EUVIMEDEUVIMED entdecken
Crossref

Enhancing protein‐ligand binding affinity prediction through sequential fusion of graph and convolutional neural networks

Yimin Yang, Ruiqin Zhang iD, Zijing Lin iD

Journal of Computational Chemistry · 2024

DOI: 10.1002/jcc.27499 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computational Chemistry, 2024. Verfasst von Yimin Yang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physics, University of Science and Technology of China, Hefei, China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Proteins, Protein Binding. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Natural Science Foundation of China (Grant Nos. 12374017 and 12074362), City University of Hong Kong (Grant No. 9231264), Innovation Program for Quantum Science and Technology (Grant No. 2021ZD0303303).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting protein‐ligand binding affinity is a crucial and challenging task in structure‐based drug discovery. With the accumulation of complex structures and binding affinity data, various machine‐learning scoring functions, particularly those based on deep learning, have been developed for this task, exhibiting superiority over their traditional counterparts. A fusion model sequentially connecting a graph neural network (GNN) and a convolutional neural network (CNN) to predict protein‐ligand binding affinity is proposed in this work. In this model, the intermediate outputs of the GNN layers, as supplementary descriptors of atomic chemical environments at different levels, are concatenated with the input features of CNN. The model demonstrates a noticeable improvement in performance on CASF‐2016 benchmark compared to its constituent CNN models. The generalization ability of the model is evaluated by setting a series of thresholds for ligand extended‐connectivity fingerprint similarity or protein sequence similarity between the training and test sets. Masking experiment reveals that model can capture key interaction regions. Furthermore, the fusion model is applied to a virtual screening task for a novel target, PI5P4Kα. The fusion strategy significantly improves the ability of the constituent CNN model to identify active compounds. This work offers a novel approach to enhancing the accuracy of deep learning models in predicting binding affinity through fusion strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerProteinsProtein BindingLigandsDeep LearningDrug Discovery

Stichwörter der Autor:innen

binding affinityconvolutional neural networksgraph neural networksmachine learningscoring function

Substanzen

LigandsProteins

Autor:innen und Institutionen

  • Department of Physics, University of Science and Technology of China, Hefei, China.
  • Department of Physics, City University of Hong Kong, Hong Kong, China.
  • Hefei National Laboratory, University of Science and Technology of China, Hefei, China.

ORCID-Profile: Ruiqin Zhang, Zijing Lin

Förderung

  • National Natural Science Foundation of China (Grant Nos. 12374017 and 12074362)
  • City University of Hong Kong (Grant No. 9231264)
  • Innovation Program for Quantum Science and Technology (Grant No. 2021ZD0303303)

Zitieren

APA

Yang, Y., Zhang, R., & Lin, Z. (2024). Enhancing protein‐ligand binding affinity prediction through sequential fusion of graph and convolutional neural networks. Journal of Computational Chemistry. https://doi.org/10.1002/jcc.27499

Vancouver

Yang Y, Zhang R, Lin Z. Enhancing protein‐ligand binding affinity prediction through sequential fusion of graph and convolutional neural networks. Journal of Computational Chemistry. 2024. doi:10.1002/jcc.27499

BibTeX
@article{Yang2024,
  author = {Yang, Yimin and Zhang, Ruiqin and Lin, Zijing},
  title = {Enhancing protein‐ligand binding affinity prediction through sequential fusion of graph and convolutional neural networks},
  journal = {Journal of Computational Chemistry},
  year = {2024},
  doi = {10.1002/jcc.27499}
}
Kostenlos starten →