Computational epigenetics[1] uses statistical methods and mathematical modelling in epigenetic research. Due to the recent explosion of epigenome datasets, computational methods play an increasing role in all areas of epigenetic research.
Research in computational epigenetics comprises the development and application of bioinformatics methods for solving epigenetic questions, as well as computational data analysis and theoretical modeling in the context of epigenetics. This includes modelling of the effects of histone and DNA CpG island methylation.
Various experimental techniques have been developed for genome-wide mapping of epigenetic information,[2] the most widely used being ChIP-on-chip, ChIP-seq and bisulfite sequencing. All of these methods generate large amounts of data and require efficient ways of data processing and quality control by bioinformatic methods.
A substantial amount of bioinformatic research has been devoted to the prediction of epigenetic information from characteristics of the genome sequence. Such predictions serve a dual purpose. First, accurate epigenome predictions can substitute for experimental data, to some degree, which is particularly relevant for newly discovered epigenetic mechanisms and for species other than human and mouse. Second, prediction algorithms build statistical models of epigenetic information from training data and can therefore act as a first step toward quantitative modeling of an epigenetic mechanism. Successful computational prediction of DNA and lysine methylation and acetylation has been achieved by combinations of various features.[3] [4]
The important role of epigenetic defects for cancer opens up new opportunities for improved diagnosis and therapy. These active areas of research give rise to two questions that are particularly amenable to bioinformatic analysis. First, given a list of genomic regions exhibiting epigenetic differences between tumor cells and controls (or between different disease subtypes), can we detect common patterns or find evidence of a functional relationship of these regions to cancer? Second, can we use bioinformatic methods in order to improve diagnosis and therapy by detecting and classifying important disease subtypes?
The first wave of research in the field of computational epigenetics was driven by rapid progress of experimental methods for data generation, which required adequate computational methods for data processing and quality control, prompted epigenome prediction studies as a means of understanding the genomic distribution of epigenetic information, and provided the foundation for initial projects on cancer epigenetics. While these topics will continue to be major areas of research and the mere quantity of epigenetic data arising from epigenome projects poses a significant bioinformatic challenge, several additional topics are currently emerging.