Thus, only 8.7% of the 50,000 PMNs submitted during the past 30 years have Salmonella mutagenicity data, almost none of which are available publically, and approximately 2% of pre-1979 PMNs have been reviewed for the need for toxicological data (Guth et al. 2007).
In the U.S. EPA New Chemicals Program, approximately 50,000 premanufacturing notice (PMN) cases have been received since 1979 when the program began; however, only 10% (4,997) have mutagenicity data, with 87% of these (4,351) having Salmonella assay data (Cimino MC, personal communication).
Kazius et al. provided an analysis of mutagenicity data correlating chemical substructures to mutagenicity [21, 27, 28].
The models were built on public Ames mutagenicity data and a variety of fingerprint descriptors were used.
PLS of the mutagenicity data using either the complete set (184) or the first reduced set (34) of chemical variables in the X data matrix was performed without satisfactory results.
Mutagenicity data from these experiments support the theory of formation of direct-acting mutagens, probably due to nitration.
A dataset of public mutagenicity data was extracted from the Vitic database [28].
A thorough analysis of the mutagenicity data set including the applicability domain estimation has been performed in [40].
This work included 3 training data sets: Set 1 (Bursi mutagenicity data set) having a total of 4337 compounds, Set 2 (Benchmark data set) with 6512 compounds and Set 3 which was a combination of Set 1 and Set 2 containing 8208 compounds after removing the duplicate structures based on the canonical smiles of the Set 1 and Set 2 using Pipeline Pilot [21].
A set of chemicals specified with mutagenicity data was retrieved, and necessary information was extracted and transferred to the working file.
