PPFlow: Target-aware Peptide Design with Torsional Flow Matching

2024/03/05 by Haitao Lin, Lin, Haitao, Odin Zhang +13 · 14 citations
Biochemistry, Genetics and Molecular Biology · Chemistry · #Advanced Proteomics Techniques and Applications #Artificial Intelligence (cs.AI) #Biomolecules (q-bio.BM) #Chemical Synthesis and Analysis #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Bioinformatics

paper · pdf · doi:10.48550/arxiv.2405.06642

openalex publication_date 2024/03/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• Generative design and validation of therapeutic peptides for glioblastoma based on a potential target ATP5A
• Full-Atom Peptide Design via Riemannian-Euclidean Bayesian Flow Networks
• Joint Design of Protein Surface and Structure Using a Diffusion Bridge Model
• Latent Retrieval Augmented Generation of Cross-Domain Protein Binders
• NS-Pep: De novo Peptide Design with Non-Standard Amino Acids
• Explicit and Effectively Symmetric Schemes for Neural SDEs on Lie Groups
• Multi-domain Distribution Learning for De Novo Drug Design
• Preference Trajectory Modeling via Flow Matching for Sequential Recommendation
• Flow Matching Meets Biology and Life Science: A Survey
• Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints
• Designing Cyclic Peptides via Harmonic SDE with Atom-Bond Modeling
• BindEnergyCraft: Casting Protein Structure Predictors as Energy-Based Models for Binder Design
• Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design
• An All-Atom Generative Model for Designing Protein Complexes

Related

• THFlow: A Temporally Hierarchical Flow Matching Framework for 3D Peptide Design
• D-Flow: Multi-modality Flow Matching for D-peptide Design
• ApexGen: Simultaneous design of peptide binder sequence and structure for target proteins
• Full-Atom Peptide Design based on Multi-modal Flow Matching
• Target specific peptide design using latent space approximate trajectory collector