Machine Learning of Toxicological Big Data Enables Read-Across Structure Activity Relationships (RASAR) Outperforming Animal Test Reproducibility

@article{Luechtefeld2018MachineLO,
  title={Machine Learning of Toxicological Big Data Enables Read-Across Structure Activity Relationships (RASAR) Outperforming Animal Test Reproducibility},
  author={T. Luechtefeld and D. Marsh and C. Rowlands and T. Hartung},
  journal={Toxicological Sciences},
  year={2018},
  volume={165},
  pages={198 - 212}
}
  • T. Luechtefeld, D. Marsh, +1 author T. Hartung
  • Published 2018
  • Computer Science, Medicine
  • Toxicological Sciences
  • Earlier we created a chemical hazard database via natural language processing of dossiers submitted to the European Chemical Agency with approximately 10 000 chemicals. [...] Key Method We identified repeat OECD guideline tests to establish reproducibility of acute oral and dermal toxicity, eye and skin irritation, mutagenicity and skin sensitization. Based on 350-700+ chemicals each, the probability that an OECD guideline animal test would output the same result in a repeat test was 78%-96% (sensitivity 50%-87…Expand Abstract
    83 Citations
    Predicting toxicity of chemicals: software beats animal testing
    • T. Hartung
    • Computer Science, Medicine
    • EFSA journal. European Food Safety Authority
    • 2019
    • 6
    • PDF
    Quantitative prediction of repeat dose toxicity values using GenRA.
    • 2
    Molecular fingerprint‐derived similarity measures for toxicological read‐across: Recommendations for optimal use
    • 12
    • Highly Influenced
    • PDF
    Skin Doctor: Machine Learning Models for Skin Sensitization Prediction that Provide Estimates and Indicators of Prediction Reliability
    • PDF

    References

    SHOWING 1-10 OF 50 REFERENCES
    Big-data and machine learning to revamp computational toxicology and its use in risk assessment.
    • 20
    • PDF
    Computational Approaches to Chemical Hazard Assessment
    • 18
    • PDF
    Supporting read-across using biological data.
    • 54
    Systematically evaluating read-across prediction and performance using a local validity approach characterized by chemical structure and bioactivity information.
    • 48
    • PDF
    Analysis of Publically Available Skin Sensitization Data from REACH Registrations 2008–2014
    • 43
    • PDF
    Analysis of Public Oral Toxicity Data from REACH Registrations 2008–2014
    • 38
    • PDF
    Assessing skin sensitization hazard in mice and men using non-animal test methods.
    • 173
    • PDF
    Green toxicology.
    • 29