EUVIMEDEUVIMED entdecken
Crossref

MolADR: Multi-Scale Complementary Learning of Dual-Granularity Molecules and Knowledge Graphs for ADR Prediction in Drug Combinations

Yifan Qi iD, Qingwen Ren, Chenxu Wang, Guihua Chen, Ami Matsumoto, Shitian Guo, Ran Guo, Haochen Xuan, Jingnan Zhang, Wenli Gu, Jiayi Huang, Kai Hang Yiu

Journal of Chemical Information and Modeling · 2026

DOI: 10.1021/acs.jcim.6c01536 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2026. Verfasst von Yifan Qi und 11 weiteren Autor:innen. Beteiligte Einrichtung: The University of Hong Kong-Shenzhen Hospital , Shenzhen, Guangdong518053, China. Hauptthemen laut MEDLINE: Drug-Related Side Effects and Adverse Reactions, Machine Learning. Die Arbeit nennt 42 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Guangdong Province, Sanming Project of Medicine in Shenzen Municipality.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the increasing use of multiple medications in clinical practice, accurate and interpretable prediction of organ-level adverse drug reactions (ADRs) induced by drug combinations is essential for drug safety assessment and precision medicine. Existing knowledge graph (KG)-based methods primarily model biomedical associations but leave direct structure-level interactions within drug pairs undercharacterized, while molecular representation methods often rely on whole-molecule or latent substructure encodings, offering limited chemically meaningful evidence for ADR risks. This study proposes MolADR, a multiscale complementary learning framework that integrates GNN-based KG learning with dual-granularity molecular cross-attention modeling to combine macro-level biomedical associations with microlevel molecular interaction cues. Under an emerging-drug setting, MolADR achieves PR-AUC scores of 81.17 ± 3.97, 84.04 ± 4.67, and 74.37 ± 9.90 on three data sets, consistently outperforming state-of-the-art baselines, with further analyses supporting its robustness and suggesting its ability to highlight chemically plausible atoms and functional groups for organ-level ADR prediction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug-Related Side Effects and Adverse ReactionsMachine LearningDrug CombinationsHumansPrediction Algorithms

Substanzen

Drug Combinations

Autor:innen und Institutionen

  • The University of Hong Kong-Shenzhen Hospital , Shenzhen, Guangdong518053, China.
  • College of Computer Science, Nankai University, Tianjin300350, China.
  • The University of Hong Kong, Pokfulam, Hong Kong, Hong Kong SAR999077, China.

ORCID-Profile: Yifan Qi

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Guangdong Province
  • Sanming Project of Medicine in Shenzen Municipality

Zitieren

APA

Qi, Y., Ren, Q., Wang, C., Chen, G., Matsumoto, A., Guo, S., Guo, R., Xuan, H., Zhang, J., Gu, W., Huang, J., & Yiu, K. H. (2026). MolADR: Multi-Scale Complementary Learning of Dual-Granularity Molecules and Knowledge Graphs for ADR Prediction in Drug Combinations. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c01536

Vancouver

Qi Y, Ren Q, Wang C, Chen G, Matsumoto A, Guo S, et al. MolADR: Multi-Scale Complementary Learning of Dual-Granularity Molecules and Knowledge Graphs for ADR Prediction in Drug Combinations. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.6c01536

BibTeX
@article{Qi2026,
  author = {Qi, Yifan and Ren, Qingwen and Wang, Chenxu and Chen, Guihua and Matsumoto, Ami and Guo, Shitian and Guo, Ran and Xuan, Haochen and Zhang, Jingnan and Gu, Wenli and Huang, Jiayi and Yiu, Kai Hang},
  title = {MolADR: Multi-Scale Complementary Learning of Dual-Granularity Molecules and Knowledge Graphs for ADR Prediction in Drug Combinations},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  doi = {10.1021/acs.jcim.6c01536}
}
Kostenlos starten →