Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints

Cyclic peptides, characterized by geometric constraints absent in linear peptides, offer enhanced biochemical properties, presenting new opportunities to address unmet medical needs. However, designing target-specific cyclic peptides remains underexplored due to limited training data. To bridge the gap, we propose CP-Composer, a novel generative framework that enables zero-shot cyclic peptide generation via composable geometric constraints. Our approach decomposes complex cyclization patterns into unit constraints, which are incorporated into a diffusion model through geometric conditioning on nodes and edges. During training, the model learns from unit constraints and their random combinations in linear peptides, while at inference, novel constraint combinations required for cyclization are imposed as input. Experiments show that our model, despite trained with linear peptides, is capable of generating diverse target-binding cyclic peptides, reaching success rates from 38\% to 84\% on different cyclization strategies.

How can we generate new target-specific cyclic peptides if we only have limited training data? Our solution is using "composable geometric constraints" to guide generation model to generate new cyclic peptides. It is always a challenging problem to design a data-driven algorithm using limited data as deep learning scientists believe that a good model usually comes from a large amount of training data. To deepen our understanding of generated cyclic peptides, we show some visualizations of simple and high-order cyclic peptides. Furthermore, we release all of our code base on the github. You can also implement your own cyclization strategies in our code.