EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Persistent Local Laplacian Prediction of Protein–Ligand Binding Affinities

Jian Liu, Hongsong Feng iD

Journal of Chemical Information and Modeling · 2026

DOI: 10.1021/acs.jcim.6c02460 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2026. Verfasst von Jian Liu und 1 weiteren Autor:innen. Beteiligte Einrichtung: Mathematical Science Research Center, Chongqing University of Technology, Chongqing400054, P. R. China. Hauptthemen laut MEDLINE: Proteins. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of North Carolina at Charlotte, Chongqing University of Technology, National Natural Science Foundation of China (NSFC).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of protein–ligand binding affinity remains a central challenge in structure-based drug discovery. The effectiveness of machine learning models critically depends on the quality of molecular representations, for which advanced mathematical frameworks provide powerful tools. In this work, we employ a novel mathematical theory, termed the persistent local Laplacian (PLL), to construct molecular descriptors that capture localized geometric and topological features of biomolecular structures. The PLL framework addresses key limitations of traditional topological data analysis methods, such as persistent homology and the persistent Laplacian, which are often insensitive to local structural variations, while maintaining high computational efficiency. The resulting molecular descriptors are integrated with advanced machine learning algorithms to develop accurate predictive models for protein–ligand binding affinity. The proposed models are systematically evaluated on three well-established benchmark datasets, including PDBbind-v2007, PDBbind-v2013, and PDBbind-v2016, demonstrating consistently strong and competitive predictive performance. Computational results show that the PLL-based models outperform existing approaches, highlighting their potential as a powerful tool for drug discovery, protein engineering, and broader applications in science and engineering.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsLigandsProtein BindingMachine LearningDrug DiscoveryPrediction AlgorithmsModels, MolecularPredictive Learning Models

Substanzen

LigandsProteins

Autor:innen und Institutionen

  • Mathematical Science Research Center, Chongqing University of Technology, Chongqing400054, P. R. China.
  • Department of Mathematics and Statistics, University of North Carolina at Charlotte, Charlotte, North Carolina28223, United States.

ORCID-Profile: Hongsong Feng

Förderung

  • University of North Carolina at Charlotte
  • Chongqing University of Technology
  • National Natural Science Foundation of China (NSFC)

Zitieren

APA

Liu, J., & Feng, H. (2026). Persistent Local Laplacian Prediction of Protein–Ligand Binding Affinities. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c02460

Vancouver

Liu J, Feng H. Persistent Local Laplacian Prediction of Protein–Ligand Binding Affinities. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.6c02460

BibTeX
@article{Liu2026,
  author = {Liu, Jian and Feng, Hongsong},
  title = {Persistent Local Laplacian Prediction of Protein–Ligand Binding Affinities},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  doi = {10.1021/acs.jcim.6c02460}
}
Kostenlos starten →