De Novo Design of Large Polypeptides Using a Lightweight Diffusion Model Integrating LSTM and Attention Mechanism Under Per-Residue Secondary Structure Constraints
Molecules · 2025
DOI: 10.3390/molecules30051116 ↗Kurz gefasst
Fachartikel in der Zeitschrift Molecules, 2025. Verfasst von Sisheng Liao und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Life Sciences, Fudan University, Shanghai 200433, China. Hauptthemen laut MEDLINE: Peptides. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Innovation Plan of Shanghai Science and Technology Commission, Research Fund for International Senior Scientists, National Natural Science Foundation of China.
Abstract (Originalsprache)
This study presents PolypeptideDesigner (PPD), a novel conditional diffusion-based model for de novo polypeptide sequence design and generation based on per-residue secondary structure conditions. By integrating a lightweight LSTM-attention neural network as the denoiser within a diffusion framework, PPD offers an innovative and efficient approach to polypeptide generation. Evaluations demonstrate that the PPD model can generate diverse and novel polypeptide sequences across various testing conditions, achieving high pLDDT scores when folded by ESMFold. In comparison to the ProteinDiffusionGenerator B (PDG-B) model, a relevant benchmark in the field, PPD exhibits the ability to produce longer and more diverse polypeptide sequences. This improvement is attributed to PPD’s optimized architecture and expanded training dataset, which enhance its understanding of protein structural pattern. The PPD model shows significant potential for optimizing functional polypeptides with known structures, paving the way for advancements in biomaterial design. Future work will focus on further refining the model and exploring its broader applications in polypeptide engineering.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Life Sciences, Fudan University, Shanghai 200433, China.
- Multiscale Research Institute of Complex Systems, Fudan University, Shanghai 200433, China.
- Zhangjiang Fudan International Innovation Center, Fudan University, Shanghai 200433, China.
- Shanghai AI Laboratory, Shanghai 200233, China.
- State Key Laboratory of Genetic Engineering, Human Phenome Institute, Center for Evolutionary Biology, and Collaborative Innovation Center for Genetics and Development, Fudan University, Shanghai 200433, China.
- Research Unit of Dissecting Population Genetics and Developing New Technologies for Treatment and Prevention of Skin Phenotypes and Dermatological Diseases (2019RU058), Chinese Academy of Medical Sciences, Beijing 10073…
ORCID-Profile: Sisheng Liao
Förderung
- Science and Technology Innovation Plan of Shanghai Science and Technology Commission
- Research Fund for International Senior Scientists
- National Natural Science Foundation of China
- National Key Research and Development Program of China
Zitieren
APA
Liao, S., Xu, G., Jin, L., & Ma, J. (2025). De Novo Design of Large Polypeptides Using a Lightweight Diffusion Model Integrating LSTM and Attention Mechanism Under Per-Residue Secondary Structure Constraints. Molecules. https://doi.org/10.3390/molecules30051116
Vancouver
Liao S, Xu G, Jin L, Ma J. De Novo Design of Large Polypeptides Using a Lightweight Diffusion Model Integrating LSTM and Attention Mechanism Under Per-Residue Secondary Structure Constraints. Molecules. 2025. doi:10.3390/molecules30051116
BibTeX
@article{Liao2025,
author = {Liao, Sisheng and Xu, Gang and Jin, Li and Ma, Jianpeng},
title = {De Novo Design of Large Polypeptides Using a Lightweight Diffusion Model Integrating LSTM and Attention Mechanism Under Per-Residue Secondary Structure Constraints},
journal = {Molecules},
year = {2025},
doi = {10.3390/molecules30051116}
}
EUVIMED