Understanding the role of the non-coding genome in congenital heart disease

Congenital heart disease (CHD) are defects that occur in the heart during development. It is the leading cause of birth defects in babies. However, there is limited knowledge to prevent CHD mainly due to lack of a comprehensive understanding of the causal genetic factors involved. So far, the focus of CHD studies has been mostly on the variants lying in gene-coding regions of the genome. However, a lot of variants lie in the non-coding part of the genome where their functional role is yet to be deciphered. This thesis presents a machine learning method to identify candidate pathogenic non-coding variants in CHD.