Recent advances in generative AI, large language models (LLMs), and multimodal learning are redefining what's possible in drug discovery. Yet significant translational challenges remain—from accurately identifying new targets to predicting therapeutic efficacy and safety in diverse patient populations. This conference directly addresses the need to bridge these gaps by convening experts across machine learning, experimental biology, pharmacology, and clinical research to explore how computational tools can drive innovation across every stage of the drug development pipeline.

This meeting will follow the arc of drug discovery, with each day dedicated to a different phase of translation:

Day 1 focuses on target discovery, highlighting computational models that decode molecular and cellular systems and validate perturbations using spatial, organoid, and real-world datasets.

Day 2 covers drug design and preclinical development, featuring generative and simulation-based approaches for molecule design, pharmacokinetics, and dose optimization.

Day 3 centers on clinical and real-world translation, showcasing multimodal learning from EHRs and clinical trials, digital biomarker discovery, and agentic AI systems for future-ready R&D.

Attendees will gain a clear, end-to-end view of how emerging computational methods are shifting traditional drug development paradigms—from iterative wet-lab cycles to predictive, simulation-driven pipelines. Through curated sessions, cross-disciplinary panels, and

networking events, the program fosters collaboration between AI developers, biologists, translational scientists, and regulatory experts.

Uniquely, this meeting spans the full translational continuum and is paired with the “Antibodies as Drugs” conference, enabling synergistic exchange between platform developers and computational toolmakers. This integrated format offers an unmatched opportunity to shape the next generation of AI-driven drug discovery.