Modeling and insights into the structural characteristics of endocrine-disrupting chemicals

Endocrine-disrupting chemicals (EDCs) can cause serious harm to human health and the environment; therefore, it is important to rapidly and correctly identify EDCs. Different computational models have been proposed for the prediction of EDCs over the past few decades, but the reported models are not always easily available, and few studies have investigated the structural characteristics of EDCs. In the present study, we have developed a series of artificial intelligence models targeting EDC receptors: the androgen receptor (AR); estrogen receptor (ER); and pregnane X receptor (PXR). The consensus models achieved good predictive results for validation sets with balanced accuracy values of 87.37%, 90.13%, and 79.21% for AR, ER, and PXR binding assays, respectively. Analysis of the physical-chemical properties suggested that several chemical properties were significantly (p < 0.05) different between EDCs and non-EDCs. We also identified structural alerts that can indicate an EDC, which were integrated into the web server SApredictor. These models and structural characteristics can provide useful tools and information in the discrimination and mechanistic understanding of EDCs in drug discovery and environmental risk assessment.

Machine Learning Methods in Computational Toxicology

Various methods of machine learning, supervised and unsupervised, linear and nonlinear, classification and regression, in combination with various types of molecular descriptors, both "handcrafted" and "data-driven," are considered in the context of their use in computational toxicology. The use of multiple linear regression, variants of naïve Bayes classifier, k-nearest neighbors, support vector machine, decision trees, ensemble learning, random forest, several types of neural networks, and deep learning is the focus of attention of this review. The role of fragment descriptors, graph mining, and graph kernels is highlighted. The application of unsupervised methods, such as Kohonen's self-organizing maps and related approaches, which allow for combining predictions with data analysis and visualization, is also considered. The necessity of applying a wide range of machine learning methods in computational toxicology is underlined.

Modeling of the hERG K+ Channel Blockage Using Online Chemical Database and Modeling Environment (OCHEM)

Human ether-a-go-go related gene (hERG) K+ channel plays an important role in cardiac action potential. Blockage of hERG channel may result in long QT syndrome (LQTS), even cause sudden cardiac death. Many drugs have been withdrawn from the market because of the serious hERG-related cardiotoxicity. Therefore, it is quite essential to estimate the chemical blockage of hERG in the early stage of drug discovery. In this study, a diverse set of 3721 compounds with hERG inhibition data was assembled from literature. Then, we make full use of the Online Chemical Modeling Environment (OCHEM), which supplies rich machine learning methods and descriptor sets, to build a series of classification models for hERG blockage. We also generated two consensus models based on the top-performing individual models. The consensus models performed much better than the individual models both on 5-fold cross validation and external validation. Especially, consensus model II yielded the prediction accuracy of 89.5 % and MCC of 0.670 on external validation. This result indicated that the predictive power of consensus model II should be stronger than most of the previously reported models. The 17 top-performing individual models and the consensus models and the data sets used for model development are available at https://ochem.eu/article/103592.

Public (Q)SAR Services, Integrated Modeling Environments, and Model Repositories on the Web: State of the Art and Perspectives for Future Development

Thousands of (Quantitative) Structure-Activity Relationships (Q)SAR models have been described in peer-reviewed publications; however, this way of sharing seldom makes models available for the use by the research community outside of the developer's laboratory. Conversely, on-line models allow broad dissemination and application representing the most effective way of sharing the scientific knowledge. Approaches for sharing and providing on-line access to models range from web services created by individual users and laboratories to integrated modeling environments and model repositories. This emerging transition from the descriptive and informative, but "static", and for the most part, non-executable print format to interactive, transparent and functional delivery of "living" models is expected to have a transformative effect on modern experimental research in areas of scientific and regulatory use of (Q)SAR models.

