EFMC Medicinal Chemistry 2026

Accelerating Drug Discovery with Integrated AI/ML Modeling

Speaker:
David Rinaldo, Senior Principal Scientist, Applications Science at Schrödinger

Abstract:
AI/ML models are now indispensable in modern drug discovery, offering powerful capabilities ranging from protein structures predictions to ligand property prediction and including 3D protein-ligand binding pose prediction or de novo molecular design. However, effectively deploying and managing these models requires a centralized, collaborative platform.

LiveDesign-ML is the module within the LiveDesign platform that empowers scientists to generate, validate, and deploy state-of-the-art AI/ML models with minimal manual intervention. We will demonstrate its capability for molecular property predictions, which are crucial for triaging newly designed ideas and enabling the screening of hundreds of thousands of compound ideas in minutes. By treating datasets as dynamic information feeds, LiveDesign ML ensures models are always optimized and reliable for your evolving chemistry.

We will also introduce RetroSynth, Schrödinger’s AI-driven synthesis planning platform. Engineered to accelerate and scale conventional retrosynthesis, RetroSynth uses advanced deep learning and a cloud-native Monte Carlo tree search (MCTS) architecture to predict and score optimal, accurate, and cost-efficient synthetic pathways. Learn how the integration of real-time building block data with AI and physics-based modeling in RetroSynth unlocks accurate retrosynthetic analysis, leading to massive project acceleration and significant cost savings in hit identification and lead optimization.

Medicinal chemists, computational chemists, and R&D leaders are welcome to join this workshop. We will showcase how Schrödinger’s LiveDesign-ML and RetroSynth are integrated to tackle critical challenges in the design and synthesis workflow. It will also be the opportunity to see the full potential of integrated AI/ML and physics-based modeling to overcome bottlenecks and advance your drug discovery programs.