Combining Deep Learning and Explainable AI for Toxicity Prediction of Chemical Compounds

TL;DR

This paper presents a novel deep learning pipeline using DenseNet121 and Grad-CAM for predicting chemical toxicity, enhancing interpretability and performance in cheminformatics.

Contribution

It introduces an image-based deep learning approach combined with explainable AI techniques for toxicity prediction, improving transparency and accuracy.

Findings

Competitive predictive performance with traditional models

Effective visualization of toxicological features using Grad-CAM

Demonstrates the value of combining image-based methods with explainability

Abstract

The task here is to predict the toxicological activity of chemical compounds based on the Tox21 dataset, a benchmark in computational toxicology. After a domain-specific overview of chemical toxicity, we discuss current computational strategies, focusing on machine learning and deep learning. Several architectures are compared in terms of performance, robustness, and interpretability. This research introduces a novel image-based pipeline based on DenseNet121, which processes 2D graphical representations of chemical structures. Additionally, we employ Grad-CAM visualizations, an explainable AI technique, to interpret the model's predictions and highlight molecular regions contributing to toxicity classification. The proposed architecture achieves competitive results compared to traditional models, demonstrating the potential of deep convolutional networks in cheminformatics. Our findings emphasize the value of combining image-based representations with explainable AI methods to improve both predictive accuracy and model transparency in toxicology.