EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

PLNet : Persistent Laplacian neural network for protein–protein binding free energy prediction

Xingjian Xu, Chunmei Wang, Guo-Wei Wei iD, Jiahui Chen iD

Protein Science · 2025-12 · 34 (12)

DOI: 10.1002/pro.70377 ↗

At a glance

Journal article in Protein Science, published online on 2025-11-20. Written by Xingjian Xu and 3 co-authors. Institution: Department of Mathematics, University of Florida, Gainesville, Florida, USA. Major MEDLINE topics: Neural Networks, Computer, Proteins, Protein Interaction Mapping. Cited 3 times so far (Crossref); 73 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Science Foundation, MSU Research Foundation, NIH HHS.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Recent advances in topology‐based modeling have greatly improved molecular prediction tasks, particularly in protein–ligand binding affinity. However, when the focus shifts to predicting protein–protein interactions (PPIs) binding free energy, the question becomes significantly more challenging due to the ineffective use of topological features and the lack of reliable datasets. In this work, we propose a persistent‐Laplacian machine learning framework centered on the Persistent‐Laplacian Neural Network (PLNet), which encodes each protein chain at the binding interface using both persistent Laplacian–based features and protein language model embeddings. It can achieve a promising Pearson correlation of 0.80 under leave‐out‐protein‐out cross‐validation on our newly assembled benchmark dataset, P2P, which includes 6886 protein complexes drawn from existing sources. For comparison, we also implement a gradient‐boosting decision tree model under the same settings. This baseline method highlights the advantage of PLNet in capturing complex topology‐aware descriptors in PPI prediction.

Subjects

MeSH terms (MEDLINE)

Neural Networks, ComputerProteinsProtein Interaction MappingProtein BindingMachine LearningDatabases, ProteinThermodynamics

Author keywords

binding free energydeep learningpersistent homologyprotein‐protein interaction

Substances

Proteins

Authors and institutions

  • Department of Mathematics, University of Florida, Gainesville, Florida, USA.
  • Department of Mathematics, Michigan State University, East Lansing, Michigan, USA.
  • Department of Electrical and Computer Engineering, Michigan State University, East Lansing, Michigan, USA.
  • Department of Biochemistry and Molecular Biology, Michigan State University, East Lansing, Michigan, USA.
  • Department of Mathematical Sciences, University of Arkansas, Fayetteville, Arkansas, USA.

ORCID profiles: Guo-Wei Wei, Jiahui Chen

Funding

  • National Science Foundation
  • MSU Research Foundation
  • NIH HHS
  • NIGMS NIH HHS
  • NIAID NIH HHS
  • Arkansas Biosciences Institute
  • National Institutes of Health

Cite

APA

Xu, X., Wang, C., Wei, G. W., & Chen, J. (2025). PLNet : Persistent Laplacian neural network for protein–protein binding free energy prediction. Protein Science, 34(12). https://doi.org/10.1002/pro.70377

Vancouver

Xu X, Wang C, Wei GW, Chen J. PLNet : Persistent Laplacian neural network for protein–protein binding free energy prediction. Protein Science. 2025;34(12). doi:10.1002/pro.70377

BibTeX
@article{Xu2025,
  author = {Xu, Xingjian and Wang, Chunmei and Wei, Guo-Wei and Chen, Jiahui},
  title = {PLNet : Persistent Laplacian neural network for protein–protein binding free energy prediction},
  journal = {Protein Science},
  year = {2025},
  volume = {34},
  number = {12},
  doi = {10.1002/pro.70377}
}
Start for free →