Are Mechanistic and Statistical QSAR Approaches Really Different? MLR Studies on 158 Cycloalkyl-Pyranones

Current approaches for choosing feature selection and learning algorithms in quantitative structure-activity relationships (QSAR)

INTRODUCTION

Quantitative structure-activity/property relationships (QSAR/QSPR) are statistical models which quantitatively correlate quantitative chemical structure information (described as molecular descriptors) to the response end points (biological activity, property, toxicity, etc.). Important strategies for QSAR model development and validation include dataset curation, variable selection, and dataset division, selection of modeling algorithms and appropriate measures of model validation. Areas covered: Different feature selection methods and various linear and nonlinear learning algorithms are employed to address the complexity of data sets for selection of appropriate features important for the responses being modeled, to reduce overfitting of the models, and to derive interpretable models. This review provides an overview of various feature selection methods as well as different statistical learning algorithms for QSAR modeling at an elementary level for nonexpert readers. Expert opinion: Novel sets of descriptors are being continuously introduced to this field; therefore, to handle this issue, there is a need to improve new tools for feature selection, which can lead to development of statistically meaningful models, usable by nonexperts in the fields. While handling data sets of limited size, special techniques like double cross-validation and consensus modeling might be more meaningful in order to remove the possibility of bias in descriptor selection.

Mind the Gap! A Journey towards Computational Toxicology

Computational methods have advanced toxicology towards the development of target-specific models based on a clear cause-effect rationale. However, the predictive potential of these models presents strengths and weaknesses. On the good side, in silico models are valuable cheap alternatives to in vitro and in vivo experiments. On the other, the unconscious use of in silico methods can mislead end-users with elusive results. The focus of this review is on the basic scientific and regulatory recommendations in the derivation and application of computational models. Attention is paid to examine the interplay between computational toxicology and drug discovery and development. Avoiding the easy temptation of an overoptimistic future, we report our view on what can, or cannot, realistically be done. Indeed, studies of safety/toxicity represent a key element of chemical prioritization programs carried out by chemical industries, and primarily by pharmaceutical companies.

Predictive QSAR modelling of algal toxicity of ionic liquids and its interspecies correlation with Daphnia toxicity

Predictive toxicology using chemometric tools can be very useful in order to fill the data gaps for ionic liquids (ILs) with limited available experimental toxicity information, in view of their growing industrial uses. Though originally promoted as green chemicals, ILs have now been shown to possess considerable toxicity against different ecological endpoints. Against this background, quantitative structure-activity relationship (QSAR) models have been developed here for the toxicity of ILs against the green algae Scenedesmus vacuolatus using computed descriptors with definite physicochemical meaning. The final models emerged from E-state indices, extended topochemical atom (ETA) indices and quantum topological molecular similarity (QTMS) indices. The developed partial least squares models support the established mechanism of toxicity of ionic liquids in terms of a surfactant action of cations and chaotropic action of anions. The models have been developed within the guidelines of the Organization of Economic Co-operation and Development (OECD) for regulatory QSAR models, and they have been validated both internally and externally using multiple strategies and also tested for applicability domain. A preliminary attempt has also been made, for the first time, to develop interspecies quantitative toxicity-toxicity relationship (QTTR) models for the algal toxicity of ILs with Daphnia toxicity, which should be interesting while predicting toxicity of ILs for an endpoint when the data for the other are available.

Optimal descriptor as a translator of eclectic data into prediction of cytotoxicity for metal oxide nanoparticles under different conditions

The Monte Carlo technique has been used to build up quantitative structure-activity relationships (QSARs) for prediction of dark cytotoxicity and photo-induced cytotoxicity of metal oxide nanoparticles to bacteria Escherichia coli (minus logarithm of lethal concentration for 50% bacteria pLC50, LC50 in mol/L). The representation of nanoparticles include (i) in the case of the dark cytotoxicity a simplified molecular input-line entry system (SMILES), and (ii) in the case of photo-induced cytotoxicity a SMILES plus symbol '^'. The predictability of the approach is checked up with six random distributions of available data into the visible training and calibration sets, and invisible validation set. The statistical characteristics of these models are correlation coefficient 0.90-0.94 (training set) and 0.73-0.98 (validation set).

QSAR Modeling is not "Push a Button and Find a Correlation": A Case Study of Toxicity of (Benzo-)triazoles on Algae

A case study of toxicity of (benzo)triazoles ((B)TAZs) to the algae Pseudokirchneriella subcapitata is used to discuss some problems and solutions in QSAR modeling, particularly in the environmental context. The relevance of data curation (not only of experimental data, but also of chemical structures and input formats for the calculation of molecular descriptors), the crucial points of QSAR model validation and the potential application for new chemicals (internal robustness, exclusion of chance correlation, external predictivity, applicability domain) are described, while developing MLR-OLS models based on molecular descriptors, calculated by various QSAR software tools (commercial DRAGON, free PaDEL-Descriptor and QSPR-THESAURUS). Additionally, the utility of consensus models is highlighted. This work summarizes a methodology for a rigorous statistical approach to obtain reliable QSAR predictions, also for a large number of (B)TAZs in the ECHA preregistration list of REACH (even if starting from limited experimental data availability), and has evidenced some ambiguities and discrepancies related to SMILES notations from different databases; furthermore it highlighted some general problems related to QSAR model generation and was useful in the implementation of the PaDEL-Descriptor software.

Novel application of the CORAL software to model cytotoxicity of metal oxide nanoparticles to bacteria Escherichia coli

Convenient to apply and available on the Internet software CORAL (http://www.insilico.eu/CORAL) has been used to build up quantitative structure-activity relationships (QSAR) for prediction of cytotoxicity of metal oxide nanoparticles to bacteria Escherichia coli (minus logarithm of concentration for 50% effect pEC50). In this study six random splits of the data into the training and test set were examined. It has been shown that the CORAL provides a reliable tool that could be used to build up a QSAR of the pEC50.

Real external predictivity of QSAR models: how to evaluate it? Comparison of different validation criteria and proposal of using the concordance correlation coefficient

The main utility of QSAR models is their ability to predict activities/properties for new chemicals, and this external prediction ability is evaluated by means of various validation criteria. As a measure for such evaluation the OECD guidelines have proposed the predictive squared correlation coefficient Q(2)(F1) (Shi et al.). However, other validation criteria have been proposed by other authors: the Golbraikh-Tropsha method, r(2)(m) (Roy), Q(2)(F2) (Schüürmann et al.), Q(2)(F3) (Consonni et al.). In QSAR studies these measures are usually in accordance, though this is not always the case, thus doubts can arise when contradictory results are obtained. It is likely that none of the aforementioned criteria is the best in every situation, so a comparative study using simulated data sets is proposed here, using threshold values suggested by the proponents or those widely used in QSAR modeling. In addition, a different and simple external validation measure, the concordance correlation coefficient (CCC), is proposed and compared with other criteria. Huge data sets were used to study the general behavior of validation measures, and the concordance correlation coefficient was shown to be the most restrictive. On using simulated data sets of a more realistic size, it was found that CCC was broadly in agreement, about 96% of the time, with other validation measures in accepting models as predictive, and in almost all the examples it was the most precautionary. The proposed concordance correlation coefficient also works well on real data sets, where it seems to be more stable, and helps in making decisions when the validation measures are in conflict. Since it is conceptually simple, and given its stability and restrictiveness, we propose the concordance correlation coefficient as a complementary, or alternative, more prudent measure of a QSAR model to be externally predictive.