Explore the Agenda
8:00 am Check-In & Morning Coffee
Workshop A
9:00 am Overcoming Data Access & Integration Barriers to Enable AI/ML-Driven Small Molecule Drug Discovery with Open Data & Federated Learning Platforms
A pressing challenge in applying AI to drug discovery is limited access to high-quality, appropriately sized datasets, particularly for early-stage biotech firms. Without robust, diverse, and validated data, AI/ML models struggle to deliver reliable predictions or actionable wet lab outcomes. Open-source and federated learning platforms aim to bridge this gap by providing access to proprietary AI models trained on extensive preclinical, safety, and target product profile data. This workshop explores data-centric challenges and collaborative platforms that democratize AI for small molecule discovery.
Participants will explore:
- The opportunities of open data and federated learning platforms, as well as privacy-preserving data sharing in collaborative drug discovery environments
- Strategies for integrating proprietary and shared datasets to improve model generalizability and predictive power
- Approaches for validating AI-generated hypotheses in wet lab settings, including alignment of experimental design with model outputs
- Techniques for ensuring data quality, chemical diversity, and reproducibility in training datasets
- Examples of how access to large-scale datasets has accelerated small molecule lead optimization and candidate selection
12:00 pm Lunch Break & Networking
Workshop B
1:00 pm Evaluating AI Tools for Target Identification in Small Molecule Discovery: Strengths, Limitations & Strategic Fit
The application of AI to target protein folding and identification is rapidly evolving, with tools like AlphaFold, and emerging hybrid models offering unprecedented insights into protein structure and function. Yet, the diversity of available technologies, each with distinct strengths and limitations, presents a challenge for teams seeking to integrate these tools into their discovery workflows. This workshop offers a foundational and critical evaluation of the current AI landscape for target enablement, helping attendees navigate the complex trade-offs between accuracy, scalability, interpretability, and experimental validation.
Participants will explore:
- The comparative strengths and weaknesses of leading AI tools for predicting protein folding, binding surfaces, and post-translational modifications
- Tool performance for hard-to-drug targets such as GPCRs, transcription factors, and RNA-binding proteins
- Strategies for integrating AI predictions with experimental methods (e.g. cross-linking, cryo-EM, FRET) to validate cryptic binding pockets and dynamic conformations
- Case studies on the use of AI in target identification and the role of pharmacophore modeling
- Practical considerations for selecting the right AI tool based on target class, data availability, and downstream application in small molecule design