Browse views: by Year, by Function, by GLF, by Subfunction, by Conference, by Journal

Evaluation Of A Statistically-Based Ames Mutagenicity QSAR Model And Interpretation Of The Results Obtained

Glowienke, Susanne and Parenty, Alexis (2016) Evaluation Of A Statistically-Based Ames Mutagenicity QSAR Model And Interpretation Of The Results Obtained. Regul Tox Pharm.


The relative wealth of bacterial mutagenicity data available in the public literature allows in silico quantitative/qualitative structure activity relationship (QSAR) systems to be readily built and the models produced are generally found to be robust and perform well when validated against other published data sets. However, these test sets can overlap significantly with the data used to build the model and, therefore, may not provide a good method of testing and understanding predictions made by the systems. A better means of investigating their performance of the models is to validate them against private unpublished data sets, which generally represent unknown data and provide a greater challenge to the model. More importantly these unpublished data would more than likely be generated using novel chemical structures, occupying novel chemical space, not available for testing in the public arena. These performance metrics can give more of an insight into the general accuracy of the predictive systems. However, one should be careful not to rely solely on raw performance metrics when judging the usefulness of this type of software since expert interpretation of the results obtained may allow for further improvements in predictivity. There should be enough information provided by a QSAR to allow the user to make general, scientifically-based arguments in order to assess and overrule predictions when necessary. With this in mind, we sought to validate the performance of the statistically-based in vitro bacterial mutagenicity prediction system Sarah Nexus (version 1.1) against private test data sets supplied by nine different pharmaceutical companies. The results of these evaluations were then analysed in order to identify findings presented by the model which would be useful for the user to take into consideration by when interpreting the results. A number of general observations were made about the presentation of the arguments leading to the prediction which can aid a user in making their final decision about the mutagenic potential of a given compound.

Item Type: Article
Date Deposited: 27 Apr 2016 23:45
Last Modified: 27 Apr 2016 23:45


Email Alerts

Register with OAK to receive email alerts for saved searches.