EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dynamics-enhanced molecular property prediction guided by deep learning

Qiang Liu iD, Debby Dan Wang iD, Weiqing Guo, Yuting Huang, Xizhao Wang

PLOS Computational Biology · 16.07.2026 · 22 (7) · e1014515

DOI: 10.1371/journal.pcbi.1014515 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 16.07.2026. Verfasst von Qiang Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China. Hauptthemen laut MEDLINE: Deep Learning, Molecular Dynamics Simulation, Computational Biology. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hong Kong Metropolitan University, Hong Kong Research Grants Council, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Molecular property prediction (MPP) is a key challenge in computational biology and drug discovery. Traditional approaches mostly rely on feature representations yielded from static structures of molecules, ignoring their dynamic nature. The scarcity of dynamics data in public databases and the complexity of learning such high-dimensional data made it more difficult for dynamics-involved studies. Accordingly, we built a series of dynamics datasets for MPP tasks by performing comprehensive molecular dynamics (MD) simulations on different molecules. In addition, we proposed a dynamically enhanced molecular representation (DEMR) method with multiple sampling strategies for the dynamics frames. Besides, two deep learning pipelines were employed for mapping DEMR to the molecular properties in various tasks. Our models achieved better performance in different MPP tasks, with practical guidance in efficient frame selection. This study highlights the significance of integrating MD data into MPP tasks and opens new avenues for structure-based drug design. The generated MD datasets are publicly available in a Zenodo repository at https://doi.org/10.5281/zenodo.15788151 , and the code is available in a GitHub repository at https://github.com/liuqiang-blib/MPP-using-DEMR.git .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMolecular Dynamics SimulationComputational BiologyDrug Discovery

Autor:innen und Institutionen

  • College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China.
  • School of Science and Technology, Hong Kong Metropolitan University, Ho Man Tin, Kowloon, Hong Kong.
  • The Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen, Guangdong, China.

ORCID-Profile: Qiang Liu, Debby Dan Wang

Förderung

  • Hong Kong Metropolitan University
  • Hong Kong Research Grants Council
  • National Natural Science Foundation of China

Zitieren

APA

Liu, Q., Wang, D. D., Guo, W., Huang, Y., & Wang, X. (2026). Dynamics-enhanced molecular property prediction guided by deep learning. PLOS Computational Biology, 22(7), e1014515. https://doi.org/10.1371/journal.pcbi.1014515

Vancouver

Liu Q, Wang DD, Guo W, Huang Y, Wang X. Dynamics-enhanced molecular property prediction guided by deep learning. PLOS Computational Biology. 2026;22(7):e1014515. doi:10.1371/journal.pcbi.1014515

BibTeX
@article{Liu2026,
  author = {Liu, Qiang and Wang, Debby Dan and Guo, Weiqing and Huang, Yuting and Wang, Xizhao},
  title = {Dynamics-enhanced molecular property prediction guided by deep learning},
  journal = {PLOS Computational Biology},
  year = {2026},
  volume = {22},
  number = {7},
  pages = {e1014515},
  doi = {10.1371/journal.pcbi.1014515}
}
Kostenlos starten →