Explainable AI for Network Pharmacology: A Critical Framework for Interpreting Multi-Target Drug Discovery on Biological Graphs
- 1Department of Medical Laboratories, College of Applied Medical Sciences, Qassim University, Buraydah 51452, Saudi Arabia
- 2Department of Information Technology, College of Computer, Qassim University, Buraydah 51452, Saudi Arabia
Abstract
Network pharmacology examines drug action across interacting targets, pathways, and disease modules. Increasingly, however, the graph neural networks and knowledge-graph models used for this purpose are difficult to inspect. This critical narrative review considers feature attribution, attention, counterfactual and rule-based explanation, explainable graph neural networks, Bayesian and causal methods, and path-based knowledge-graph reasoning. We assess these approaches against three demands imposed by biological graphs: preservation of heterogeneous node and relation semantics, support for multi-hop reasoning, and concordance with evidence excluded from model training. Among the methods reviewed, none has yet been shown to satisfy all three demands consistently. A model-faithful explanation may still emphasize node degree, network hubs, or heavily studied entities instead of a disease-specific mechanism. To address this problem, we propose five evaluation domains: faithfulness, stability, external biological concordance, bias sensitivity, and translational utility, together with a six-item reporting standard. Both are conceptual proposals; they remain unweighted, uncalibrated, and unevaluated empirically. An exploratory, literature-based application to TxGNN, DDI-GCN, and MINERVA shows that transparency-related reporting is useful but incomplete. This exercise demonstrates how the criteria might be used; it is not an empirical evaluation or calibration of the framework. We did not retrain or rerun any model or conduct new quantitative benchmarking. The field still lacks a unified biomedical benchmark that evaluates prediction and explanation together under heterogeneous, cold-start, and provenance-aware graph settings. Progress will depend on task-matched evaluation, explicit treatment of uncertainty, and experiments designed to distinguish what a model uses from what biology actually does.
Related
- From Prediction to Mechanism: Explainable AI for Plant–Microbiome Multi-Omics Integration and Biological Discovery
- Special Issue “Molecular Mechanism Discovery of the Bioactive Phytochemicals against Different Diseases Based on Network Pharmacology and Molecular Docking, 2nd Edition”
- Benchmarking AI scientists for omics data–driven biological discovery
- Biological process engineering by Pseudomonas sp. ABC1: a discovery-stage ecological chassis for open bioproduction
- Explainable computational framework for subtype classification and biomarker identification in head and neck squamous cell carcinoma using machine learning
BibTeX
@article{allemailem2026explainable,
title = {{Explainable AI for Network Pharmacology: A Critical Framework for Interpreting Multi-Target Drug Discovery on Biological Graphs}},
author = {Khaled S. Allemailem and Ahmad Almatroudi and Abdullah M. Alnajim},
journal = {International Journal of Molecular Sciences},
year = {2026},
month = oct,
doi = {10.3390/ijms27219479},
url = {https://www.mdpi.com/1422-0067/27/21/9479},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Explainable AI for Network Pharmacology: A Critical Framework for Interpreting Multi-Target Drug Discovery on Biological Graphs
AU - Khaled S. Allemailem
AU - Ahmad Almatroudi
AU - Abdullah M. Alnajim
PY - 2026
DA - 2026/10/23
JO - International Journal of Molecular Sciences
DO - 10.3390/ijms27219479
UR - https://www.mdpi.com/1422-0067/27/21/9479
AB - Network pharmacology examines drug action across interacting targets, pathways, and disease modules. Increasingly, however, the graph neural networks and knowledge-graph models used for this purpose are difficult to inspect. This critical narrative review considers feature attribution, attention, counterfactual and rule-based explanation, explainable graph neural networks, Bayesian and causal methods, and path-based knowledge-graph reasoning. We assess these approaches against three demands imposed by biological graphs: preservation of heterogeneous node and relation semantics, support for multi-hop reasoning, and concordance with evidence excluded from model training. Among the methods reviewed, none has yet been shown to satisfy all three demands consistently. A model-faithful explanation may still emphasize node degree, network hubs, or heavily studied entities instead of a disease-specific mechanism. To address this problem, we propose five evaluation domains: faithfulness, stability, external biological concordance, bias sensitivity, and translational utility, together with a six-item reporting standard. Both are conceptual proposals; they remain unweighted, uncalibrated, and unevaluated empirically. An exploratory, literature-based application to TxGNN, DDI-GCN, and MINERVA shows that transparency-related reporting is useful but incomplete. This exercise demonstrates how the criteria might be used; it is not an empirical evaluation or calibration of the framework. We did not retrain or rerun any model or conduct new quantitative benchmarking. The field still lacks a unified biomedical benchmark that evaluates prediction and explanation together under heterogeneous, cold-start, and provenance-aware graph settings. Progress will depend on task-matched evaluation, explicit treatment of uncertainty, and experiments designed to distinguish what a model uses from what biology actually does.
SN - 1422-0067
ER -