AI3SD, OSM & RSC-CICAG Predicting the activity of Drug Candidates when there is no target Workshop Report

This one-day meeting brought together two highly topical areas of drug discovery. Firstly, the application of machine learning/artificial intelligence (ML/AI) approaches to the discovery of new drug leads and secondly, programs where the biological target is not clearly established - so-called phenotypic drug discovery. Whilst there have been a number of publications describing AI or machine learning approaches in drug discovery many use historical data sets that have been carefully cleaned and validated. Unfortunately, real world experimental data from a phenotypic screen is rarely clean and tidy and presents significant challenges to model builders.