Development of a new quantitative structure–activity relationship model for predicting Ames mutagenicity of food flavor chemicals using StarDrop™ auto-Modeller™

Abstract

Background Food flavors are relatively low molecular weight chemicals with unique odor-related functional groups that may also be associated with mutagenicity. These chemicals are often difficult to test for mutagenicity by the Ames test because of their low production and peculiar odor. Therefore, application of the quantitative structure–activity relationship (QSAR) approach is being considered. We used the StarDrop™ Auto-Modeller™ to develop a new QSAR model. Results In the first step, we developed a new robust Ames database of 406 food flavor chemicals consisting of existing Ames flavor chemical data and newly acquired Ames test data. Ames results for some existing flavor chemicals have been revised by expert reviews. We also collected 428 Ames test datasets for industrial chemicals from other databases that are structurally similar to flavor chemicals. A total of 834 chemicals’ Ames test datasets were used to develop the new QSAR models. We repeated the development and verification of prototypes by selecting appropriate modeling methods and descriptors and developed a local QSAR model. A new QSAR model “StarDrop NIHS 834_67” showed excellent performance (sensitivity: 79.5%, specificity: 96.4%, accuracy: 94.6%) for predicting Ames mutagenicity of 406 food flavors and was better than other commercial QSAR tools. Conclusions A local QSAR model, StarDrop NIHS 834_67, was customized to predict the Ames mutagenicity of food flavor chemicals and other low molecular weight chemicals. The model can be used to assess the mutagenicity of food flavors without actual testing.

Genotoxicity assessment of food-flavoring chemicals used in Japan

“…The ICH-M7 guideline also allows the use of the quantitative structure–activity relationship ((Q)SAR) approach for the initial assessment of genotoxicity instead of the Ames test. We have developed and validated some (Q)SAR tools for assessing the genotoxicity of food-flavoring chemicals, demonstrating good correlation between the (Q)SAR and Ames results [6] , [7] , [8] , [14] . We believe that (Q)SAR will be widely accepted in the field of genotoxicity as an alternative to the Ames test in the near future.…”

“…Table 1 summarizes the results of the Ames test, CA test, MN test, and TG assay. The Ames test data have already been reported in a previous study [14] , and the raw data of the Ames test are available in the additional file of the study. The CA test, MN test, and TG assay were conducted in this study.…”

In vivo and in vitro mutagenicity of perillaldehyde and cinnamaldehyde

“…In the present study, cinnamaldehyde showed a similar response, i.e., the maximum revertant frequency in the TA100 strain in the absence of S9-mix was slightly more than twice that in the negative control. Trans-cinnamaldehyde (cas# 104–55-2), 4′-methoxy cinnamaldehyde (cas#1963-36-6), and benzalacetone (4-phenyl − 3-buten-2-one; cas# 122–57-6), which are cinnamaldehyde-related flavor chemicals, have also shown positive results in Ames tests [ 39 ]. We concluded that cinnamaldehyde and its derivatives are mutagenic in vitro, given that they show reproducible Ames mutagenicity and have α,β-unsaturated aldehydes.…”

Multitask Deep Neural Networks for Ames Mutagenicity Prediction

“…The development of in silico methods for predicting the result of the AMES toxicity test is an active field of research in computational toxicology, − and several articles have reviewed the most relevant models and software tools for predicting mutagenicity under different datasets. − However, the impact that different strains used in the Ames test could have in the design of QSAR (Quantitative Structure Activity Relationship) methods has been scarcely studied. QSAR models found in the literature are trained using only overall values (i.e., toxic and nontoxic classes) resulting from the Ames test, without considering the intermediate results achieved by the experiments individually conducted for each strain.…”