Machine-learning–guided optimization of cyclic peptide permeability
C2PO is an ML-powered optimizer of the membrane permeability of cyclic peptides through targeted chemical modification. The platform proposes minimal, synthesizable edits designed to improve passive permeability while preserving potency and developability.
Request accessPlatform focus
- Permeability-aware chemical modification strategies
- Multi-objective optimization across ADME-relevant properties
- Constraint-driven design aligned with medicinal chemistry workflows
Technology
C2PO combines generative molecular edits with predictive scoring models trained on permeability-relevant data and physicochemical descriptors. The system emphasizes interpretability, allowing chemists to understand why a proposed modification is expected to improve membrane transport.
Platform capabilities
- Enumeration of chemically plausible peptide modifications
- Ranking by predicted permeability impact and trade-off analysis
- Integration of user-defined constraints and design priorities
Use cases
- Lead optimization for intracellular peptide targets
- Rapid triage of cyclic peptide series
- Design exploration under strict developability constraints
Contact
For collaboration inquiries, platform access, or partnership discussions, please contact:
hello@c2po.bio