Testing by artificial intelligence: computational alternatives to the determination of mutagenicity.

In order to develop methods for evaluating the predictive performance of computer-driven structure-activity methods (SAR) as well as to determine the limits of predictivity, we investigated the behavior of two Salmonella mutagenicity data bases: (a) a subset from the Genetox Program and (b) one from the U.S. National Toxicology Program (NTP). For molecules common to the two data bases, the experimental concordance was 76% when "marginals" were included and 81% when they were excluded. Three SAR methods were evaluated: CASE, MULTICASE and CASE/Graph Indices (CASE/GI). The programs "learned" the Genetox data base and used it to predict NTP molecules that were not present in the Genetox compilation. The concordances were 72, 80 and 47% respectively. Obviously, the MULTICASE version is superior and approaches the 85% interlaboratory variability observed for the Salmonella mutagenicity assays when the latter was carried out under carefully controlled conditions.

[1]  Errol Zeiger,et al.  Evaluation of four in vitro genetic toxicity tests for predicting rodent carcinogenicity: Confirmation of earlier results with 41 additional chemicals , 1990, Environmental and molecular mutagenesis.

[2]  D. Brusick,et al.  The Salmonella typhimurium/mammalian microsomal assay. A report of the U.S. Environmental Protection Agency Gene-Tox Program. , 1986, Mutation research.

[3]  E. Zeiger,et al.  Salmonella mutagenicity test results for 250 chemicals. , 1983, Environmental mutagenesis.

[4]  R. Tennant,et al.  Classification according to chemical structure, mutagenicity to Salmonella and level of carcinogenicity of a further 39 chemicals tested for carcinogenicity by the U.S. National Toxicology Program. , 1991, Mutation research.

[5]  G Klopman,et al.  Structure-activity relations: maximizing the usefulness of mutagenicity and carcinogenicity databases. , 1991, Environmental health perspectives.

[6]  H S Rosenkranz,et al.  Structural basis of the mutagenicity of phenylazoaniline dyes. , 1989, Mutation research.

[7]  H S Rosenkranz,et al.  Structural basis of carcinogenicity in rodents of genotoxicants and non-genotoxicants. , 1990, Mutation research.

[8]  Gilles Klopman,et al.  Evaluation of quantitative structure-activity predictions. Comparison of the predictive power of an artificial intelligence system with human experts , 1990 .

[9]  R. Tennant,et al.  Definitive relationships among chemical structure, carcinogenicity and mutagenicity for 301 chemicals tested by the U.S. NTP. , 1991, Mutation research.

[10]  D. E. Bailey,et al.  Probability and statistics;: Models for research , 1971 .

[11]  H S Rosenkranz,et al.  Quantification of the predictivity of some short-term assays for carcinogenicity in rodents. , 1991, Mutation research.

[12]  R. Tennant,et al.  Chemical structure, Salmonella mutagenicity and extent of carcinogenicity as indicators of genotoxic carcinogenesis among 222 chemicals tested in rodents by the U.S. NCI/NTP. , 1988, Mutation research.

[13]  H. Rosenkranz,et al.  The structural basis of the mutagenicity of chemicals in Salmonella typhimurium: the Gene-Tox data base. , 1990, Mutation research.

[14]  Errol Zeiger,et al.  Measuring Intra-Assay Agreement for the Ames Salmonella Assay , 1991 .

[15]  H S Rosenkranz,et al.  Structure activity-based predictive toxicology: an efficient and economical method for generating non-congeneric data bases. , 1991, Mutagenesis.