Development of a read-across-derived classification model for the predictions of mutagenicity data and its comparison with traditional QSAR models and expert systems.

Mutagenicity is considered an important endpoint from the regulatory, environmental and medical points of view. Due to the wide number of compounds that may be of concern and the enormous expenses (in terms of time, money, and animals) associated with rodent mutagenicity bioassays, this endpoint is a major target for the development of alternative approaches for screening and prediction. The majority of old-aged expert systems and quantitative structure-activity relationship (QSAR) models may show reduced performance over time for their application on newer chemical candidates; thus, researchers constantly try to improve the modeling strategies. In our report, we initially performed traditional classification-based linear discriminant analysis (LDA) QSAR modeling using the benchmark Ames dataset of diverse chemicals (6512 compounds) to recognize the relationship between the molecules and their potential mutagenic behavior. The classical LDA QSAR model is developed from a selected set of 2D descriptors. The LDA QSAR model was developed by using a total of 31 descriptors identified from the analysis of the most discriminating features. Additionally, we have used similarity-derived features obtained from the read-across (RA) to develop an RA-based QSAR model. The developed RA-based LDA QSAR model has better predictivity, transferability, and interpretability compared to the LDA QSAR model, and it uses a very small number of descriptors compared to the classical QSAR model. Different machine learning (ML) models were also developed using the descriptors appearing in the read-across-based LDA QSAR model for comparative studies. We have checked the prediction quality of 216 true external set compounds using the novel similarity-derived RA model. The performance of the OECD toolbox is also compared with the RA-derived LDA QSAR model for a true external set. The current study aimed to explore the significance of the read-across-based algorithm and its application to the most current experimental mutagenicity data to complement already available expert systems.

Comparing the performance and coverage of selected in silico (liver) metabolism tools relative to reported studies in the literature to inform analogue selection in read-across: A case study.

Changes in the regulatory landscape of chemical safety assessment call for the use of New Approach Methodologies (NAMs) including read-across to fill data gaps. One critical aspect of analogue evaluation is the extent to which target and source analogues are metabolically similar. In this study, a set of 37 structurally diverse chemicals were compiled from the EPA ToxCast inventory to compare and contrast a selection of metabolism in silico tools, in terms of their coverage and performance relative to metabolism information reported in the literature. The aim was to build understanding of the scope and capabilities of these tools and how they could be utilised in a read-across assessment. The tools were Systematic Generation of Metabolites (SyGMa), Meteor Nexus, BioTransformer, Tissue Metabolism Simulator (TIMES), OECD Toolbox, and Chemical Transformation Simulator (CTS). Performance was characterised by sensitivity and precision determined by comparing predictions against literature reported metabolites (from 44 publications). A coverage score was derived to provide a relative quantitative comparison between the tools. Meteor, TIMES, Toolbox, and CTS predictions were run in batch mode, using default settings. SyGMa and BioTransformer were run with user-defined settings, (two passes of phase I and one pass of phase II). Hierarchical clustering revealed high similarity between TIMES and Toolbox. SyGMa had the highest coverage, matching an average of 38.63% of predictions generated by the other tools though was prone to significant overprediction. It generated 5,125 metabolites, which represented 54.67% of all predictions. Precision and sensitivity values ranged from 1.1-29% and 14.7-28.3% respectively. The Toolbox had the highest performance overall. A case study was presented for 3,4-Toluenediamine (3,4-TDA), assessed for the derivation of screening-level Provisional Peer Reviewed Toxicity Values (PPRTVs), was used to demonstrate the practical role in silico metabolism information can play in analogue evaluation as part of a read-across approach.

Integrated approach to testing and assessment for predicting rodent genotoxic carcinogenicity.

We investigated the performance of an integrated approach to testing and assessment (IATA), designed to cover different genotoxic mechanisms causing cancer and to replicate measured carcinogenicity data included in a new consolidated database. Genotoxic carcinogenicity was predicted based on positive results from at least two genotoxicity tests: one in vitro and one in vivo (which were associated with mutagenicity categories according to the Globally Harmonized System classification). Substances belonging to double positives mutagenicity categories were assigned to be genotoxic carcinogens. In turn, substances that were positive only in a single mutagenicity test were assigned to be mutagens. Chemicals not classified by the selected genotoxicity endpoints were assigned to be negative genotoxic carcinogens and subsequently evaluated for their capability to elicit non-genotoxic carcinogenicity. However, non-genotoxic carcinogenicity mechanisms were not currently included in the developed IATA. The IATA is docked to the OECD Toolbox and uses measured data for different genotoxicity endpoints when available. Alternatively, the system automatically provides predictions by SAR genotoxicity models using the OASIS Tissue Metabolism Simulator platform. When the developed IATA was tested against the consolidated database, its performance was found to be high, with sensitivity of 74% and specificity of 83%, when measured carcinogenicity data were used along with predictions falling within the models' applicability domains. Performance of the IATA would be slightly changed to a sensitivity of 80% and specificity of 72% when the evaluation by non-genotoxic carcinogenicity mechanisms was taken into account. Copyright © 2016 John Wiley & Sons, Ltd.

Computer models versus reality: how well do in silico models currently predict the sensitization potential of a substance.

National legislations for the assessment of the skin sensitization potential of chemicals are increasingly based on the globally harmonized system (GHS). In this study, experimental data on 55 non-sensitizing and 45 sensitizing chemicals were evaluated according to GHS criteria and used to test the performance of computer (in silico) models for the prediction of skin sensitization. Statistic models (Vega, Case Ultra, TOPKAT), mechanistic models (Toxtree, OECD (Q)SAR toolbox, DEREK) or a hybrid model (TIMES-SS) were evaluated. Between three and nine of the substances evaluated were found in the individual training sets of various models. Mechanism based models performed better than statistical models and gave better predictivities depending on the stringency of the domain definition. Best performance was achieved by TIMES-SS, with a perfect prediction, whereby only 16% of the substances were within its reliability domain. Some models offer modules for potency; however predictions did not correlate well with the GHS sensitization subcategory derived from the experimental data. In conclusion, although mechanistic models can be used to a certain degree under well-defined conditions, at the present, the in silico models are not sufficiently accurate for broad application to predict skin sensitization potentials.