BPS 2025
Physics+AI-Guided Design and Plate-Based Synthesis Unlock >10¹² Cyclic Peptidomimetics for Cell-Permeable Inhibitor Discovery
Wentao Guo
Technical Business Development – AI/ML solutions, Atombeat Inc.
ABSTRACT
Cyclic peptidomimetics occupy the sweet spot between small molecules and biologics, combining high target affinity with proteolytic stability and intrinsic cell penetration. However, their vast chemical space presents significant challenges for discovery. To address this, we (Atombeat Inc.) introduce RiDYMO.PepTx, a physics- and AI-guided platform that enables rational in silica design within an in silico library of over 10¹² macrocycles, constructed from more than 500 natural and unatural amino acids. The platform integrates drug-likeness and permeability neural networks to prioritize candidates for rapid synthesis and testing.
We applied RiDYMO.PepTx to two contrasting targets: thrombin, where 8 of 89 compounds showed greater than 50% inhibition, and β-catenin, where 11 of 29 compounds demonstrated cellular IC₅₀ values below 10 µM. One β-catenin lead was confirmed to disrupt the BCL9 interaction, exhibit passive permeability, and inhibit Wnt signaling.
All hits emerged from a single design-make-test cycle, demonstrating how AI-enhanced, physics-informed design-coupled with parallel synthesis – can accelerate discovery and unlock challenging macrocyclic space.
BIO
Wentao Guo is a technical business development and product manager focused on AI/ML solutions at Atombeat Inc., a next-generation biotech company specializing in AI-driven and physics-based peptide and small molecule design. Wentao is a former postdoctoral researcher at Caltech and holds a Ph.D. in Computational Chemistry and an M.S. in Statistics.
Wentao aims to help translate AI capabilities into impactful scientific and life science applications. Serving as a bridge between technical teams, collaborators, and external partners, she plays a critical role in aligning project goals and model designs with effective execution. With an interdisciplinary background spanning pharmaceutical chemistry, physical chemistry, statistics, and deep learning, Wentao has contributed to the design and coordination of multiple AI models and deployment scenarios—particularly in scientific domains where cross-modality integration and precision modeling are essential.