Skip to content
Open access

vToxiNet: An interpretable deep learning framework for hepatotoxicity prediction and mechanism exploration.

Oct 2026 · Journal of Hazardous Materials · Vol 518, pp. 143880 · 0 citations · 60 references
Medicine

TL;DR

This study introduces the virtual toxicity network (vToxiNet), a biologically constrained deep learning framework that embeds systems toxicology knowledge directly into neural network architecture for interpretable hepatotoxicity prediction and supports further development of mechanism-informed approaches for chemical hazard assessment.

Abstract

Hepatotoxicity remains a leading cause of drug attrition and post-marketing withdrawal, resulting from diverse and complex toxicity mechanisms. Traditional in vitro models can only capture a limited subset of toxicity pathways, and animal studies face translational and ethical limitations. Regulatory agencies have therefore promoted new approach methodologies, including human-relevant assays, omics technologies, and computational models to improve predictive toxicology and support evidence-based decision-making. However, most machine learning models for hepatotoxicity either rely solely on chemical structure or operate as black boxes, limiting mechanistic interpretability and broader applicability. Here, we introduce the virtual toxicity network (vToxiNet), a biologically constrained deep learning framework that embeds systems toxicology knowledge directly into neural network architecture for interpretable hepatotoxicity prediction. vToxiNet integrates chemical descriptors, high-throughput assay responses, transcriptomic signatures, and Reactome pathway hierarchy to construct a virtual adverse outcome pathway network. Across cross-validation and external validation, vToxiNet demonstrates promising predictive performance. Importantly, interpretation of vToxiNet enables gene and pathway-level attribution, supporting mechanism-informed hazard characterization and chemical prioritization. By integrating multimodal data and biological hierarchy as architectural constraints, this study provides a framework that combines prediction with mechanistic interpretation and supports further development of mechanism-informed approaches for chemical hazard assessment.

Read PDF

Similar papers

Review Oct 2026

Artificial Intelligence and machine learning in toxicogenomics for drug safety assessment: a critical review.

INTRODUCTION Predicting drug-induced toxicity remains one of the principal bottlenecks in drug development: in vivo and in vitro assays are resource-intensive, and their concordance with human-specific toxicity is often limited. Toxicogenomics addresses this gap by linking chemical exposure to gene-expression and pathw...

Baseerat Fatima, Minal Zaka, Maham Ashraf et al. · 0 citations
Review Open access Oct 2026

Artificial intelligence - driven toxicogenomics for predictive environmental and pharmaceutical safety

The significance of AI-based toxicogenomics in drug development, environmental contaminant screening, and regulatory toxicology, while addressing key challenges such as data heterogeneity, model interpretability, and regulatory acceptance is discussed.

Mohammed Monirul Islam, Sibghatullah Muhammad Ali Sangi, Girish Meravanige et al. · 0 citations
#graph neural networks Review Open access Oct 2026

A review on advances in chemical compound toxicology prediction

The accurate prediction of chemical toxicity remains a major challenge in drug development and chemical safety assessment because conventional approaches can be costly, time-consuming, ethically constrained, and limited in predictive performance. This review examines how artificial intelligence (AI), particularly machi...

Ahmed Hagag, Nada A. Elsayed, Ibrahim Abdelbaky · 0 citations
Open access Oct 2026

Causality-integrated graph learning for multi-endpoint toxicity prediction.

A causality-integrated graph learning framework that embeds toxicological mechanisms extracted from large-scale literature mining as directed graphs within deep learning (DL) models, establishing a mechanism-constrained, causality-informed learning paradigm that is highly relevant for multi-endpoint toxicity assessment...

Hao-Yue Tan, Tong Bao, Yin Fang et al. · 0 citations
Open access Sep 2026

Machine Learning for Toxicity Prediction in Low-Sample Molecular Classes

A framework that fine-tunes a general baseline model trained on publicly available data on small, class-specific datasets to retain the baseline’s generalization ability while gaining class-specific accuracy and produce probabilistic outputs that capture uncertainty in the training data is proposed.

C. Barajas, Laura L. Dunphy, Luke C. Mullany et al. · 0 citations
Open access Oct 2026

Integrating in silico ADME modeling with Tox21 toxicity profiling to support compound prioritization

Toxicity remains a leading cause of late-stage attrition in drug development and is heavily influenced by a compound’s ADME (Absorption, Distribution, Metabolism, and Excretion) properties. The ability of a molecule to reach its target tissue, persist in circulation, or undergo bioactivation fundamentally shapes its...

Pranav Shah, C. Weber, Nivedita Kinatukara et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.