Related Experiment Video
Updated: Nov 16, 2025
08:58
Artificial Intelligence Approaches to Assessing Primary Cilia
Published on: May 1, 2021
3.9K
Coloring Molecules with Explainable Artificial Intelligence for Preclinical Relevance Assessment
José Jiménez-Luna1, Miha Skalic2, Nils Weskamp2
1Department of Chemistry and Applied Biosciences, RETHINK, ETH Zurich, 8049 Zurich, Switzerland.
Journal of Chemical Information and Modeling
|February 25, 2021
Summary
This study enhances drug discovery by making graph neural network models more transparent using explainable artificial intelligence (XAI). The approach identifies key molecular features for rational drug design and is open-sourced for wider use.
Area of Science:
- Computational chemistry and cheminformatics
- Artificial intelligence in drug discovery
Background:
- Graph neural networks (GNNs) show promise in drug discovery tasks like molecular property prediction.
- GNNs are often 'black-box' models, limiting interpretability and debugging for rational molecular design.
Purpose of the Study:
- To improve the transparency of GNN models in drug discovery.
- To apply the integrated gradients explainable artificial intelligence (XAI) approach to GNNs for rational molecular design.
Main Methods:
- Trained GNN models for predicting key drug properties: plasma protein binding, hERG channel inhibition, passive permeability, and cytochrome P450 inhibition.
- Employed the integrated gradients XAI technique to analyze and interpret the GNN models.
Main Results:
- The XAI methodology successfully highlighted critical molecular features and structural elements consistent with known pharmacophore motifs.
- Identified property cliffs and provided insights into unspecific ligand-target interactions, enhancing understanding of model predictions.
- Demonstrated the utility of XAI for rational molecular design and debugging of GNNs.
Conclusions:
- The integrated gradients XAI approach enhances the interpretability of GNNs in drug discovery.
- This open-sourced methodology facilitates rational molecular design and can be applied to other clinically relevant endpoints.
- Improves trust and debugging capabilities for AI models in pharmaceutical research.
