Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints

Dapeng Jiang, Xiangzhe Kong, Jiaqi Han, Mingyu Li, Rui Jiao, Wenbing Huang, Stefano Ermon, Jianzhu Ma, Yang Liu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27553-27568, 2025.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-jiang25d, title = {Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints}, author = {Jiang, Dapeng and Kong, Xiangzhe and Han, Jiaqi and Li, Mingyu and Jiao, Rui and Huang, Wenbing and Ermon, Stefano and Ma, Jianzhu and Liu, Yang}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {27553--27568}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/jiang25d/jiang25d.pdf}, url = {https://proceedings.mlr.press/v267/jiang25d.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints %A Dapeng Jiang %A Xiangzhe Kong %A Jiaqi Han %A Mingyu Li %A Rui Jiao %A Wenbing Huang %A Stefano Ermon %A Jianzhu Ma %A Yang Liu %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-jiang25d %I PMLR %P 27553--27568 %U https://proceedings.mlr.press/v267/jiang25d.html %V 267 %X 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.
APA
Jiang, D., Kong, X., Han, J., Li, M., Jiao, R., Huang, W., Ermon, S., Ma, J. & Liu, Y.. (2025). Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:27553-27568 Available from https://proceedings.mlr.press/v267/jiang25d.html.

Related Material