Explore the Agenda
8:00 am Check-In & Morning Coffee
8:50 am Chair’s Opening Remarks
Leveraging Virtual Screening Platforms Powered Using AI/ML & Tapping into Vast Unexplored
Chemical Spaces Beyond Traditional Datasets to Generate New Small Molecules
9:00 am AI–Physics Convergence for Early Discovery: From Tractability & Large-Scale Screening to Candidate Prioritization
- Demonstrate a reproducible workflow that integrates tractability/pocket mapping, large-scale ligand-based and structure-based virtual screening, potency ML using interaction fingerprints, and physics-based scoring (MM-PBSA, RBFE/FEP+, dissociation FE)
- Share applications across two target studies. The first being, 8M-scale screening, pharmacophore/LBVS+SBVS funnel to 496 candidates. The second being, ensemble docking, ML selection, physics-based rescoring
- Demonstrate the translation of computational signals into ranked, purchase-ready lists and model-informed designs in LiveDesign
- Highlight the advantages and caveats in speed and accuracy (e.g., HMR for throughput, cycle-closure curation to remove high-uncertainty RBFE transformations, off-target filters like hERG). Experimental validation is still ongoing
9:30 am Quality Over Quantity: Rethinking AI-Driven Drug Discovery
- Highlight the data fallacy in AI drug discovery and why the common belief that “more data means better models” can actually mislead R&D efforts in pharmaceutical AI
- Elevate how the power of model design and well-designed AI architectures can efficiently learn from smaller, high-quality datasets to enable meaningful insights without massive data volumes
- Demonstrate a path towards smarter discovery and how shifting focus from data quantity to data quality and model integrity leads to more reliable predictions, faster iterations, and ultimately better drug candidates
10:00 am Physics as Guardrails for AI: From ADME Prediction to Quantum-Chemically Accurate Ligand Ranking
- Learn how AI and GPU‑quantum chemistry are creating a virtuous cycle: more accurate data leads to better models, which leads to smarter AI
- Discover how quantum chemical descriptors are supercharging ADMET predictions for difficult targets like Caco-2 Permeability and BBB
- Explore how Promethium's QC Score can be coupled with GenAI for ligand ranking with quantum chemical accuracy
10:30 am Morning Break, Networking & Scientific Poster Session
11:00 am Breaking the Throughput Barrier: Ultra-Large Virtual Screening as a Precision Amplifier for AI-Driven Drug Discovery
- Move towards out-of-domain chemistry by using models that generalize beyond the data we already have, enabling discovery in unexplored regions of biology an chemistry
- Generate novel chemistry and move beyond rediscovery of known scaffolds by investing in platforms that can generate truly new chemical matter
- Expand throughput and explore the full depth of chemical diversity where transformative, next generation drugs reside
11:30 am The ADME Factory: Generating Model-Ready, Structured Data for Generative AI
- Ginkgo provides AI/ML ready ADME data at scale
- Data has been rigorously validated against external benchmarks
- The power of data density: learn everything all at once by combining ADME and transcriptomic pharmacology/toxicology
Tackling Hard Targets with Enhanced Insights from AI/ML Technologies Used in Combination
with Ligand-Based Drug Design Approaches
11:40 am Session Reserved for Superluminal Medicines
12:10 pm The CONECTA™ Platform: Integrating Multimodal Foundation Models with Nature’s Chemical Intelligence to Find Solutions for Hard-To-Drug Targets
- Advanced AI is making it possible to discover new oral therapeutics for chronic disease and address significant unmet patient needs
- Montai Therapeutics’ CONECTA™ platform integrates proprietary bioassay data from a diverse chemical space and multimodal foundation models built on billions of chemical and biological datapoints
- This platform enables us to find diverse compounds inspired by nature’s chemical intelligence that can solve previously undruggable targets with the highest probability of becoming successful drugs
12:40 pm Applying ML to Analyze DNA Encoded Library Data in 3D
- Highlight that current methods to identify structural similarities among hits from DEL screens focus on 2D methods
- Analyze pharmacophore and shape similarity is valuable although computationally expensive
- Learn how to approximate expensive steps with ML and apply to historical and test data sets
1:10 pm Lunch Break, Networking & Scientific Poster Session
2:00 pm Multi-Parameter Optimization Guided by Explainable AI (Xai), Generative Chemistry & Physics-Based Ensemble Modeling: Shortening the Path from Hit-to-Lead Using Revenir
- Uncover how the Revenir drug discovery platform integrates molecular dynamics, ensemble pocket discovery, and collects AI-driven analytics to accelerate structure function understanding
- Using two case studies to demonstrate how an explainable ML framework identifies atomic drivers of potency and liabilities to guide medicinal chemistry optimization
- Explore how generative design powered by Revenir data enables the rapid discovery of novel, experimentally validated small molecules
2:30 pm MolecuLern: AI-Driven Precision in Small Molecule Glue Degraders Through a Data-First Approach to De-Risk & Accelerate Drug Discovery
- Demonstrate how data-first AI frameworks in discovery reduce attrition by sharing practical, validated examples of how they are being used to design real, experimentally confirmed small-molecule degraders, showing what works (and what doesn’t) in moving from prediction to proof
- Gain insight into emerging strategies for precision molecular glue design and highlight novel approaches to rationally engineer glue degraders by integrating structural biology, cheminformatics, and predictive modeling offering valuable lessons for anyone working on targeted protein degradation, GLUES or PROTACs, or complex modality discovery
- Discover frameworks to de-risk R&D pipelines and learn how data-centric model validation and feedback loops can reduce late-stage attrition, accelerate candidate selection, and improve return on discovery investment. Ideas that can be applied across therapeutic areas to accelerate the path from concept to candidate
Harnessing AI/ML Methods to Predict & Optimize Small Molecules for Drug-Like Properties to
Increase Probability of Success & Derisk Pipeline Progression Efforts
3:00 pm Generating AI Strategies for the Enhancement of Hit Finding & Optimization
- Virtual screening strategies for ultra-large databases
- Predictive AI/ML models for potency at the target and ADME-Tox profiling
- Property-based drug design coupled with AI/ML models, chemical space network analysis and composite metrics important in lead optimization
3:30 pm Accelerating Drug Discovery with Eli Lilly’s TuneLab
- TuneLab provides access to Eli Lilly-trained AI models to help accelerate breakthrough medicines to patients
- The platform employs federated learning, a privacy-preserving approach that enables biotechs to tap into Eli Lilly’s AI models without directly exposing their proprietary data
- Learn how to become a participant in this first-of-its-kind, collaborative AI/ML drug discovery platform
4:00 pm Raising the Bar on ADMET Prediction with Open Science
- The majority of medicinal chemistry resources are consumed by the complex task of balancing pharmacokinetics with the mitigation of off-target interactions
- At OpenADMET, we seek to model off-target interactions through a systematic, integrated approach that synthesizes three critical pillars: targeted data generation, high-resolution structural insights from X-ray crystallography and cryo-EM, and predictive machine learning
- OpenADMET both encourages and relies upon community collaboration in the form of model and data releases, blog posts, and blind challenges that provide a statistically rigorous comparison of approaches to push the needle forward on ADMET prediction