A large comparison of integrated SAR/QSAR models of the Ames test for mutagenicity^$

Abstract

Results from the Ames test are the first outcome considered to assess the possible mutagenicity of substances. Many QSAR models and structural alerts are available to predict this endpoint. From a regulatory point of view, the recommendation from international authorities is to consider the predictions of more than one model and to combine results in order to develop conclusions about the mutagenicity risk posed by chemicals. However, the results of those models are often conflicting, and the existing inconsistency in the predictions requires intelligent strategies to integrate them. In our study, we evaluated different strategies for combining results of models for Ames mutagenicity, starting from a set of 10 diverse individual models, each built on a dataset of around 6000 compounds. The novelty of our study is that we collected a much larger set of about 18,000 compounds and used the new data to build a family of integrated models. These integrations used probabilistic approaches, decision theory, machine learning, and voting strategies in the integration scheme. Results are discussed considering balanced or conservative perspectives, regarding the possible uses for different purposes, including screening of large collection of substances for prioritization.

Inhibition of Protease of Novel Corona Virus by Designed Noscapines: Molecular Docking and ADMET Studies

“…Value 0 indicate ames negative while value 1 indicates ames positive. (Benfenati et al, 2018) Highest ames positive probability was found for nos83 while the lowest possibility for nos41.…”

Value and limitation ofin vitrobioassays to support the application of the threshold of toxicological concern to prioritise unidentified chemicals in food contact materials

“…available for IAS) or in silico predictions using both (Quantitative) Structure Activity Relationships (QSARs) and grouping/read across (Schilter et al 2014). There are a number of models capable of predicting Ames mutagenicity with high accuracy (Benfenati et al 2018;Honma et al 2019). To increase confidence, it is recommended to integrate QSAR models based on numerical descriptors with rule-based expert systems.…”

A natural language processing approach based on embedding deep learning from heterogeneous compounds for quantitative structure–activity relationship modeling

“…Benfenati et al. (2018) have used deep learning to find a good accuracy of Ames test for mutagenicity, from simple SMILES notation of the chemicals, and similarly, SMILES representation was used by Hirohara et al. (2018) to develop the convolutional neural network for TOX 21.…”

“…Zhang et al (2019) compared the performance of the prediction of deep neural network (DNN) algorithm models and RF models developed through structural and physicochemical features of chemicals for human ether-ago-go-related gene (hERG) activity. Benfenati et al (2018) have used deep learning to find a good accuracy of Ames test for mutagenicity, from simple SMILES notation of the chemicals, and similarly, SMILES representation was used by Hirohara et al (2018) to develop the convolutional neural network for TOX 21.…”