Machine learning for epigenetics: some initial results
Guido Sanguinetti (University of Edinburgh)
Friday 21st November, 2014 15:00-16:00 Maths 203
Epigenetics attempts to explain biological variability through factors other than genetic variability. It is thought to play a major role in development and in many diseases, and it has gathered a lot of attention over the last 5 years or so due to the advent of next generation sequencing techniques which actually allow the measurement of many epigenetic modifications. About three years ago I started taking an interest in modelling such data, in particular histone modifications and DNA methylation. In this talk I will give a brief intro to the area, and briefly describe three areas where we made some progress: defining statistical testing procedures for histone modifications, relating histone modifications to protein binding, and devising statistical testing procedures for DNA methylation. The talk will be mostly high level in an attempt not to pre-empt more detailed talks by post-docs and students who have actually done the work (Gabriele Schweikert and Tom Mayo).
Refs: Gabriele Schweikert, Botond Cseke, Thomas Clouaire, Adrian Bird and Guido Sanguinetti, MMDiff: quantitative testing for shape changes in ChIP-Seq data sets, BMC Genomics 14:826, 2013