Deep Dive Workshop: AI-Driven Ternary Complex Prediction & Optimization to Reduce Medicinal Chemistry Burden & Accelerate Induced Proximity Drug Discovery
Time: 9:00 am
day: Day Two
Details:
The design of induced proximity-based drugs requires precise ternary complex formation to achieve optimal target engagement and functional efficacy. Traditionally, medicinal chemistry has relied on brute-force screening, but recent advances in AI-driven modeling and bioinformatics are transforming this process—enabling faster, more accurate, and costeffective drug design.
This session will explore how machine learning and computational modeling can predict stable ternary complexes with greater accuracy, refine protein-protein interaction networks, and integrate experimental data to accelerate drug discovery pipelines. Key considerations include minimizing structural bias, enhancing target selectivity, and optimizing hit-to-lead strategies for novel mechanisms of action.
We will showcase real-world applications of AI and bioinformatics in reducing medicinal chemistry burdens, streamlining lead optimization, and driving the next generation of induced proximity-based drugs.
Key Learning Objectives:
How are AI-driven models evolving beyond traditional screening methods to improve the accuracy of prospectively predicting stable ternary complexes?
How can ML approaches optimize protein-protein interactions to improve ligand design, target selectivity, and functional readouts in induced proximity drug discovery to minimize off-target effects and accelerate clinically viable induced proximity therapeutics?
How does integrating bioinformatics with experimental data reduce structural bias, accelerate validation, and improve hit-to-lead strategies for novel MoAs?