Drug repurposing, i.e. the use of previously approved drugs for novel clinical applications, may dramatically speed up the development of novel therapeutic agents, a urgent need especially during health emergencies. The recent availability of large collections of drug-induced genome-wide expression profiles made the use of modern AI approaches feasible and promising. With this project, we will use a deep adversarial deconfounding model with the aim of producing a gene-expression based embedding of small molecules that is coherent with their known therapeutic applications. Building on our previous experience on gene-expression based computational drug repurposing, we will thus obtain a next-generation tool for finding novel treatment candidates

This project aims to develop a transportation analytics solution that can be used by urban planners and public transit systems authorities. The solution is unique in that it is totally non-intrusive, i.e. does not require commuters’ opt-in, as well as being conveniently scalable. Our solution exploits cellular signal measurement reports to give some visibility and insights into commuters’ mobility patterns and transportation modes, e.g. walking, biking, scooter, bus, etc. Examples of questions that our solution should be able to answer include: • How many means of transportation people use to get to work? • How long do people need to walk when connecting between two modes of transportation? • How long and painful is the “last mile” piece of the commuters’ journeys?