Abstract

The aim of the Project is to combine detailed molecular studies with machine learning approaches to understand how genetic and epigenetic factors give rise to unique gene expression patterns in response to human diseases.

To address this, we attempt to utilise the vast wealth of biological data produced by modern large scale genomic projects. Modern experimental techniques allow direct genome-wide measurement of various molecular feature and these measurements are deposited in large scale quantitative databases. However, the complex interactions of multiple genetic and epigenetic factors are hard to determine experimentally. In the absence of such biological experiments, it becomes necessary to utilise systematic analysis methods, including machine learning.

Current state-of-the-art takes existing knowledge and asks “How does this data relate to what we already know?” By applying machine learning approaches the Project will integrate and explore the data to discover new biological knowledge and generate testable hypotheses. The Project is open-ended.