When using this QDB archive, please cite (see details) it together with the original article:
Lawless, M. Data for: ADMET Predictor - Bacterial mutagenicity model (MUT_NIHS). QsarDB repository, QDB.254. 2021. http://dx.doi.org/10.15152/QDB.254
Daga, P. ADMET Predictor - Bacterial mutagenicity model (MUT_NIHS). 2020.
Title: | Daga, P. ADMET Predictor - Bacterial mutagenicity model (MUT_NIHS). 2020. |
Abstract: | MUT_NIHS The Ames bacterial mutagenicity test is an important regulatory screen for potential carcinogenicity. In silico prediction of Ames positivity plays two important but somewhat distinct roles in the discovery and development of biologically active compounds. A positive Ames test does not necessarily derail development of an active ingredient (AI), because some bacterial mutagens are not carcinogenic. As a practical matter, however, demonstrating non-carcinogenicity is challenging enough that having a robust predictive model for Ames mutagenicity is a very cost-effective alternative to automatically testing every active compound, especially since the model can be used to help decide which particular compounds to synthesize or purchase. In addition, regulatory guidance now allows the use of in silico predictions of mutagenicity to help justify waiving Ames testing requirements for impurities; ADMET Predictor®’s MUT_Risk qualifies as a “statistical model” under ICH M7. MUT_NIHS is one of the 11 models that provide input to MUT_Risk. It is an artificial neural network ensemble (ANNE) classification model built on literature data for 1716 positive examples and 10020 negative examples from the 5 standard Ames test strains (S. typhimurium strain TA98, TA100, and TA1535; S. typhimurium strain TA97 or TA1537; or S. typhimurium TA102 or E. coli WP2 uvrA) with and without metabolic activation. Of those, 342 and 2006, respectively, were set aside as an external test set for which the sensitivity was 0.780 and the specificity was 0.757 with an overall concordance of 0.760. The corresponding training set performance statistics were 0.719, 0.767, and 0.760, respectively. Predictions for any compounds for which any descriptor falls more than 10% outside the range of that descriptor seen in the training data are flagged as out-of-scope, and statistically rigorous confidences (doi 10.1186/1758-2946-6-34) are provided for all in-scope predictions. |
URI: | http://hdl.handle.net/10967/254
http://dx.doi.org/10.15152/QDB.254 |
Date: | 2021-09-02 |
Name | Description | Format | Size | View |
---|---|---|---|---|
QMRF_ADMET_MUT_NIHS-v4.xml | n/a | application/qmrf-xml | 33.63Kb | View/ |
QMRF_ADMET_MUT_NIHS-v4.xml.pdf | n/a | 39.75Kb | View/ |