Full characterization of Drug-Drug interactions using deep learning methods
Better understanding Drug-Drug interactions (DDIs) is crucial for planning therapies and drugs co-administration. While, considerable efforts are spent in labor-intensive in vivo experiments and time-consuming clinical trials, understanding the pharmacological implications and adverse side-effects for some drug combinations is challenging. The majority of interactions remains undetected until therapies are prescribed to patients. We propose to use computational tools for predicting interactions in order to reduce experimental costs and improve safety. To achieve this, we will use data about the drugs and information about their biological target that are available at the beginning the drug R&D process. Our hypothesis is that artificial intelligence will improve DDI characterization and provide information earlier in the drug development process. Creating such comprehensive tool will help to reduce the risks associated to drug interactions.