Relation-Aware Heterogeneous Graph Learning for miRNA–Drug Response Association Prediction Under Cold-Start Generalization
- 1Department of Information Systems, College of Computer and Information Sciences, Jouf University, Sakaka 72441, Saudi Arabia
Abstract
(1) Background: Cancer drug resistance can be influenced by microRNAs (miRNAs), which can alter gene expression and cellular pathways that determine how cancer cells respond to treatment. Potential miRNA–drug response associations can be identified using computational models; however, evaluating these models using edge-based evaluation can result in an optimistic view of model generalization since test miRNAs or drugs can appear in other response associations during training. (2) Methods: This paper presents a relation-aware heterogeneous learning framework that integrates miRNA expression profiles, miRNA–gene regulatory interactions, gene–gene functional associations, drug molecular features, and distinct drug–gene relations in a unified miRNA–gene–drug network. A Heterogeneous Graph Transformer (HGT) was used to preserve relation-specific information, and biological paths connecting each miRNA to each drug were used as additional information for the corresponding candidate miRNA–drug pair. A leakage-safe five-fold cross-validation approach was used to evaluate the proposed framework under different settings: edge, miRNA-cold, drug-cold, and double-cold. (3) Results: The proposed framework obtained an AUC and AUPR of 0.9537 ± 0.0044 and 0.9494 ± 0.0069, respectively, under the edge-based setting. The performance remained high under the miRNA-cold-based setting, where the model achieved an AUC and AUPR of 0.9466 ± 0.0061 and 0.9436 ± 0.0049, respectively. A substantial drop in performance was observed under the drug-cold setting, where the proposed framework obtained an AUC and AUPR of 0.6685 ± 0.0354 and 0.6534 ± 0.0569, respectively. The performance was also substantially reduced under the double-cold-based setting. The results also show that the structural resemblance alone is not enough to explain generalization to new drugs, since no significant relationship between cold-start performance and either ChemBERTa molecular similarity or DrugBank target similarity was shown by drug-level analysis. Literature evidence supported 6 out of 20 top-ranked previously unlabeled predictions compared to 1 of 120 randomly selected controls (Fisher’s exact test, p = 2.63 × 10−5; empirical p = 2.80 × 10−5). (4) Conclusions: The obtained results show that the proposed framework can rank candidate miRNA–drug response associations effectively. They also show that predicting response associations under the drug-cold-based setting remains much harder than predicting for similarly held-out miRNAs, which is an important limitation of conventional edge-based evaluation.
Related
- Robust and comprehensive meta-path modeling with multi-graph learning for miRNA-disease association prediction.
- TriTower-m6Am: A triple-tower heterogeneous deep learning architecture integrating semantic, sequential, and structural information for mRNA N6,2′-O-dimethyladenosine site prediction
- BRIDGE-KO: auditable transfer learning with bridged knockoffs improves cross-cohort microbiome prediction of immunotherapy response
- Multiscale and physically consistent multitask learning for protein melting temperature prediction
- Representation learning for low-data protein fitness prediction using sequence–structure embeddings and graph neural networks
BibTeX
@article{elbashir2026relationaware,
title = {{Relation-Aware Heterogeneous Graph Learning for miRNA–Drug Response Association Prediction Under Cold-Start Generalization}},
author = {Murtada K. Elbashir},
journal = {International Journal of Molecular Sciences},
year = {2026},
month = oct,
doi = {10.3390/ijms27209013},
url = {https://www.mdpi.com/1422-0067/27/20/9013},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Relation-Aware Heterogeneous Graph Learning for miRNA–Drug Response Association Prediction Under Cold-Start Generalization
AU - Murtada K. Elbashir
PY - 2026
DA - 2026/10/11
JO - International Journal of Molecular Sciences
DO - 10.3390/ijms27209013
UR - https://www.mdpi.com/1422-0067/27/20/9013
AB - (1) Background: Cancer drug resistance can be influenced by microRNAs (miRNAs), which can alter gene expression and cellular pathways that determine how cancer cells respond to treatment. Potential miRNA–drug response associations can be identified using computational models; however, evaluating these models using edge-based evaluation can result in an optimistic view of model generalization since test miRNAs or drugs can appear in other response associations during training. (2) Methods: This paper presents a relation-aware heterogeneous learning framework that integrates miRNA expression profiles, miRNA–gene regulatory interactions, gene–gene functional associations, drug molecular features, and distinct drug–gene relations in a unified miRNA–gene–drug network. A Heterogeneous Graph Transformer (HGT) was used to preserve relation-specific information, and biological paths connecting each miRNA to each drug were used as additional information for the corresponding candidate miRNA–drug pair. A leakage-safe five-fold cross-validation approach was used to evaluate the proposed framework under different settings: edge, miRNA-cold, drug-cold, and double-cold. (3) Results: The proposed framework obtained an AUC and AUPR of 0.9537 ± 0.0044 and 0.9494 ± 0.0069, respectively, under the edge-based setting. The performance remained high under the miRNA-cold-based setting, where the model achieved an AUC and AUPR of 0.9466 ± 0.0061 and 0.9436 ± 0.0049, respectively. A substantial drop in performance was observed under the drug-cold setting, where the proposed framework obtained an AUC and AUPR of 0.6685 ± 0.0354 and 0.6534 ± 0.0569, respectively. The performance was also substantially reduced under the double-cold-based setting. The results also show that the structural resemblance alone is not enough to explain generalization to new drugs, since no significant relationship between cold-start performance and either ChemBERTa molecular similarity or DrugBank target similarity was shown by drug-level analysis. Literature evidence supported 6 out of 20 top-ranked previously unlabeled predictions compared to 1 of 120 randomly selected controls (Fisher’s exact test, p = 2.63 × 10−5; empirical p = 2.80 × 10−5). (4) Conclusions: The obtained results show that the proposed framework can rank candidate miRNA–drug response associations effectively. They also show that predicting response associations under the drug-cold-based setting remains much harder than predicting for similarly held-out miRNAs, which is an important limitation of conventional edge-based evaluation.
SN - 1422-0067
ER -