In this example we will illustrate how knowledge-based predictions of toxicity can be used within a MPO environment to guide the selection and design of compounds with a good balance of properties and reduced risk of toxicity. We will explore a library of compounds with COX2 inhibition data, with the goal of identifying a high quality lead series, using StarDrop’s Probabilistic Scoring to integrate experimental data, predicted ADME properties from the ADME QSAR module and predictions of toxicity risk from the Derek Nexus module.