Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 41 min ago
PreprintCC BYbioRxiv

PeTFlow: Flow-Matching Based All-Atom Peptide Design through Side-Chain State Tokenization

  • Q. Deng
  • M. Xu
  • H. Chen
  • J. Lei1
  1. 1State Key Laboratory of Anti-Infective Drug Discovery and Development, Guangdong Provincial Key Laboratory of Chiral Molecule and Drug Discovery, School of Phar
Read full textPDFDOICite

Abstract

Peptide offers a powerful modality for targeting protein-protein interfaces, yet their computational design remains challenging because sequence identity, backbone geometry and side-chain packing must be optimized simultaneously within a three-dimensional pocket constrained environment. Here we present PeTFlow, a pocket-conditioned all-atom peptide co-design framework that rationalizes this constrained design problem through discrete side-chain state tokenization. In PeTFlow, each residue is represented as a chemically compatible state token, enabling unified modeling of peptide sequence, conformation and all-atom interface geometry. PeTFlow achieved superior generation quality on peptide-design benchmarks and can further be applied to therapeutically relevant peptide drug design.

Related

  1. A genome-wide computational approach for therapeutic targets identification and synthetic peptide assembly enable rational vaccine design against Arcanobacterium haemolyticum
    Khawaja Fawad Parvez, Farwa Najeeb, Muhammad Umer Khan +6
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textMolecular biology & gene regulationCrossref
  2. Computational Design of a TCR-like Human VH Domain Antibody That Specifically Recognizes a WT1-Derived Peptide Presented by Class I Major Histocompatibility Complex
    Tae-Sung Oh, Seong-Woo Kim, SangPhil Ahn +7
    Computational and structural biotechnology journalPeer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMC
  3. Efficient Microwave-Enhanced Solid Phase Peptide Synthesis of Secretin Hormones Amenable for Rapid Library Design and Lead Optimization
    Brenson A. Jassim, Kyle T. Faivre, Severin T. Schneebeli
    ChemRxivPreprintCC BYFull textMolecular biology & gene regulationChemRxiv
  4. RNA Design via Conditioned Flow Matching and Finite-Policy Reinforcement Learning
    Zefeng Lin, Xianyong Fang, Tianfan Fu +1
    arXivPreprintarXiv licenceFull textBiophysicsarXiv
  5. La-Ribo: RNA Co-Design via Geometry-Latent Flow Matching
    Runze Ma, Will Hua, Shuangjia Zheng
    arXivPreprintarXiv licenceFull textBiophysicsarXiv

Cite

BibTeXRIS
BibTeX
@misc{deng2026petflow,
  title = {{PeTFlow: Flow-Matching Based All-Atom Peptide Design through Side-Chain State Tokenization}},
  author = {Q. Deng and M. Xu and H. Chen and J. Lei},
  howpublished = {bioRxiv},
  year = {2026},
  month = oct,
  doi = {10.64898/2026.10.09.757799},
  url = {https://www.biorxiv.org/content/10.64898/2026.10.09.757799v1},
  note = {CC BY},
}
RIS
TY  - UNPB
TI  - PeTFlow: Flow-Matching Based All-Atom Peptide Design through Side-Chain State Tokenization
AU  - Q. Deng
AU  - M. Xu
AU  - H. Chen
AU  - J. Lei
PY  - 2026
DA  - 2026/10/09
PB  - bioRxiv
DO  - 10.64898/2026.10.09.757799
UR  - https://www.biorxiv.org/content/10.64898/2026.10.09.757799v1
AB  - Peptide offers a powerful modality for targeting protein-protein interfaces, yet their computational design remains challenging because sequence identity, backbone geometry and side-chain packing must be optimized simultaneously within a three-dimensional pocket constrained environment. Here we present PeTFlow, a pocket-conditioned all-atom peptide co-design framework that rationalizes this constrained design problem through discrete side-chain state tokenization. In PeTFlow, each residue is represented as a chemically compatible state token, enabling unified modeling of peptide sequence, conformation and all-atom interface geometry. PeTFlow achieved superior generation quality on peptide-design benchmarks and can further be applied to therapeutically relevant peptide drug design.
ER  -