EUVIMEDEUVIMED entdecken
Crossref

MML-DTI: Multimanifold Learning with Hyperbolic Graph Neural Networks for Enhanced Drug–Target Interaction Prediction

Haotian Guan iD, Tian Bai, Chuande Yang, Tao Zhang, Han Wang iD, Guishen Wang iD

Journal of Chemical Information and Modeling · 23.03.2026 · 66 (6) · 3302-3319

DOI: 10.1021/acs.jcim.5c02826 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 09.03.2026. Verfasst von Haotian Guan und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Jilin University, No. 2699 Qianjin Street, Changchun, Jilin 130012, China. Hauptthemen laut MEDLINE: Graph Neural Networks, Drug Interactions. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Jilin Provincial Scientific and Technological Development Program, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurately predicting drug-target interactions (DTIs) is crucial for drug discovery, repositioning. However, most deep learning-based DTI models are designed in Euclidean space, making it difficult to effectively represent the hierarchical and scale-free characteristics of biological data. Due to its unique negatively curved geometric properties, hyperbolic space can more effectively represent hierarchical relationships within data. Therefore, we propose a multimanifold learning framework that integrates multimodal features in hyperbolic and Euclidean spaces for drug-target interaction prediction. Specifically, we employ a Hyperbolic Graph Neural Network (HGNN) to extract features from molecular graphs of small-molecular drugs, thereby effectively capturing the hierarchical structural information within these graphs. To integrate heterogeneous information, a Multi-Manifold Feature Fusion Module combines structural features from the HGNN, chemical fingerprints, and semantic embeddings derived from pretrained language models. Extensive experiments on benchmark data sets demonstrate that our framework achieves superior performance compared with state-of-the-art Euclidean-based methods. The experimental results demonstrate that hyperbolic geometry offers significant advantages in extracting hierarchical features from non-Euclidean data and also highlight the promising potential of multimanifold feature fusion in the field of drug-target interaction prediction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Graph Neural NetworksDrug InteractionsDeep LearningDrug Discovery

Autor:innen und Institutionen

  • College of Computer Science and Technology, Jilin University, No. 2699 Qianjin Street, Changchun, Jilin 130012, China.
  • Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, No. 2699 Qianjin Street, Changchun, Jilin 130012, China.
  • College of Software, Jilin University, No. 2699 Qianjin Street, Changchun, Jilin 130012, China.
  • School of Artificial Intelligence, China Pharmaceutical University, No. 639 Longmian Street, Nanjing, Jiangsu 210009, China.
  • School of Information Science and Technology, Institute of Computational Biology, Northeast Normal University, No. 2555 Jingyue Street, Changchun, Jilin 130117, China.
  • School of Computer Science and Engineering, Changchun University of Technology, No. 2055 Yan'an Street, Changchun, Jilin 130012, China.

ORCID-Profile: Haotian Guan, Han Wang, Guishen Wang

Förderung

  • Jilin Provincial Scientific and Technological Development Program
  • National Natural Science Foundation of China

Zitieren

APA

Guan, H., Bai, T., Yang, C., Zhang, T., Wang, H., & Wang, G. (2026). MML-DTI: Multimanifold Learning with Hyperbolic Graph Neural Networks for Enhanced Drug–Target Interaction Prediction. Journal of Chemical Information and Modeling, 66(6), 3302-3319. https://doi.org/10.1021/acs.jcim.5c02826

Vancouver

Guan H, Bai T, Yang C, Zhang T, Wang H, Wang G. MML-DTI: Multimanifold Learning with Hyperbolic Graph Neural Networks for Enhanced Drug–Target Interaction Prediction. Journal of Chemical Information and Modeling. 2026;66(6):3302-3319. doi:10.1021/acs.jcim.5c02826

BibTeX
@article{Guan2026,
  author = {Guan, Haotian and Bai, Tian and Yang, Chuande and Zhang, Tao and Wang, Han and Wang, Guishen},
  title = {MML-DTI: Multimanifold Learning with Hyperbolic Graph Neural Networks for Enhanced Drug–Target Interaction Prediction},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  volume = {66},
  number = {6},
  pages = {3302--3319},
  doi = {10.1021/acs.jcim.5c02826}
}
Kostenlos starten →