Computers Instead of Cells: Computational Modeling of Chemical Toxicity

Abstract

Animal toxicity testing is broadly utilized both in the pharmaceutical industry and by environmental organizations to determine the potential health hazards of drug candidates and environmental chemicals. The traditional approaches for animal toxicity testing (e.g., chronic toxicity tests) are costly, time-consuming, and have low throughput. Cell-based assays, especially those using high throughput screening (HTS) techniques, have been developed and used as a possible alternative to in vivo toxicity testing. Additionally, quantitative structure–activity relationships (QSAR) can be used to explore the dependency of biological, toxicological, or other types of activities/properties of chemicals on their molecular features and thereby used as a predictive tool. In the past two decades, computational toxicity models, especially those by QSAR modeling, have been used extensively in the drug discovery process. Computer toxicity predictors can be used to evaluate the toxicity potential of compounds before they are synthesized. This chapter reviews recent efforts in computational toxicology, including chemical toxicity database curation, information on public and commercial toxicity predictors, and modern computational toxicity models developed by hybrid modeling techniques. The applications introduced in this chapter will be of interest to researchers working in the field of computational drug discovery and environmental chemical risk assessment.