Unveiling molecular moieties through hierarchical Grad-CAM graph explainability.

ABSTRACT:

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 fa

SUBMITTER: Contino S 

PROVIDER: S-EPMC12551347 | biostudies-literature | 2025 Oct

REPOSITORIES: biostudies-literature