methylation. However, showing associations of these epigenetic measures with HNSCC does not demonstrate causality of either alcohol or CpG on HNSCC, as either or both associations (alcohol→HNSCC and CpG→HNSCC) could be confounded or alcohol could influence HNSCC through another pathway (dashed line). (B) To investigate this, another Mendelian randomization experiment could be undertaken using an SNP known to have a cis influence on loci-specific DNA methylation. If an association were observed between this SNP and both CpG and HNSCC, this would support a role for DNA methylation in the causation of HNSCC.