EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DEKP: a deep learning model for enzyme kinetic parameter prediction based on pretrained models and graph neural networks

Yizhen Wang iD, Li Cheng, Yanyun Zhang, Yujia Cao, Daniyal Alghazzawi

Briefings in Bioinformatics · 04.03.2025 · 26 (2)

DOI: 10.1093/bib/bbaf187 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 24.04.2025. Verfasst von Yizhen Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Hubei University, No. 368 Youyi Road, 430062 Wuhan, China. Hauptthemen laut MEDLINE: Deep Learning, Neural Networks, Computer, Enzymes. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Technology Research and Development Program of China, Major Science and Technology Project of Hubei Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The prediction of enzyme kinetic parameters is crucial for screening enzymes with high catalytic efficiency and desired characteristics to catalyze natural or non-natural reactions. Data-driven machine learning models have been explored to reduce experimental cost and speed up the enzyme design process. However, the prediction performance is still subject to significant limitations due to the variance in sequence similarity between training and testing datasets. In this work, we introduce DEKP, an integrated deep learning approach enzyme kinetic parameter prediction. It leverages pretrained models of protein sequences and incorporates enhanced graph neural networks that provide comprehensive representation of protein structural features. This novel approach can effectively alleviate the performance degradation caused by sequence similarity variation. Moreover, it provides sensitive detection of changes in catalytic efficiency due to enzyme mutations. Experiments validate that DEKP outperforms existing models in predicting enzyme kinetic parameters. This work is expected to significantly improve the performance of the enzyme screening process and provide a robust tool for enzyme-directed evolution research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningNeural Networks, ComputerEnzymesKineticsGraph Neural Networks

Stichwörter der Autor:innen

deep learningenzyme kinetic parametersgraph neural networkpretrained model

Substanzen

Enzymes

Autor:innen und Institutionen

  • School of Computer Science, Hubei University, No. 368 Youyi Road, 430062 Wuhan, China.
  • Key Laboratory of Intelligent Sensing System and Security, Hubei University, Ministry of Education, No. 368 Youyi Road, 430062 Wuhan, China.
  • Hubei Key Laboratory of Big Data Intelligent Analysis and Application, Hubei University, No. 368 Youyi Road, 430062 Wuhan, China.
  • Faculty of Computing and Information Technology (FCIT), 3599 King Abdulaziz University (KAU), Unit 3600, Jeddah 22254-7653, Saudi Arabia.

ORCID-Profile: Yizhen Wang

Förderung

  • National Key Technology Research and Development Program of China
  • Major Science and Technology Project of Hubei Province

Zitieren

APA

Wang, Y., Cheng, L., Zhang, Y., Cao, Y., & Alghazzawi, D. (2025). DEKP: a deep learning model for enzyme kinetic parameter prediction based on pretrained models and graph neural networks. Briefings in Bioinformatics, 26(2). https://doi.org/10.1093/bib/bbaf187

Vancouver

Wang Y, Cheng L, Zhang Y, Cao Y, Alghazzawi D. DEKP: a deep learning model for enzyme kinetic parameter prediction based on pretrained models and graph neural networks. Briefings in Bioinformatics. 2025;26(2). doi:10.1093/bib/bbaf187

BibTeX
@article{Wang2025,
  author = {Wang, Yizhen and Cheng, Li and Zhang, Yanyun and Cao, Yujia and Alghazzawi, Daniyal},
  title = {DEKP: a deep learning model for enzyme kinetic parameter prediction based on pretrained models and graph neural networks},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  volume = {26},
  number = {2},
  doi = {10.1093/bib/bbaf187}
}
Kostenlos starten →