PPFLOW: Target-Aware Peptide Design with Torsional Flow Matching

Haitao Lin, Odin Zhang, Huifeng Zhao, Dejun Jiang, Lirong Wu, Zicheng Liu, Yufei Huang, Stan Z. Li
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30510-30528, 2024.

Abstract

Therapeutic peptides have proven to have great pharmaceutical value and potential in recent decades. However, methods of AI-assisted peptide drug discovery are not fully explored. To fill the gap, we propose a target-aware peptide design method called PPFlow, based on conditional flow matching on torus manifolds, to model the internal geometries of torsion angles for the peptide structure design. Besides, we establish a protein-peptide binding dataset named PPBench2024 to fill the void of massive data for the task of structure-based peptide drug design and to allow the training of deep learning methods. Extensive experiments show that PPFlow reaches state-of-the-art performance in tasks of peptide drug generation and optimization in comparison with baseline models, and can be generalized to other tasks including docking and side-chain packing.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-lin24z, title = {{PPFLOW}: Target-Aware Peptide Design with Torsional Flow Matching}, author = {Lin, Haitao and Zhang, Odin and Zhao, Huifeng and Jiang, Dejun and Wu, Lirong and Liu, Zicheng and Huang, Yufei and Li, Stan Z.}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {30510--30528}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/lin24z/lin24z.pdf}, url = {https://proceedings.mlr.press/v235/lin24z.html}, abstract = {Therapeutic peptides have proven to have great pharmaceutical value and potential in recent decades. However, methods of AI-assisted peptide drug discovery are not fully explored. To fill the gap, we propose a target-aware peptide design method called PPFlow, based on conditional flow matching on torus manifolds, to model the internal geometries of torsion angles for the peptide structure design. Besides, we establish a protein-peptide binding dataset named PPBench2024 to fill the void of massive data for the task of structure-based peptide drug design and to allow the training of deep learning methods. Extensive experiments show that PPFlow reaches state-of-the-art performance in tasks of peptide drug generation and optimization in comparison with baseline models, and can be generalized to other tasks including docking and side-chain packing.} }
Endnote
%0 Conference Paper %T PPFLOW: Target-Aware Peptide Design with Torsional Flow Matching %A Haitao Lin %A Odin Zhang %A Huifeng Zhao %A Dejun Jiang %A Lirong Wu %A Zicheng Liu %A Yufei Huang %A Stan Z. Li %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-lin24z %I PMLR %P 30510--30528 %U https://proceedings.mlr.press/v235/lin24z.html %V 235 %X Therapeutic peptides have proven to have great pharmaceutical value and potential in recent decades. However, methods of AI-assisted peptide drug discovery are not fully explored. To fill the gap, we propose a target-aware peptide design method called PPFlow, based on conditional flow matching on torus manifolds, to model the internal geometries of torsion angles for the peptide structure design. Besides, we establish a protein-peptide binding dataset named PPBench2024 to fill the void of massive data for the task of structure-based peptide drug design and to allow the training of deep learning methods. Extensive experiments show that PPFlow reaches state-of-the-art performance in tasks of peptide drug generation and optimization in comparison with baseline models, and can be generalized to other tasks including docking and side-chain packing.
APA
Lin, H., Zhang, O., Zhao, H., Jiang, D., Wu, L., Liu, Z., Huang, Y. & Li, S.Z.. (2024). PPFLOW: Target-Aware Peptide Design with Torsional Flow Matching. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:30510-30528 Available from https://proceedings.mlr.press/v235/lin24z.html.

Related Material