Genetic toxicology data is used as a surrogate for long-term carcinogenicity data during early drug development. The aim of genotoxicity testing is to identify potentially hazardous drug candidates. Results from genetic toxicology tests in combination with acute and subchronic animal data are used as the basis to approve clinical trials of drug candidates. With few exceptions, mutagenic compounds are dropped from development and clastogenic compounds result in unfavorable labeling, require disclosure in clinical trial consent forms, and can impact the marketability of a new drug. Therefore, genetic toxicology testing in drug discovery and optimization serves to quickly identify mutagens and remove them from development. Additionally, clastogenicity can delay drug development by requiring additional testing to determine in vivo relevance of in vitro clastogenic responses. Clastogenicity screening is conducted so any additional testing can be planned and perhaps integrated into other toxicity studies to expedite progression of drugs into the clinic. Commercially available genotoxicity and carcinogenicity predictive software systems used for decision support by ICSAS, FDA/CDER is described along with the strengths and weakness of each system. The FDA has concentrated on using a consensus approach to maximize certainty for positive predictions at the expense of sensitivity. The consensus approach consists of requiring 2 complementary software packages, such as MC4PC and MDL QSAR models, to agree that a compound has a genotoxic or carcinogenic liability. Mutagenicity and clastogenicity screening tests are described along with advantages and disadvantages of each test. Several testing strategies are presented for consideration.