EUVIMEDEUVIMED entdecken
Open Access

Multimodal Bond Reconstruction toward Generative Molecular Design

Jian Wang iD, Nikolay V Dokholyan iD

Journal of Chemical Information and Modeling · 2026

DOI: 10.1021/acs.jcim.5c03052 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2026. Verfasst von Jian Wang und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology and Neuroscience, University of Virginia, School of Medicine, Charlottesville, Virginia 22903, United States. Hauptthemen laut MEDLINE: Drug Design. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS, National Institutes for Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generative models such as diffusion-based approaches have transformed de novo drug design by enabling rapid generation of novel molecular structures in both 2D and 3D formats. However, accurate reconstruction of chemical bonds, especially from distorted geometries produced by generative models, remains a critical challenge. Here, we present YuelBond, a multimodal graph neural network framework for robust bond reconstruction across three key scenarios: (i) recovery of bonds from accurate 3D atomic coordinates, (ii) reconstruction of chemically valid bonds in crude de novo generated compounds (CDGs) with perturbed geometries, and (iii) reassignment of bond orders in 2D topological graphs. YuelBond outperforms traditional rule-based methods such as RDKit, achieving 98.4% F1 score on standard 3D structures and maintaining strong performance (92.7% F1 score) on distorted CDGs, even when RDKit fails in most cases. Our results demonstrate that YuelBond enables accurate and reliable bond reconstruction from imperfect molecular data, bridging a critical gap in generative drug discovery pipelines.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug DesignGraph Neural NetworksGenerative Artificial IntelligenceModels, MolecularMolecular Conformation

Autor:innen und Institutionen

  • Department of Neurology and Neuroscience, University of Virginia, School of Medicine, Charlottesville, Virginia 22903, United States.
  • Department of Biomedical Engineering, University of Virginia, School of Medicine, Charlottesville, Virginia 22903, United States.

ORCID-Profile: Jian Wang, Nikolay V Dokholyan

Förderung

  • NIGMS NIH HHS
  • National Institutes for Health

Zitieren

APA

Wang, J., & Dokholyan, N. V. (2026). Multimodal Bond Reconstruction toward Generative Molecular Design. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.5c03052

Vancouver

Wang J, Dokholyan NV. Multimodal Bond Reconstruction toward Generative Molecular Design. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.5c03052

BibTeX
@article{Wang2026,
  author = {Wang, Jian and Dokholyan, Nikolay V},
  title = {Multimodal Bond Reconstruction toward Generative Molecular Design},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  doi = {10.1021/acs.jcim.5c03052}
}
Kostenlos starten →