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

• URL: http://arxiv.org/abs/2510.22572v1
• Date: Sun, 26 Oct 2025 08:05:11 GMT
• Title: Combining Deep Learning and Explainable AI for Toxicity Prediction of Chemical Compounds
• Authors: Eduard Popescu, Adrian Groza, Andreea Cernat,
• Abstract summary: This research introduces a novel image-based pipeline based on DenseNet121, which processes 2D graphical representations of chemical structures.<n>We employ Grad-CAM visualizations, an explainable AI technique, to interpret the model's predictions and highlight molecular regions contributing to toxicity classification.
• Score: 0.764671395172401
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• Unveiling Latent Knowledge in Chemistry Language Models through Sparse Autoencoders [42.033443425253644]
  We extend sparse autoencoder techniques to uncover and examine interpretable features within chemistry language models.<n>Our findings reveal that these models encode a rich landscape of chemical concepts.<n>Our approach provides a generalisable framework for uncovering latent knowledge in chemistry-focused AI systems.
  arXiv  Detail & Related papers  (2025-12-08T22:20:01Z)
• RxnCaption: Reformulating Reaction Diagram Parsing as Visual Prompt Guided Captioning [51.393018266721576]
  We propose the RxnCaption framework for the task of chemical Reaction Diagram Parsing (RxnDP)<n>Our framework reformulates the traditional coordinate prediction driven parsing process into an image captioning problem.<n>We introduce a strategy termed "BBox and Index as Visual Prompt" (BIVP), which uses our state-of-the-art molecular detector, MolYOLO, to pre-draw molecular bounding boxes and indices directly onto the input image.
  arXiv  Detail & Related papers  (2025-11-04T09:08:44Z)
• Foundation Models for Discovery and Exploration in Chemical Space [57.97784111110166]
  MIST is a family of molecular foundation models trained on large unlabeled datasets.<n>We demonstrate the ability of these models to solve real-world problems across chemical space.
  arXiv  Detail & Related papers  (2025-10-20T17:56:01Z)
• Graph Neural Networks in Modern AI-aided Drug Discovery [16.25759507753197]
  Graph neural networks (GNNs) have emerged as powerful tools for AI-aided drug discovery (AIDD)<n>GNNs offer an intuitive and expressive framework for learning the complex topological and geometric features of drug-like molecules.<n>This review provides a comprehensive overview of the methodological foundations and representative applications of GNNs in drug discovery.
  arXiv  Detail & Related papers  (2025-06-07T20:29:59Z)
• Contrastive Dual-Interaction Graph Neural Network for Molecular Property Prediction [0.0]
  We introduce DIG-Mol, a novel self-supervised graph neural network framework for molecular property prediction. DIG-Mol integrates a momentum distillation network with two interconnected networks to efficiently improve molecular characterization. We have established DIG-Mol's state-of-the-art performance through extensive experimental evaluation in a variety of molecular property prediction tasks.
  arXiv  Detail & Related papers  (2024-05-04T10:09:27Z)
• Benchmarking Toxic Molecule Classification using Graph Neural Networks and Few Shot Learning [0.0]
  Traditional Graph Convolutional Networks (GCNs) face challenges with limited data and class imbalance. We harness the power of Graph Isomorphic Networks, Multi Headed Attention and Free Large-scale Adversarial Augmentation separately on Graphs. We incorporate Few-Shot Learning to improve the model's generalization with limited annotated samples.
  arXiv  Detail & Related papers  (2023-11-22T16:07:32Z)
• Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations [68.32093648671496]
  We introduce GODE, which accounts for the dual-level structure inherent in molecules.<n> Molecules possess an intrinsic graph structure and simultaneously function as nodes within a broader molecular knowledge graph.<n>By pre-training two GNNs on different graph structures, GODE effectively fuses molecular structures with their corresponding knowledge graph substructures.
  arXiv  Detail & Related papers  (2023-06-02T15:49:45Z)
• Hierarchical Graph Representation Learning for the Prediction of Drug-Target Binding Affinity [7.023929372010717]
  We propose a novel hierarchical graph representation learning model for the drug-target binding affinity prediction, namely HGRL-DTA. In this paper, we adopt a message broadcasting mechanism to integrate the hierarchical representations learned from the global-level affinity graph and the local-level molecular graph. Besides, we design a similarity-based embedding map to solve the cold start problem of inferring representations for unseen drugs and targets.
  arXiv  Detail & Related papers  (2022-03-22T04:50:16Z)
• Energy-based View of Retrosynthesis [70.66156081030766]
  We propose a framework that unifies sequence- and graph-based methods as energy-based models. We present a novel dual variant within the framework that performs consistent training over Bayesian forward- and backward-prediction. This model improves state-of-the-art performance by 9.6% for template-free approaches where the reaction type is unknown.
  arXiv  Detail & Related papers  (2020-07-14T18:51:06Z)
• Graph Neural Networks for the Prediction of Substrate-Specific Organic Reaction Conditions [79.45090959869124]
  We present a systematic investigation using graph neural networks (GNNs) to model organic chemical reactions. We evaluate seven different GNN architectures for classification tasks pertaining to the identification of experimental reagents and conditions.
  arXiv  Detail & Related papers  (2020-07-08T17:21:00Z)
• Retrosynthesis Prediction with Conditional Graph Logic Network [118.70437805407728]
  Computer-aided retrosynthesis is finding renewed interest from both chemistry and computer science communities. We propose a new approach to this task using the Conditional Graph Logic Network, a conditional graphical model built upon graph neural networks.
  arXiv  Detail & Related papers  (2020-01-06T05:36:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.