Benchmark Data Set
for In Silico Prediction of Ames Mutagenicity

On these pages we present a public benchmark data set of 6512 chemical compounds together with their Ames mutagenicity test results (2-class classification problem). The data set was designed for the evaluation of in silico prediction methods. [ Download | Results ]

Available Versions

		compounds	online since
Version 2	Information	6512	April 2009
Version 1	Information	7090	November 2008

Data Set Characteristics Version 2

Ames Mutagenicity

positive compounds	3503
negative compounds	3009
total	6512

The classes of positive and negative Ames Test results are balanced.
Ames Test
In the Ames test, frame-shift mutations or base-pair substitutions may be detected by exposure of histidine-dependent strains of Salmonella typhimurium to a test compound. When these strains are exposed to a mutagen, reverse mutations to the original histidine-independent form enable bacterial colony growth on a medium deficient in histidine ("revertants"). Since many chemicals interact with genetic material only after metabolic activation by enzyme systems not available in the bacterial cell, the test compound is additionally examined in the presence of a mammalian metabolizing system (with S9 mix). A compound is classified positive if it significantly induces revertant colony growth at least in one strain, either in the presence or absence of S9 mix. A compound is labeled negative if it does not induce revertant colony growth in any strain tested, both in the presence and absence of S9 mix.

Molecular Weight

The molecular weight averages 249 (median 230).

Data Sources

The data was collected from public sources:

Source	no of compounds	reference
CCRIS	2539	[1]
Kazius 2004	2224	[2]
Helma 2004	138	[3]
Feng 2003	391	[4]
VITIC	1194	[5]
GENETOX	26	[6]

[1] Chemical Carcinogenesis Research Information System. http://www.cancerinformatics.org.uk/matrix/CCRIS.htm
[2] Kazius J et al. Derivation and Validation of Toxicophores for Mutagenicity Prediction. J. Med. Chem. 2005, 48, 312-320
[3] C. Helma et al. Data Mining and Machine Learning Techniques for the Identification of Mutagenicity Inducing Substructures and Structure Activity Relationships of Noncongeneric Compounds. J. Chem. Inf. Comput. Sci. 2004, 44, 1402-1411
[4] J. Feng et al. Predictive Toxicology: Benchmarking Molecular Descriptors and Statistical Methods. J. Chem. Inf. Comput. Sci. 2003, 43, 1463-1470
[5] PN Judsom et al. Towards the Creation of an International Toxicology Information Centre. Toxicology 213(1-2):117-28, 2005
[6] Genetic Toxicity, Reproductive and Development Toxicity, and Carcinogenicity Database. http://www.fda.gov/Cder/Offices/OPS_IO/genrepcar.htm

, . Impressum