Using epigenomics data to predict gene expression in breast cancer

Abstract

Epigenetics is the study that deals with phenotype alterations that do not cause any modification in the DNA sequence of cells. Basically, it adds something to the top of DNA to alter its properties. This subsequently prevents the execution of certain behavior of DNA. Such epigenetic alterations are found in cancerous cells. These alterations are not the only cause of cancer; nevertheless, accurate statistical data that provides adequate shreds of evidence is still missing. In this research, four different types of data are used to bifurcate cancerous cells from non-cancerous cells. The data are Methylation, Histone, Human Genome and RNA-Seq data. The processing of these datasets is done using custom R-script. The tool that is used for feature selection and classification in the presented work is Weka 3.With the help of the machine learning method, the epigenetics data shows the prediction of breast cancer in the given set of cells.