⇒
Congenital heart defects (CHD) are the most common structural malformation presenting at birth, affecting 1.35 million infants annually world-wide, and the single largest contributor to infant mortality from birth defects. Advances in genomic research methodologies have prompted searches for genes associated with CHDs. However, a significant challenge arising from genomic research is associating specific genes with disease.
⇒
In this study, we exploited the computer-based machine learning methodology to identify genes with a high probability of being involved in cardiac development from their attributes. These genes, when mutated, would therefore be promising candidates for causing CHDs. The accuracy of this gene classifier is 81%. This classifier provides predictions of the cardiac development association status for all protein-coding genes in the mouse genome. This knowledge of cardiac developmental genes will accelerate the processes of reaching a genetic diagnosis for patients born with CHDs.
⇒
This research was supported by British Heart Foundation grants PG/20/14/35030 and PG/22/11127 to Kathryn Hentges' lab.
