Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 20 min ago
Peer-reviewedCC BY 4.0Frontiers in Bioinformatics

A review on advances in chemical compound toxicology prediction

  • Ahmed Hagag1,2
  • Nada A. Elsayed3
  • Ibrahim Abdelbaky3,4
4 affiliations
  1. 1Information Technology and Computing Program, Faculty of Computer Studies, Arab Open University, El-Shorouk, Egypt
  2. 2Department of Scientific Computing, Faculty of Computers and Artificial Intelligence, Benha University, Benha, Egypt
  3. 3Department of Artificial Intelligence, Faculty of Computers and Artificial Intelligence, Benha University, Benha, Egypt
  4. 4Computer Science Department, Faculty of Computers and Information Technology, Future University in Egypt, New Cairo, Egypt
Read full textPDFDOICite

Abstract

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 machine learning (ML) and deep learning (DL), is being applied to predictive toxicology. It covers conventional algorithms such as support vector machines (SVMs), decision trees (DTs), and ensemble methods, together with advanced approaches including graph neural networks (GNNs). The review evaluates AI-based methods across five organ-specific toxicity domains—hepatotoxicity, cardiotoxicity, respiratory toxicity, nephrotoxicity, and neurotoxicity—and critically compares molecular representations, data-integration strategies, model architectures, validation protocols, and interpretability approaches. Particular emphasis is placed on data quality, class imbalance, model explainability, applicability domains, external validation, and regulatory acceptance. By integrating recent methodological advances with persistent implementation challenges, this review provides a technical framework for developing more transparent, reliable, and generalizable computational tools for safety assessment in drug discovery and environmental health.

Related

  1. Bridging MS2 Spectra and Chemical Space: Advances in Spectral Similarity, Molecular Retrieval, and De Novo Structure Discovery
    Julian Pollmann, Roman Bushuiev, Anton Bushuiev +2
    ChemRxivPreprintCC BYFull textMolecular biology & gene regulationChemRxiv
  2. Metabolomics in the Prediction and Early Diagnosis of Type 2 Diabetes Mellitus: Advances and Applications.
    Xiaokai Wei, Min He, Haili Wang +9
    International journal of medical sciencesPeer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMC
  3. Chemical and geometric representation fidelity improves drug--target affinity prediction
    Yixiao Li, Yining Qian, Yefan Chen +5
    arXivPreprintarXiv licenceFull textBiophysicsStatisticsarXiv
  4. New Advances and Current Trends in Bioavailability of Coffee and Coffee By-Product Constituents and Their Metabolites: A Review
    Boris Nemzer, Fadwa Al-Taher, Nebiyu Abshiru +1
    International Journal of Molecular SciencesPeer-reviewedCC BY 4.0General biochemistryCrossref
  5. Identification of Toxicological Targets of Benzo[a]pyrene and Its Metabolite BPDE in Lung Adenocarcinoma Revealed by Integrated Network Toxicology, Machine Learning and Multi-Omics
    Hongcai Mao, Xingyao Chen, Xiangyu Zhang +2
    MetabolitesPeer-reviewedCC BY 4.0Proteomics & metabolomicsCrossref

Cite

BibTeXRIS
BibTeX
@article{hagag2026review,
  title = {{A review on advances in chemical compound toxicology prediction}},
  author = {Ahmed Hagag and Nada A. Elsayed and Ibrahim Abdelbaky},
  journal = {Frontiers in Bioinformatics},
  year = {2026},
  month = oct,
  doi = {10.3389/fbinf.2026.1974935},
  url = {https://doi.org/10.3389/fbinf.2026.1974935},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - A review on advances in chemical compound toxicology prediction
AU  - Ahmed Hagag
AU  - Nada A. Elsayed
AU  - Ibrahim Abdelbaky
PY  - 2026
DA  - 2026/10/12
JO  - Frontiers in Bioinformatics
DO  - 10.3389/fbinf.2026.1974935
UR  - https://doi.org/10.3389/fbinf.2026.1974935
AB  - 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 machine learning (ML) and deep learning (DL), is being applied to predictive toxicology. It covers conventional algorithms such as support vector machines (SVMs), decision trees (DTs), and ensemble methods, together with advanced approaches including graph neural networks (GNNs). The review evaluates AI-based methods across five organ-specific toxicity domains—hepatotoxicity, cardiotoxicity, respiratory toxicity, nephrotoxicity, and neurotoxicity—and critically compares molecular representations, data-integration strategies, model architectures, validation protocols, and interpretability approaches. Particular emphasis is placed on data quality, class imbalance, model explainability, applicability domains, external validation, and regulatory acceptance. By integrating recent methodological advances with persistent implementation challenges, this review provides a technical framework for developing more transparent, reliable, and generalizable computational tools for safety assessment in drug discovery and environmental health.
SN  - 2673-7647
ER  -