EUVIMEDEUVIMED entdecken
Crossref

An Attention‐Driven Graph Transformer With Nonlinear Modeling and Neuro‐Fuzzy Fusion for High‐Order Toxic Molecular Graph Learning

Phu Pham iD

Molecular Informatics · 2026-05 · 45 (5)

DOI: 10.1002/minf.70037 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Informatics, online erschienen am 09.05.2026. Verfasst von Phu Pham. Beteiligte Einrichtung: Faculty of Information Technology, HUTECH University, Ho Chi Minh City, Vietnam. Hauptthemen laut MEDLINE: Fuzzy Logic, Nonlinear Dynamics, Neural Networks, Computer. Die Arbeit nennt 25 Literaturangaben. Gefördert von: HUTECH University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Learning expressive representations for complex, size‐varied molecular graphs remains a fundamental challenge in toxic molecular property prediction and regression. The inherent nonlinearity of atomic interactions, together with intricate structural dependencies and latent high‐order structural characteristics, makes accurate graph‐based learning particularly difficult. Although recent deep learning (DL)/graph neural network (GNN) approaches have leveraged message passing, attention mechanisms, and graph transformer architectures, these techniques still suffer from limited nonlinear expressiveness, insufficient modeling of high‐order structural information, and a lack of explicit uncertainty handling. To address these limitations, we propose a novel AKAGTL model, which is an attention‐driven Kolmogorov–Arnold network (KAN)‐based graph transformer framework for toxic molecular graph embedding and regression learning. Unlike existing approaches that rely on linear or shallow nonlinear transformations, our proposed AKAGTL model introduces a structured KAN‐based functional transformation to explicitly model complex high‐order atomic interactions within an attention‐driven graph transformer backbone. In addition, high‐order structural representations are systematically incorporated to complement structural encoding, while a Gaussian neuro‐fuzzy fusion mechanism enables uncertainty‐aware aggregation of heterogeneous feature spaces. The proposed framework is evaluated on multiple molecular toxicity benchmarks under a unified experimental protocol with repeated runs. Comprehensive experiments within benchmark molecular graph datasets demonstrate that our AKAGTL model can consistently improve regression accuracy compared to representative GNN and graph transformer baselines. These findings suggest that jointly modeling nonlinear functional interactions, structural dependencies, and uncertainty‐aware fusion provides a more expressive and robust solution for toxic molecular graph embedding and regression learning.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Fuzzy LogicNonlinear DynamicsNeural Networks, ComputerGraph Neural NetworksDeep Learning

Stichwörter der Autor:innen

Kolmogorov–Arnold network (KAN)graph neural network (GNN)graph regressiongraph transformerhigh‐order interactiontoxic molecule

Autor:innen und Institutionen

  • Faculty of Information Technology, HUTECH University, Ho Chi Minh City, Vietnam.

ORCID-Profile: Phu Pham

Förderung

  • HUTECH University

Zitieren

APA

Pham, P. (2026). An Attention‐Driven Graph Transformer With Nonlinear Modeling and Neuro‐Fuzzy Fusion for High‐Order Toxic Molecular Graph Learning. Molecular Informatics, 45(5). https://doi.org/10.1002/minf.70037

Vancouver

Pham P. An Attention‐Driven Graph Transformer With Nonlinear Modeling and Neuro‐Fuzzy Fusion for High‐Order Toxic Molecular Graph Learning. Molecular Informatics. 2026;45(5). doi:10.1002/minf.70037

BibTeX
@article{Pham2026,
  author = {Pham, Phu},
  title = {An Attention‐Driven Graph Transformer With Nonlinear Modeling and Neuro‐Fuzzy Fusion for High‐Order Toxic Molecular Graph Learning},
  journal = {Molecular Informatics},
  year = {2026},
  volume = {45},
  number = {5},
  doi = {10.1002/minf.70037}
}
Kostenlos starten →