EUVIMEDEUVIMED entdecken
Crossref

Multimodal Feature Fusion for Bone Toxicity Prediction and Local Platform

Zhijie Pan, Xin Yang, Churong Wang, Tianming Han, Qi Zhao iD

Journal of Chemical Information and Modeling · 08.12.2025 · 65 (23) · 12799-12810

DOI: 10.1021/acs.jcim.5c02280 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 20.11.2025. Verfasst von Zhijie Pan und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan 114051, China. Hauptthemen laut MEDLINE: Bone and Bones. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: Science and Technology Plan Project of Liaoning Province, Fundamental Research Funds for the Liaoning Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drug-induced osteotoxicity refers to the detrimental effects of certain drugs on bone metabolism, density, and structure, posing serious safety concerns in clinical practice, drug development, and environmental health. Although previous studies have attempted to use machine learning methods to predict osteotoxicity, traditional approaches often struggle to capture the complex relationships between molecular structure and toxicity. To address this issue, we curate a dedicated bone toxicity data set and propose a novel multimodal predictive model, termed BTP-MFFGNN, which integrates molecular fingerprints with graph-based features. By designing a graph neural network specifically tailored to address the complex interactions in osteotoxicity, along with advanced attention mechanisms and adaptive gating fusion strategies, our model can precisely capture the nonlinear relationship between molecular structure and toxicity, revealing the intricate molecular interactions in depth. Experimental results demonstrate that BTP-MFFGNN achieves significant improvements in osteotoxicity prediction, with an ACC of 0.85 and an AUC of 0.92, representing 13 and 8% increases, respectively, compared to the best previous model. To enable practical application, we develop a local platform named OsteoToxPred (refer to the demo at https://pzj-123456.github.io/), which supports SMILES input and delivers rapid, visualized predictions. Our work provides an effective computational framework for bone toxicity assessment and offers valuable support for safer drug discovery and mechanism-driven toxicology research. All of the codes are freely available online at https://github.com/zhaoqi106/BTP-MFFGNN.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bone and BonesHumansNeural Networks, ComputerMachine Learning

Autor:innen und Institutionen

  • School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan 114051, China.
  • School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China.
  • EFREI Engineering School of Digital Technologies, Paris-Panthéon-Assas University, Villejuif 94800, France.

ORCID-Profile: Qi Zhao

Förderung

  • Science and Technology Plan Project of Liaoning Province
  • Fundamental Research Funds for the Liaoning Universities

Zitieren

APA

Pan, Z., Yang, X., Wang, C., Han, T., & Zhao, Q. (2025). Multimodal Feature Fusion for Bone Toxicity Prediction and Local Platform. Journal of Chemical Information and Modeling, 65(23), 12799-12810. https://doi.org/10.1021/acs.jcim.5c02280

Vancouver

Pan Z, Yang X, Wang C, Han T, Zhao Q. Multimodal Feature Fusion for Bone Toxicity Prediction and Local Platform. Journal of Chemical Information and Modeling. 2025;65(23):12799-12810. doi:10.1021/acs.jcim.5c02280

BibTeX
@article{Pan2025,
  author = {Pan, Zhijie and Yang, Xin and Wang, Churong and Han, Tianming and Zhao, Qi},
  title = {Multimodal Feature Fusion for Bone Toxicity Prediction and Local Platform},
  journal = {Journal of Chemical Information and Modeling},
  year = {2025},
  volume = {65},
  number = {23},
  pages = {12799--12810},
  doi = {10.1021/acs.jcim.5c02280}
}
Kostenlos starten →