EUVIMEDEUVIMED entdecken
Crossref

LapGAT: A Semi‐Supervised Learning Framework for Drug–Target Interaction Prediction

Lianjun Song iD, Wei Yuan, Xinyu Pei

Molecular Informatics · 2026-04 · 45 (4)

DOI: 10.1002/minf.70028 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Informatics, online erschienen am 21.04.2026. Verfasst von Lianjun Song und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Data Engineering, Tianjin University of Finance and Economics Pearl River College, Tianjin, China. Hauptthemen laut MEDLINE: Drug Discovery, Supervised Machine Learning. Die Arbeit nennt 96 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drug–target interaction (DTI) prediction is a fundamental task in the field of drug discovery, with direct implications for the identification of novel therapeutic candidates and the repositioning of existing drugs. However, the practical application of DTI prediction remains hindered by several persistent challenges, including data scarcity, the absence of reliable negative samples, and limited model generalization across diverse biological contexts. Addressing these limitations is crucial for developing robust and generalizable predictive frameworks. In this study, we present LapGAT, a semi‐supervised framework combining graph‐enhanced Laplacian regularized least squares (LapRLS) with a graph attention network (GAT) to address these issues. In the upstream stage, LapRLS fuses multiple drug–target similarity matrices, applies Laplacian regularization, and selects top‐ and bottom‐scoring pairs as high‐confidence positive and negative samples. In the downstream stage, a multilayer GAT learns from these pseudo‐labeled interactions, capturing both local graph structures and nonlinear dependencies. We validate LapGAT on four target categories (enzymes, G‐protein‐coupled receptors (GPCRs), ion channels, nuclear receptors), demonstrating robust performance in computational and experimental validation. Molecular docking (AutoDock Vina) confirms the physical plausibility of top‐ranked predictions, with binding affinities ranging from −4.5 to −7.3 kcal/mol. Literature‐based validation achieves accuracies of 81.3% (enzymes), 100% (GPCRs), 71.4% (ion channels), and 88.9% (nuclear receptors). This work offers a scalable and flexible computational tool for accelerating drug discovery efforts, with the potential for broad applicability across various therapeutic domains.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug DiscoverySupervised Machine LearningHumansReceptors, G-Protein-CoupledGraph Neural NetworksReceptors, Cytoplasmic and NuclearLeast-Squares AnalysisIon Channels

Stichwörter der Autor:innen

Laplacian regularized least squaresdrug–target interaction predictiongraph attention networkmolecular docking and literature‐based validationsemi‐supervised learning

Substanzen

Receptors, G-Protein-CoupledReceptors, Cytoplasmic and NuclearIon Channels

Autor:innen und Institutionen

  • Department of Data Engineering, Tianjin University of Finance and Economics Pearl River College, Tianjin, China.
  • College of Computer and Information Engineering, Tianjin Agricultural University, Tianjin, China.

ORCID-Profile: Lianjun Song

Zitieren

APA

Song, L., Yuan, W., & Pei, X. (2026). LapGAT: A Semi‐Supervised Learning Framework for Drug–Target Interaction Prediction. Molecular Informatics, 45(4). https://doi.org/10.1002/minf.70028

Vancouver

Song L, Yuan W, Pei X. LapGAT: A Semi‐Supervised Learning Framework for Drug–Target Interaction Prediction. Molecular Informatics. 2026;45(4). doi:10.1002/minf.70028

BibTeX
@article{Song2026,
  author = {Song, Lianjun and Yuan, Wei and Pei, Xinyu},
  title = {LapGAT: A Semi‐Supervised Learning Framework for Drug–Target Interaction Prediction},
  journal = {Molecular Informatics},
  year = {2026},
  volume = {45},
  number = {4},
  doi = {10.1002/minf.70028}
}
Kostenlos starten →