In the beginning of the 21st century, we are witnessing a truly pandemic growth of common diseases that are molecularly and genetically complex, including cancer, neurological disorders, heart disease, diabetes, and many others. Recent advances in the Next Generation Sequencing technology have provided us with tremendous amounts of data, revealing that these complex diseases are linked to the variations in the key genetic mechanisms, if compared to the data from the healthy individuals. Our goal is to use a fast and cheap computational approach to understand the complex interplay between those mechanisms and their effects, which could lead to more accurate diagnostics and more efficient therapy.

In this talk, I will introduce our recent work on understanding the effects of genetic, structural, and post-transcriptional variations associated with complex genetic disorders, with the focus on studying the rewiring of individual molecular interactions and large-scale interaction networks. Specifically, I will first talk about how the supervised and semi-supervised machine learning approaches can be used to predict the individual functional effects of the disease variants. Then, I will introduce a robustness theory based approach to quantify the commutative effects of groups of variants associated with the diseases. I will conclude by highlighting the most important results and discussing the future steps.