Using machine learning in the quest for understanding oligogenic diseases
Machine learning has been successfully applied on understanding the causes of genetic diseases, mostly at the level of single variant prediction. However, clinically relevant and interpretable machine learning methods are still required for more complex cases, such as oligogenic diseases. In this direction, machine learning methods have been recently developed that can predict the pathogenicity and effect of gene pairs in individuals, which can be used to construct predicted pathogenic networks
I am a PhD Candidate at the Interuniversity Institute of Bioinformatics in Brussels (IB2), a collaboration between ULB and VUB. I am also part of the Machine Learning Group of ULB, while at VUB I am affiliated with the Artificial Intelligence lab. I have been working with bacteria phylogenetics, as well as plant and human genomics. My current research is focused on the application of machine learning on the development of predictive tools for oligogenic diseases, and my aim is to apply the gained knowledge on the study and understanding of neurodevelopmental disorders, such as intellectual disability and autism.