EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MSER-DDI: molecular and semantic event representations for few-shot and unseen-event drug–drug interaction prediction

Wen Li, Yanxiu Fu, Xiangqiong Wu, Wei Zhang, Qiang Xie, Peng Wang

Frontiers in Chemistry · 06.11.2026 · 14

DOI: 10.3389/fchem.2026.2004356 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Chemistry, online erschienen am 06.11.2026. Verfasst von Wen Li und 5 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hunan Province, Education Department of Hunan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Sparse event annotations limit drug-drug interaction (DDI) prediction, particularly for rare events and event categories absent from training data.

Methods

We propose MSER-DDI, a framework with two independently trained pathways that represent target events using labeled drug pairs or textual descriptions. The sample-driven pathway, PharDDIE, combines molecular structure and biological context with reconstruction-regularized latent encoding to construct event prototypes from a few labeled pairs. The semantics-driven pathway, EviDDIE, maps event descriptions into the drug-pair representation space and uses evidential inference without labeled target-event examples.

Results

In 1-shot rare-event prediction, PharDDIE achieved higher mean area under the receiver operating characteristic curve (AUROC), accuracy, and event-macro F1 than retrained RareDDIE across five matched training seeds. These means also exceeded the published baseline estimates. Under the respective evaluation conditions, 5-shot predictions had lower Brier score, negative log-likelihood, and calibration error than 1-shot predictions, together with lower high-confidence error rates and broader coverage across all three event-frequency groups. EviDDIE predicted interactions for event categories excluded from molecular training. Literature-based assessment identified drug- or class-level pharmacological consistency for a subset of selected positive benchmark examples.

Discussion

MSER-DDI supports event-level prediction when target-event annotations are scarce or unavailable, while joint evaluation of discrimination and probability quality characterizes predictive performance and confidence. The resulting predictions provide interaction hypotheses for further pharmacological investigation.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Hunan Province
  • Education Department of Hunan Province

Zitieren

APA

Li, W., Fu, Y., Wu, X., Zhang, W., Xie, Q., & Wang, P. (2026). MSER-DDI: molecular and semantic event representations for few-shot and unseen-event drug–drug interaction prediction. Frontiers in Chemistry, 14. https://doi.org/10.3389/fchem.2026.2004356

Vancouver

Li W, Fu Y, Wu X, Zhang W, Xie Q, Wang P. MSER-DDI: molecular and semantic event representations for few-shot and unseen-event drug–drug interaction prediction. Frontiers in Chemistry. 2026;14. doi:10.3389/fchem.2026.2004356

BibTeX
@article{Li2026,
  author = {Li, Wen and Fu, Yanxiu and Wu, Xiangqiong and Zhang, Wei and Xie, Qiang and Wang, Peng},
  title = {MSER-DDI: molecular and semantic event representations for few-shot and unseen-event drug–drug interaction prediction},
  journal = {Frontiers in Chemistry},
  year = {2026},
  volume = {14},
  doi = {10.3389/fchem.2026.2004356}
}
Kostenlos starten →