MaNGA: a novel multi-niche multi-objective genetic algorithm for QSAR modelling.

SUMMARY: Quantitative structure-activity relationship (QSAR) modelling is currently used in multiple fields to relate structural properties of compounds to their biological activities. This technique is also used for drug design purposes with the aim of predicting parameters that determine drug behaviour. To this end, a sophisticated process, involving various analytical steps concatenated in series, is employed to identify and fine-tune the optimal set of predictors from a large dataset of molecular descriptors (MDs). The search of the optimal model requires to optimize multiple objectives at the same time, as the aim is to obtain the minimal set of features that maximizes the goodness of fit and the applicability domain (AD). Hence, a multi-objective optimization strategy, improving multiple parameters in parallel, can be applied. Here we propose a new multi-niche multi-objective genetic algorithm that simultaneously enables stable feature selection as well as obtaining robust and validated regression models with maximized AD. We benchmarked our method on two simulated datasets. Moreover, we analyzed an aquatic acute toxicity dataset and compared the performances of single- and multi-objective fitness functions on different regression models. Our results show that our multi-objective algorithm is a valid alternative to classical QSAR modelling strategy, for continuous response values, since it automatically finds the model with the best compromise between statistical robustness, predictive performance, widest AD, and the smallest number of MDs. AVAILABILITY AND IMPLEMENTATION: The python implementation of MaNGA is available at https://github.com/Greco-Lab/MaNGA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

An integrated quantitative structure and mechanism of action-activity relationship model of human serum albumin binding.

BACKGROUND: Traditional quantitative structure-activity relationship models usually neglect the molecular alterations happening in the exposed systems (the mechanism of action, MOA), that mediate between structural properties of compounds and phenotypic effects of an exposure. RESULTS: Here, we propose a computational strategy that integrates molecular descriptors and MOA information to better explain the mechanisms underlying biological endpoints of interest. By applying our methodology, we obtained a statistically robust and validated model to predict the binding affinity to human serum albumin. Our model is also able to provide new venues for the interpretation of the chemical-biological interactions. CONCLUSION: Our observations suggest that integrated quantitative models of structural and MOA-activity relationships are promising complementary tools in the arsenal of strategies aiming at developing new safe- and useful-by-design compounds.

Toxicity of contaminants of emerging concern to Dugesia japonica: QSTR modeling and toxicity relationship with Daphnia magna.

Freshwater planarian Dugesia japonica has a critical ecological importance owing to its unique properties. This study presents for the first time an in silico approach to determine a priori the acute toxicity of contaminants of emerging concern towards D. japonica. Quantitative structure-toxicity/toxicity-toxicity relationship (QSTR/QTTR) models provided here allow producing reliable information using the existing data, thus, reducing the demand of in vivo and in vitro experiments, and contributing to the need for a more holistic approach to environmental safety assessment. Both models are promising for being notably simple and robust, meeting rigorous validation metrics and the OECD criteria. The QTTR model based on the available Daphnia magna data might also contribute to the US EPA Interspecies Correlation Estimation web application. Moreover, the proposed models were applied on hundreds of environmentally significant chemicals lacking experimental D. japonica toxicity data and predicted toxicity values were reported for the first time. The models presented here can be used as potential tools in toxicity assessment, screening and prioritization of chemicals and development of risk management measures in a scientific and regulatory frame.

An in silico approach to cytotoxicity of pharmaceuticals and personal care products on the rainbow trout liver cell line RTL-W1.

The authors constructed novel, robust, and validated linear Quantitative Structure-Toxicity Relationship (QSTR) models in line with Organisation of Co-operation and Development (OECD) criteria using 2 cytotoxicity data sets which were obtained from the Alamar Blue and 5-carboxyfluorescein diacetate acetoxymethyl ester (CFDA-AM) assays. The data sets comprise the cytotoxic effect of structurally diverse and widely used pharmaceuticals, synthetic musks, and industrial chemicals on the rainbow trout (Oncorhynchus mykiss) liver cell line RTL-W1. Common descriptors defined the relationship between structure and cytotoxicity for both the Alamar Blue and the CFDA-AM assays which measure the metabolic activity and membrane integrity, respectively. Only the statistical parameters of the best Alamar Blue-based model were given (nTR = 13; R2 = 0.839; the root-mean-square error of the training set [RMSETR ] = 0.261; nTEST = 5; R2TEST = 0.903; RMSETEST = 0.181; CCCTEST = 0.939). The proposed QSTR model was able to predict the cytotoxicity of 101 diverse chemicals on the RTL-W1 cell line with 91% structural coverage. The authors found that in vitro-derived cytotoxicity data are promising predictors of in vivo fish toxicity and may provide an initial, rapid screening tool for acute fish toxicity assessment and reduce the need for extensive in vivo toxicity testing. Environ Toxicol Chem 2017;36:1162-1169. © 2016 SETAC.

An in silico algal toxicity model with a wide applicability potential for industrial chemicals and pharmaceuticals.

The authors modeled the 72-h algal toxicity data of hundreds of chemicals with different modes of action as a function of chemical structures. They developed mode of action-based local quantitative structure-toxicity relationship (QSTR) models for nonpolar and polar narcotics as well as a global QSTR model with a wide applicability potential for industrial chemicals and pharmaceuticals. The present study rigorously evaluated the generated models, meeting the Organisation for Economic Co-operation and Development principles of robustness, validity, and transparency. The proposed global model had a broad structural coverage for the toxicity prediction of diverse chemicals (some of which are high-production volume chemicals) with no experimental toxicity data. The global model is potentially useful for endpoint predictions, the evaluation of algal toxicity screening, and the prioritization of chemicals, as well as for the decision of further testing and the development of risk-management measures in a scientific and regulatory frame. Environ Toxicol Chem 2017;36:1012-1019. © 2016 SETAC.