Construction of Sonosensitizer-Drug Co-Assembly Based on Deep Learning Method.

Journal: Small (Weinheim an der Bergstrasse, Germany)
Published Date: May 16, 2025

Abstract

Drug co-assemblies have attracted extensive attention due to their advantages of easy preparation, adjustable performance and drug component co-delivery. However, the lack of a clear and reasonable co-assembly strategy has hindered the wide application and promotion of drug-co assembly. This paper introduces a deep learning-based sonosensitizer-drug interaction (SDI) model to predict the particle size of the drug mixture. To analyze the factors influencing the particle size after mixing, the graph neural network is employed to capture the atomic, bond, and structural features of the molecules. A multi-scale cross-attention mechanism is designed to integrate the feature representations of different scale substructures of the two drugs, which not only improves prediction accuracy but also allows for the analysis of the impact of molecular structures on the predictions. Ablation experiments evaluate the impact of molecular properties, and comparisons with other machine and deep learning methods show superiority, achieving 90.00% precision, 96.00% recall, and 91.67% F1-score. Furthermore, the SDI predicts the co-assembly of the chemotherapy drug methotrexate (MET) and the sonosensitizer emodin (EMO) to form the nanomedicine NanoME. This prediction is further validated through experiments, demonstrating that NanoME can be used for fluorescence imaging of liver cancer and sonodynamic/chemotherapy anticancer therapy.

Authors

  • Kanqi Wang
    Institute of Artificial Intelligence, Xiamen University, Xiamen, 361102, China.
  • Liuyin Yang
    State Key Laboratory of Vaccines for Infectious Diseases, Xiang An Biomedicine Laboratory, National Innovation Platform for Industry-Education Integration in Vaccine Research, Fujian Engineering Research Center of Molecular Theranostic Technology, Center for Molecular Imaging and Translational Medicine, School of Public Health, Xiamen University, Xiamen, 361102, China.
  • Xiaowei Lu
    State Key Laboratory of Water Pollution Control and Green Resource Recycling, School of the Environment, Nanjing University, Nanjing 210023, China.
  • Mingtao Cheng
    State Key Laboratory of Vaccines for Infectious Diseases, Xiang An Biomedicine Laboratory, National Innovation Platform for Industry-Education Integration in Vaccine Research, Fujian Engineering Research Center of Molecular Theranostic Technology, Center for Molecular Imaging and Translational Medicine, School of Public Health, Xiamen University, Xiamen, 361102, China.
  • Xiran Gui
    State Key Laboratory of Vaccines for Infectious Diseases, Xiang An Biomedicine Laboratory, National Innovation Platform for Industry-Education Integration in Vaccine Research, Fujian Engineering Research Center of Molecular Theranostic Technology, Center for Molecular Imaging and Translational Medicine, School of Public Health, Xiamen University, Xiamen, 361102, China.
  • Qingmin Chen
    College of Food and Biological Engineering, Jimei University, Xiamen 361021, China.
  • Yilin Wang
    Key Laboratory of Behavioral Science, Institute of Psychology, Chinese Academy of Sciences, Beijing, China.
  • Yang Zhao
    The George Institute for Global Health, Faculty of Medicine, University of New South Wales, Sydney, NSW, Australia.
  • Dong Li
    Department of Cardiovascular Medicine, Lanzhou University Second Hospital, 730030 Lanzhou, Gansu, China.
  • Gang Liu
    Department of Interventional Radiology, Qinghai Red Cross Hospital, Xining, Qinghai, China.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals