Structured multi-view relational learning for drug response prediction.
- 1School of Computer Science and Technology, Wuhan University of Science and Technology, 2 Huangjiahuxi Road, Hongshan District, Wuhan 430065, Hubei, China.
- 2School of Computer Science and Artificial Intelligence, Wuhan Textile University, 1 Yangguang Avenue, Jiangxia District, Wuhan 430200, Hubei, China.
Abstract
Drug response prediction (DRP) requires models that jointly characterize molecular drug structure and heterogeneous cellular states. Although recent deep learning approaches have integrated multi-omics profiles with drug representations, many treat omics views as parallel feature sources or merge them before relational modeling, which can weaken omics-view-specific cell-line relation structures. Here, we propose MulDR, a structured multi-view relational learning framework that preserves omics-view-specific cell-line relation structures before drug-conditioned cell-drug interaction. MulDR constructs separate relation structures for pathway activity, gene expression, mutation, and DNA methylation, learns view-specific relational cell representations, and uses complementary motif-level, geometry-aware molecular graph, and Morgan fingerprint drug representations to condition their fusion. With this design, cell-line similarity remains view-dependent until the interaction stage, rather than being prematurely compressed into a single feature or relation space. Extensive experiments show that MulDR consistently outperforms representative and recent baselines under the same evaluation protocol, reducing root mean square error by 6.07% relative to the strongest baseline. Cold-start evaluations on unseen drugs and cell lines further show that MulDR generalizes to previously unseen entities, while ablation studies show that removing either view-specific relational modeling or drug-conditioned fusion consistently compromises predictive performance. Together, these results suggest that preserving omics-specific cell-line relations before drug-conditioned interaction modeling provides an effective strategy for robust DRP.
Related
- Computational Fluid Dynamics-Informed Machine Learning-Enabled Digital Twin for Vapor Maldistribution Prediction in Structured Packed Distillation Columns
- Accelerating Proton Affinity Prediction with Multi-Fidelity Machine Learning
- Topology-Guided Multi-Level Graph Learning: A Unified Framework for Molecular Property Prediction
- Physics-Informed Deep Learning Surrogate for Mechanical-Response Prediction and Failure Assessment of High-Performance Polymer Composites
- Prediction model for compressive strength of alkali-activated multi-source solid-waste grouting materials based on generative adversarial networks and machine learning
BibTeX
@article{wang2026structured,
title = {{Structured multi-view relational learning for drug response prediction.}},
author = {Zengwei Wang and Wanchen Li and Junlin Xu and Yajie Meng and Hao Zhou and Shuting Jin},
journal = {Briefings in bioinformatics},
year = {2026},
month = nov,
doi = {10.1093/bib/bbag619},
url = {https://europepmc.org/article/MED/42998281},
note = {CC BY},
}
RIS
TY - JOUR
TI - Structured multi-view relational learning for drug response prediction.
AU - Zengwei Wang
AU - Wanchen Li
AU - Junlin Xu
AU - Yajie Meng
AU - Hao Zhou
AU - Shuting Jin
PY - 2026
DA - 2026/11/01
JO - Briefings in bioinformatics
DO - 10.1093/bib/bbag619
UR - https://europepmc.org/article/MED/42998281
AB - Drug response prediction (DRP) requires models that jointly characterize molecular drug structure and heterogeneous cellular states. Although recent deep learning approaches have integrated multi-omics profiles with drug representations, many treat omics views as parallel feature sources or merge them before relational modeling, which can weaken omics-view-specific cell-line relation structures. Here, we propose MulDR, a structured multi-view relational learning framework that preserves omics-view-specific cell-line relation structures before drug-conditioned cell-drug interaction. MulDR constructs separate relation structures for pathway activity, gene expression, mutation, and DNA methylation, learns view-specific relational cell representations, and uses complementary motif-level, geometry-aware molecular graph, and Morgan fingerprint drug representations to condition their fusion. With this design, cell-line similarity remains view-dependent until the interaction stage, rather than being prematurely compressed into a single feature or relation space. Extensive experiments show that MulDR consistently outperforms representative and recent baselines under the same evaluation protocol, reducing root mean square error by 6.07% relative to the strongest baseline. Cold-start evaluations on unseen drugs and cell lines further show that MulDR generalizes to previously unseen entities, while ablation studies show that removing either view-specific relational modeling or drug-conditioned fusion consistently compromises predictive performance. Together, these results suggest that preserving omics-specific cell-line relations before drug-conditioned interaction modeling provides an effective strategy for robust DRP.
SN - 1467-5463
SN - 1477-4054
ER -