EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ConoGPT: Fine-Tuning a Protein Language Model by Incorporating Disulfide Bond Information for Conotoxin Sequence Generation

Guohui Zhao, Cheng Ge iD, Wenzheng Han, Rilei Yu iD, Hao Liu iD

Toxins · 2025

DOI: 10.3390/toxins17020093 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Toxins, 2025. Verfasst von Guohui Zhao und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Ocean University of China, Songling Road, Qingdao 266100, China. Hauptthemen laut MEDLINE: Conotoxins, Disulfides. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key R&D Program of Shandong Province, China, Key R&D Program of Shandong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conotoxins are a class of peptide toxins secreted by marine mollusks of the Conus genus, characterized by their unique mechanism of action and significant biological activity, making them highly valuable for drug development. However, traditional methods of acquiring conotoxins, such as in vivo extraction or chemical synthesis, face challenges of high costs, long cycles, and limited exploration of sequence diversity. To address these issues, we propose the ConoGPT model, a conotoxin sequence generation model that fine-tunes the ProtGPT2 model by incorporating disulfide bond information. Experimental results demonstrate that sequences generated by ConoGPT exhibit high consistency with authentic conotoxins in physicochemical properties and show considerable potential for generating novel conotoxins. Furthermore, compared to models without disulfide bond information, ConoGPT outperforms in terms of generating sequences with ordered structures. The majority of the filtered sequences were shown to possess significant binding affinities to nicotinic acetylcholine receptor (nAChR) targets based on molecular docking. Molecular dynamics simulations of the selected sequences further confirmed the dynamic stability of the generated sequences in complex with their respective targets. This study not only provides a new technological approach for conotoxin design but also offers a novel strategy for generating functional peptides.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ConotoxinsDisulfidesReceptors, NicotinicAmino Acid SequenceMolecular Dynamics SimulationAnimalsMolecular Docking SimulationConus Snail

Stichwörter der Autor:innen

activity predictionconotoxinspeptide generationprotein language modelreceptors

Substanzen

ConotoxinsDisulfidesReceptors, Nicotinic

Autor:innen und Institutionen

  • College of Computer Science and Technology, Ocean University of China, Songling Road, Qingdao 266100, China.
  • School of Medicine and Pharmacy, Ocean University of China, Songling Road, Qingdao 266100, China.

ORCID-Profile: Cheng Ge, Rilei Yu, Hao Liu

Förderung

  • Key R&D Program of Shandong Province, China
  • Key R&D Program of Shandong Province

Zitieren

APA

Zhao, G., Ge, C., Han, W., Yu, R., & Liu, H. (2025). ConoGPT: Fine-Tuning a Protein Language Model by Incorporating Disulfide Bond Information for Conotoxin Sequence Generation. Toxins. https://doi.org/10.3390/toxins17020093

Vancouver

Zhao G, Ge C, Han W, Yu R, Liu H. ConoGPT: Fine-Tuning a Protein Language Model by Incorporating Disulfide Bond Information for Conotoxin Sequence Generation. Toxins. 2025. doi:10.3390/toxins17020093

BibTeX
@article{Zhao2025,
  author = {Zhao, Guohui and Ge, Cheng and Han, Wenzheng and Yu, Rilei and Liu, Hao},
  title = {ConoGPT: Fine-Tuning a Protein Language Model by Incorporating Disulfide Bond Information for Conotoxin Sequence Generation},
  journal = {Toxins},
  year = {2025},
  doi = {10.3390/toxins17020093}
}
Kostenlos starten →