GATv2-DDI: Structure Aware Graph Attention Networks for Drug–Drug Interaction Prediction, with a Leakage-Controlled EvaluationProtocol
International Journal of Biomedical Informatics, Health Systems and Integrated Health Sciences · 21.09.2026 · 3 (2) · 1-29
DOI: 10.68715/6engn579 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Biomedical Informatics, Health Systems and Integrated Health Sciences, online erschienen am 21.09.2026. Verfasst von Agatha Omondi und 1 weiteren Autor:innen. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
Purpose of Study: This study develops GATv2-DDI, a structure-aware graph attention framework for drug–drug interaction prediction. It aims to combine molecular descriptors with graph-based representations while systematically evaluating the effects of transductive edge exposure and data leakage. The study also assesses whether graph attention provides meaningful predictive value beyond simpler feature-based learning approaches. Methodology: A corpus of 1,090 approved small-molecule drugs was retrieved from ChEMBL and represented using 4,277-dimensional hybrid molecular descriptors. Structural-similarity proxy labels generated 1,098 balanced drug pairs. GATv2-DDI used a three-layer, eight-head GATv2 encoder with residual connections and an MLP decoder. Performance was evaluated using transductive and leakage-controlled protocols alongside logistic regression, random forest, and feature-only baselines.
Findings
The published GATv2-DDI checkpoint achieved an AUROC of 0.9678 and AUPRC of 0.955 under the transductive evaluation protocol. At the Youden optimal threshold, accuracy, F1, and MCC were 0.923, 0.923, and 0.845, respectively. However, a parameter-free edge-lookup rule achieved an AUROC of 1.0000, demonstrating that validation labels were exposed through message-passing edges. After validation edges were withheld, GATv2-DDI achieved an AUROC of 0.8598, compared with 0.9566 for the feature-only model. Logistic regression achieved 0.9998 AUROC, demonstrating that the similarity-derived labels were essentially linearly separable from molecular features.
Conclusion
GATv2-DDI provides a reproducible framework for graph-based drug-pair scoring and efficient prediction. However, its headline performance is substantially affected by transductive edge exposure and the structure-derived nature of the benchmark labels. Leakage-controlled evaluation and strong non-graph baselines are therefore essential. Clinically curated DDI datasets are needed to establish genuine clinical predictive utility.
Zitieren
APA
Omondi, A., & Gitonga, J. (2026). GATv2-DDI: Structure Aware Graph Attention Networks for Drug–Drug Interaction Prediction, with a Leakage-Controlled EvaluationProtocol. International Journal of Biomedical Informatics, Health Systems and Integrated Health Sciences, 3(2), 1-29. https://doi.org/10.68715/6engn579
Vancouver
Omondi A, Gitonga J. GATv2-DDI: Structure Aware Graph Attention Networks for Drug–Drug Interaction Prediction, with a Leakage-Controlled EvaluationProtocol. International Journal of Biomedical Informatics, Health Systems and Integrated Health Sciences. 2026;3(2):1-29. doi:10.68715/6engn579
BibTeX
@article{Omondi2026,
author = {Omondi, Agatha and Gitonga, Jim},
title = {GATv2-DDI: Structure Aware Graph Attention Networks for Drug–Drug Interaction Prediction, with a Leakage-Controlled EvaluationProtocol},
journal = {International Journal of Biomedical Informatics, Health Systems and Integrated Health Sciences},
year = {2026},
volume = {3},
number = {2},
pages = {1--29},
doi = {10.68715/6engn579}
}
EUVIMED