AI/ML models are powerful tools for predicting diverse physical and chemical properties of small molecules. However, fine-tuning these models is resource-intensive and challenging to scale for numerous, frequently updated datasets. Automating this process, and ensuring models are re-trained as new data becomes available, enhances the efficiency of using AI/ML models to advance drug discovery programs.

In this webinar, we will present LiveDesign Learning, a new module in Schrödinger’s LiveDesign collaborative enterprise informatics platform, for training and deploying state-of-the-art AI/ML models with minimal manual intervention. LiveDesign Learning treats datasets as dynamic information feeds that evolve as scientists explore new chemistry to deliver optimized AI/ML models. It provides dynamic, reliable, and rapid molecular property predictions in an interactive design environment, allowing teams to triage newly sketched design ideas or hundreds of thousands of compound ideas in minutes for large library screening.