mlsanityData to 7 Oct 2026

PPFlow: Target-aware Peptide Design with Torsional Flow Matching

arXiv 2405.06642 ↗First posted 5 Mar 2024q-bio.BM cs.AI cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

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 textscPPFlow, 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.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 28 of its 65 references that are in the map. First posted on arXiv 5 Mar 2024.

Builds on

28 of 65 references.

References · 28

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2022Flow Matching for Generative Modelingcited by 5,426
  3. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  4. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
  5. 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Dockingcited by 307
  6. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 248
  7. 2023SE(3) diffusion model with application to protein backbone generationcited by 214
  8. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  9. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 182
  10. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 176
  11. 2021E(n) Equivariant Normalizing Flowscited by 165
  12. 2022A 3D Generative Model for Structure-Based Drug Designcited by 148
16 more
  1. 2023SE(3)-Stochastic Flow Matching for Protein Backbone Generationcited by 147
  2. 2021Self-supervised Learning on Graphs: Contrastive, Generative,or Predictivecited by 136
  3. 2020Normalizing Flows on Tori and Spherescited by 117
  4. 2022Protein structure generation via folding diffusioncited by 113
  5. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  6. 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
  7. 2022DiffBP: Generative Diffusion of 3D Molecules for Target Protein Bindingcited by 58
  8. 2023Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Cloudscited by 53
  9. 2020Generating 3D Molecular Structures Conditional on a Receptor Binding Site with Deep Generative Modelscited by 33
  10. 2023Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaborationcited by 30
  11. 2021Roto-translated Local Coordinate Frames For Interacting Dynamical Systemscited by 24
  12. 2023DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packingcited by 24
  13. 2024MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embeddingcited by 22
  14. 2023Protein 3D Graph Structure Learning for Robust Structure-based Protein Property Predictioncited by 13
  15. 2023A Hierarchical Training Paradigm for Antibody Structure-sequence Co-designcited by 13
  16. 2022A Survey on Protein Representation Learning: Retrospect and Prospectcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 15; 2026: 9.

26 papers.

Sort:

By area:

  1. 2024Fast and Robust Visuomotor Riemannian Flow Matching Policycited by 18
  2. 2025Multi-domain Distribution Learning for De Novo Drug Designcited by 15
  3. 2025Flow Matching Meets Biology and Life Science: A Surveycited by 14
  4. 2025UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Designcited by 11
  5. 2025dyAb: Flow Matching for Flexible Antibody Design with AlphaFold-driven Pre-binding Antigencited by 10
  6. 2024Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extensioncited by 9
  7. 2025An All-Atom Generative Model for Designing Protein Complexescited by 9
  8. 2026Proteo-R1: Reasoning Foundation Models for De Novo Protein Designcited by 6
  9. 2025Zero-Shot Cyclic Peptide Design via Composable Geometric Constraintscited by 4
  10. 2026Surface-based Molecular Design with Multi-modal Flow Matchingcited by 3
  11. 2025Designing Cyclic Peptides via Harmonic SDE with Atom-Bond Modelingcited by 2
  12. 2026Generating Cyclic Conformers with Flow Matching in Cremer-Pople Coordinatescited by 2
14 more
  1. 2025Explicit and Effectively Symmetric Schemes for Neural SDEs on Lie Groupscited by 1
  2. 2025Full-Atom Peptide Design via Riemannian-Euclidean Bayesian Flow Networkscited by 1
  3. 2026APCyc: Property-Informed Design of Cyclic Peptides via Automated Cyclizationcited by 1
  4. 2025THFlow: A Temporally Hierarchical Flow Matching Framework for 3D Peptide Designcited by 0
  5. 2025BindEnergyCraft: Casting Protein Structure Predictors as Energy-Based Models for Binder Designcited by 0
  6. 2025NS-Pep: De novo Peptide Design with Non-Standard Amino Acidscited by 0
  7. 2025Latent Retrieval Augmented Generation of Cross-Domain Protein Binderscited by 0
  8. 2025Joint Design of Protein Surface and Structure Using a Diffusion Bridge Modelcited by 0
  9. 2025Generative design and validation of therapeutic peptides for glioblastoma based on a potential target ATP5Acited by 0
  10. 2026Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Designcited by 0
  11. 2026Riemannian Diffusion Models on General Manifolds via Physics-Informed Neural Networkscited by 0
  12. 2026Pepti-drift: Scalable Safe-Active Peptide Generation Without Inference-Time Guidancecited by 0
  13. 2026TriGlue: a Biology-Inspired Generative Model for Generating Molecular Glue-Induced Ternary Complexcited by 0
  14. 2026FAR-DPO: Feasibility-Aware and Robust Direct Preference Optimization for Cyclic Peptide Designcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Prior-Guided Flow Matching for Target-Aware Molecule Design with Learnable Atom Number
  2. 2024Full-Atom Peptide Design based on Multi-modal Flow Matching
  3. 2024FlowDock: Geometric Flow Matching for Generative Protein-Ligand Docking and Affinity Prediction
  4. 2023Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Design
  5. 2025Peptide2Mol: A Diffusion Model for Generating Small Molecules as Peptide Mimics for Targeted Protein Binding
  6. 2025FLOWR.root: A flow matching based foundation model for joint multi-purpose structure-aware 3D ligand generation and affinity prediction
  7. 2026Navigating Route Latent Space for Synthesizable Molecular Design
  8. 2025Matcha: Multi-Stage Riemannian Flow Matching for Accurate and Physically Valid Molecular Docking