EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Informative relational learning for adverse reaction prediction with enhanced generalization to novel drugs

Shuge Sun iD, Dalin Zhang, Hongjun Chu, Xinyi Gong

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag494 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Shuge Sun und 3 weiteren Autor:innen. Beteiligte Einrichtung: Space Information Research Institute, Hangzhou Dianzi University, Baiyang, Hangzhou, Zhejiang 310018, China. Hauptthemen laut MEDLINE: Drug-Related Side Effects and Adverse Reactions, Machine Learning, Computational Biology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Leading Innovative and Entrepreneurial Team Program of Zhejiang.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Accurate prediction of adverse drug reactions (ADRs) is essential for drug safety surveillance, and recent advances in machine learning with heterogeneous biomedical information have improved predictive performance. However, two challenges remain: current methods often learn inadequate ADR representations that fail to capture dependencies among ADRs, and generalize poorly to novel drugs. Results To obtain informative ADR embeddings, we construct a multi-source, multi-relational ADR graph that integrates hierarchical structure and empirical ADR co-occurrence, and apply a relational graph convolutional network (R-GCN) to learn relation-aware ADR representations. To enhance generalization to novel drugs, we exploit the hierarchical structure of the Anatomical Therapeutic Chemical (ATC) classification to link drugs via shared higher-level categories for effective knowledge transfer and model these relations with an R-GCN. We further introduce a Conditional Domain Adversarial Network (CDAN) to reduce distribution shifts between known and novel drugs by aligning features conditioned on predicted ADR labels, learning domain-invariant yet task-relevant representations. Additionally, to exploit similar ADR patterns among related drugs, we introduce a dual-branch mixture-of-experts (Dual-MoE) module where each expert captures ADR commonalities within a drug category in one branch, while a separate branch models global patterns. Extensive experiments show that our method consistently outperforms seven baselines, achieving F1 improvements of 4.3% and 4.7% over the best baseline on two datasets, respectively, with more balanced precision–recall trade-offs. It also improves AUC on uncommon ADRs by 7% more than on common ADRs, and remains more robust under data sparsity, with more gradual performance degradation as training data decreases. Availability and implementation The code of our model is available at https://github.com/fzsdb/Knowledge-guided-ADR-prediction.git.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug-Related Side Effects and Adverse ReactionsMachine LearningComputational BiologyGraph Neural NetworksHumansPrediction AlgorithmsAlgorithms

Autor:innen und Institutionen

  • Space Information Research Institute, Hangzhou Dianzi University, Baiyang, Hangzhou, Zhejiang 310018, China.

ORCID-Profile: Shuge Sun

Förderung

  • Leading Innovative and Entrepreneurial Team Program of Zhejiang

Zitieren

APA

Sun, S., Zhang, D., Chu, H., & Gong, X. (2026). Informative relational learning for adverse reaction prediction with enhanced generalization to novel drugs. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag494

Vancouver

Sun S, Zhang D, Chu H, Gong X. Informative relational learning for adverse reaction prediction with enhanced generalization to novel drugs. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag494

BibTeX
@article{Sun2026,
  author = {Sun, Shuge and Zhang, Dalin and Chu, Hongjun and Gong, Xinyi},
  title = {Informative relational learning for adverse reaction prediction with enhanced generalization to novel drugs},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag494}
}
Kostenlos starten →