Unveiling molecular moieties through hierarchical Grad-CAM graph explainability

Background Virtual Screening (VS) has become an essential tool in drug discovery, enabling the rapid and cost-effective identification of potential bioactive molecules. Among recent advancements, Graph Neural Networks (GNNs) have gained prominence for their ability to model complex molecular structu...

Full description

Saved in:
Bibliographic Details
Published in:BMC bioinformatics Vol. 26; no. 1; pp. 261 - 23
Main Authors: Contino, Salvatore, Sortino, Paolo, Gulotta, Maria Rita, Perricone, Ugo, Pirrone, Roberto
Format: Journal Article
Language:English
Published: London BioMed Central 23.10.2025
BioMed Central Ltd
Springer Nature B.V
BMC
Subjects:
Algorithms
Artificial intelligence
Binding
Bioinformatics
Bioinformatics and chemoinformatics in drug discovery
Biological activity
Biomedical and Life Sciences
Classification
Computational Biology/Bioinformatics
Computer Appl. in Life Sciences
Computer-aided design
Computer-Aided Drug Design (CADD)
Datasets
Drug development
Drug discovery
Drug Discovery - methods
Electronic data processing
Graph Explainability
Graph Neural Networks
Graph representations
Graphical representations
Kinases
Life Sciences
Ligands
Message passing
Methods
Microarrays
Molecular moieties
Molecular structure
Molecules
Neural networks
Neural Networks, Computer
Optimization
Prediction models
Proteins
Screening
Technology application
Virtual Screening
Italy
Computer-Aided Drug Design (CADD)
Graph Explainability
Virtual Screening
Molecular moieties
Graph Neural Networks
ISSN:1471-2105, 1471-2105
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background Virtual Screening (VS) has become an essential tool in drug discovery, enabling the rapid and cost-effective identification of potential bioactive molecules. Among recent advancements, Graph Neural Networks (GNNs) have gained prominence for their ability to model complex molecular structures using graph-based representations. However, the integration of explainable methods to elucidate the specific contributions of molecular substructures to biological activity remains a significant challenge. This limitation hampers both the interpretability of predictive models and the rational design of novel therapeutics. Results We trained 20 GNN models on a dataset of small molecules with the goal of predicting their activity on 20 distinct protein targets from the Kinase family. These classifiers achieved state-of-the-art performance in virtual screening tasks, demonstrating high accuracy and robustness on different targets. Building upon these models, we implemented the Hierarchical Grad-CAM graph Explainer (HGE) framework, enabling an in-depth analysis of the molecular moieties driving protein-ligand binding stabilization. HGE exploits Grad-CAM explanations at the atom, ring, and whole-molecule levels, leveraging the message-passing mechanism to highlight the most relevant chemical moieties. Validation against experimental data from the literature confirmed the ability of the explainer to recognize a molecular pattern of drugs and correctly annotate them to the known target. Conclusions Our approach may represent a valid support to shorten both the screening and the hit discovery process. Detailed knowledge of the molecular substructures that play a role in the binding process can help the computational chemist to gain insights into the structure optimization, as well as in drug repurposing tasks.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1471-2105
1471-2105
DOI:10.1186/s12859-025-06208-y