Artificial Intelligence for Network Medicine

The main aim of the course is to introduce some of the state-of-the-art Artificial Intelligence (AI) methods for the analysis of complex biological systems, such as networks of proteins, genes and drugs.
The main topics of the course will cover: a) Semi-supervised learning methods for node label and edge prediction problems in biological systems modeled as graphs, with a focus on predicting with unbalanced labels; b)
Graph embedding methods for supervised node and edge label prediction and the unsupervised analysis of complex heterogeneous graphs; d) intrinsic dimensionality estimation and complex data embedding.
Relevant applications in Network Medicine, including drug repurposing, drug-target prediction, and the prediction of genes associated with cancer and genetic diseases will be discussed.
The course is conceived for Computer Science students, but students in Mathematics, Physics, Chemistry, Biology, Pharmacology and Medicine are welcome.