Computational Toxicology Methods in Drug and Green Chemical Discovery
Author Information
Author(s): Bueso-Bordils Jose I., Antón-Fos Gerardo M., Martín-Algarra Rafael, Alemán-López Pedro A.
Primary Institution: CEU Cardenal Herrera University
Hypothesis
How can computational toxicology methods improve drug and green chemical discovery?
Conclusion
Computational toxicology methods, particularly machine learning and deep learning, can significantly enhance the prediction of toxicity in drug development and environmental safety.
Supporting Evidence
- Computational toxicology can predict chemical hazards without the need for animal testing.
- Machine learning methods are increasingly important due to the availability of diverse toxicology data.
- Deep learning models can learn complex patterns in toxicological data, improving prediction accuracy.
- QSAR models link chemical structure to biological activity, aiding in toxicity prediction.
Takeaway
Scientists can use computers to predict if chemicals are safe without testing on animals. This helps in making new medicines and protecting the environment.
Methodology
The review summarizes various computational methods, including machine learning and deep learning, used for toxicity prediction in drug design and environmental toxicology.
Limitations
The review highlights challenges such as the need for comprehensive toxicity data and the low prediction accuracy of some models.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website