Several types of predictive models are employed in toxicology:
Quantitative Structure-Activity Relationship (QSAR) Models: These models predict the activity of a substance based on its chemical structure. By analyzing the relationship between chemical structure and biological activity, QSAR models can forecast toxicity. Machine Learning Models: Machine learning algorithms are increasingly used to analyze large datasets of chemical properties and biological activities, providing predictions about toxicity based on patterns and trends. Physiologically Based Pharmacokinetic (PBPK) Models: These models simulate the absorption, distribution, metabolism, and excretion of chemicals in the human body, helping predict how a substance might behave in a living organism. In Silico Models: Computer-based simulations that predict chemical toxicity without physical experiments, often using databases and computational algorithms.
