Juan Sebastian Diaz Boada: Polypharmacy side effect prediction with Graph Convolutional Neural Networks based on heterogeneous structural and biological Data
MSc Thesis in Scientific Computing
Time: Fri 2021-01-22 15.00
Location: Zoom, email organiser
Subject area: Scientific Computing
Respondent: Juan Sebastian Diaz Boada
Opponent: Francesco Ferranti
Supervisor: Narsis Kiani (KI), Michael Hanke
Abstract
The prediction of polypharmacy side effects is crucial to reduce the mortality and morbidity of patients suffering from complex diseases. However, its experimental prediction is unfeasible due to the many possible drug combinations, leaving in silico tools as the most promising way of addressing this problem. This thesis improves the performance and robustness of a state-of-the-art graph convolutional network designed to predict polypharmacy side effects, by feeding it with complexity properties of the drug-protein network. The modifications also involve the creation of a direct pipeline to reproduce the results and test it with different datasets.