Relation-aware multimodal knowledge graph learning for drug–drug interaction prediction
- 1College of Computer and Information Engineering, Xinjiang Agricultural University
Abstract
Drug–drug interactions (DDIs) can alter therapeutic efficacy and lead to adverse events, making accurate DDI prediction important for drug safety assessment. Existing computational methods often rely on limited drug features or do not sufficiently capture heterogeneous biomedical relations surrounding drugs. We present RA-DDI, a relation-aware knowledge graph framework for DDI prediction. RA-DDI constructs a drug-centered knowledge graph (KG) from DrugBank and initializes drug representations by integrating molecular structures, textual descriptions, and graph-derived relational features. These multimodal representations are then refined through relation-aware graph learning to capture multi-hop dependencies among drugs and related biomedical entities. A prediction module combines the learned drug embeddings with pairwise interaction features to classify DDI types. We evaluated RA-DDI on three public benchmark datasets, DrugBank, DDInter, and PDD-Graph. The proposed framework achieved competitive performance and showed consistent improvements over representative baselines on several key classification and ranking metrics. These findings demonstrate that combining multimodal drug representation learning with relation-aware knowledge graph modeling is effective for DDI prediction.
Related
- PRInter: an inductive multimodal heterogeneous network embedding framework with contrastive learning for lncRNA-protein interaction prediction
- HAFI-DTA: an interpretable multimodal framework for drug-target affinity prediction based on hierarchical attention guidance and feature iterative interaction
- Multimodal ensemble machine learning pipeline for oocyte fertilization prediction using first polar body morphology and clinical factors
- Prediction of pathological complete response to neoadjuvant chemo-immunotherapy in locally advanced lung adenocarcinoma: a multimodal machine learning approach
- Interpretable multimodal deep learning for time-resolved survival prediction after hepatocellular carcinoma resection
BibTeX
@article{bai2026relationaware,
title = {{Relation-aware multimodal knowledge graph learning for drug–drug interaction prediction}},
author = {Tao Bai and YuWei Gao and HaiFeng Zhang and Dapeng Yue and RuiQiang Qiao and Yuquan Feng},
journal = {Scientific Reports},
year = {2026},
month = sep,
doi = {10.1038/s41598-026-69025-0},
url = {https://doi.org/10.1038/s41598-026-69025-0},
note = {CC BY},
}
RIS
TY - JOUR
TI - Relation-aware multimodal knowledge graph learning for drug–drug interaction prediction
AU - Tao Bai
AU - YuWei Gao
AU - HaiFeng Zhang
AU - Dapeng Yue
AU - RuiQiang Qiao
AU - Yuquan Feng
PY - 2026
DA - 2026/09/01
JO - Scientific Reports
DO - 10.1038/s41598-026-69025-0
UR - https://doi.org/10.1038/s41598-026-69025-0
AB - Drug–drug interactions (DDIs) can alter therapeutic efficacy and lead to adverse events, making accurate DDI prediction important for drug safety assessment. Existing computational methods often rely on limited drug features or do not sufficiently capture heterogeneous biomedical relations surrounding drugs. We present RA-DDI, a relation-aware knowledge graph framework for DDI prediction. RA-DDI constructs a drug-centered knowledge graph (KG) from DrugBank and initializes drug representations by integrating molecular structures, textual descriptions, and graph-derived relational features. These multimodal representations are then refined through relation-aware graph learning to capture multi-hop dependencies among drugs and related biomedical entities. A prediction module combines the learned drug embeddings with pairwise interaction features to classify DDI types. We evaluated RA-DDI on three public benchmark datasets, DrugBank, DDInter, and PDD-Graph. The proposed framework achieved competitive performance and showed consistent improvements over representative baselines on several key classification and ranking metrics. These findings demonstrate that combining multimodal drug representation learning with relation-aware knowledge graph modeling is effective for DDI prediction.
SN - 2045-2322
ER -