Prediction of logP for Pt(II) and Pt(IV) complexes: Comparison of statistical and quantum-chemistry based approaches

The octanol/water partition coefficient, logP, is one of the most important physico-chemical parameters for the development of new metal-based anticancer drugs with improved pharmacokinetic properties. This study addresses an issue with the absence of publicly available models to predict logP of Pt(IV) complexes. Following data collection and subsequent development of models based on 187 complexes from literature, we validate new and previously published models on a new set of 11 Pt(II) and 35 Pt(IV) complexes, which were kept blind during the model development step. The error of the consensus model, 0.65 for Pt(IV) and 0.37 for Pt(II) complexes, indicates its good accuracy of predictions. The lower accuracy for Pt(IV) complexes was attributed to experimental difficulties with logP measurements for some poorly-soluble compounds. This model was developed using general-purpose descriptors such as extended functional groups, molecular fragments and E-state indices. Surprisingly, models based on quantum-chemistry calculations provided lower prediction accuracy. We also found that all the developed models strongly overestimate logP values for the three complexes measured in the presence of DMSO. Considering that DMSO is frequently used as a solvent to store chemicals, its effect should not be overlooked when logP measurements by means of the shake flask method are performed. The final models are freely available at http://ochem.eu/article/76903.

Modeling the Biodegradability of Chemical Compounds Using the Online CHEmical Modeling Environment (OCHEM)

Biodegradability describes the capacity of substances to be mineralized by free‐living bacteria. It is a crucial property in estimating a compound’s long‐term impact on the environment. The ability to reliably predict biodegradability would reduce the need for laborious experimental testing. However, this endpoint is difficult to model due to unavailability or inconsistency of experimental data. Our approach makes use of the Online Chemical Modeling Environment (OCHEM) and its rich supply of machine learning methods and descriptor sets to build classification models for ready biodegradability. These models were analyzed to determine the relationship between characteristic structural properties and biodegradation activity. The distinguishing feature of the developed models is their ability to estimate the accuracy of prediction for each individual compound. The models developed using seven individual descriptor sets were combined in a consensus model, which provided the highest accuracy. The identified overrepresented structural fragments can be used by chemists to improve the biodegradability of new chemical compounds. The consensus model, the datasets used, and the calculated structural fragments are publicly available at http://ochem.eu/article/31660.

Development of conformation independent computational models for the early recognition of breast cancer resistance protein substrates

ABC efflux transporters are polyspecific members of the ABC superfamily that, acting as drug and metabolite carriers, provide a biochemical barrier against drug penetration and contribute to detoxification. Their overexpression is linked to multidrug resistance issues in a diversity of diseases. Breast cancer resistance protein (BCRP) is the most expressed ABC efflux transporter throughout the intestine and the blood-brain barrier, limiting oral absorption and brain bioavailability of its substrates. Early recognition of BCRP substrates is thus essential to optimize oral drug absorption, design of novel therapeutics for central nervous system conditions, and overcome BCRP-mediated cross-resistance issues. We present the development of an ensemble of ligand-based machine learning algorithms for the early recognition of BCRP substrates, from a database of 262 substrates and nonsubstrates compiled from the literature. Such dataset was rationally partitioned into training and test sets by application of a 2-step clustering procedure. The models were developed through application of linear discriminant analysis to random subsamples of Dragon molecular descriptors. Simple data fusion and statistical comparison of partial areas under the curve of ROC curves were applied to obtain the best 2-model combination, which presented 82% and 74.5% of overall accuracy in the training and test set, respectively.

Development of dimethyl sulfoxide solubility models using 163,000 molecules: using a domain applicability metric to select more reliable predictions

The dimethyl sulfoxide (DMSO) solubility data from Enamine and two UCB pharma compound collections were analyzed using 8 different machine learning methods and 12 descriptor sets. The analyzed data sets were highly imbalanced with 1.7–5.8% nonsoluble compounds. The libraries’ enrichment by soluble molecules from the set of 10% of the most reliable predictions was used to compare prediction performances of the methods. The highest accuracies were calculated using a C4.5 decision classification tree, random forest, and associative neural networks. The performances of the methods developed were estimated on individual data sets and their combinations. The developed models provided on average a 2-fold decrease of the number of nonsoluble compounds amid all compounds predicted as soluble in DMSO. However, a 4–9-fold enrichment was observed if only 10% of the most reliable predictions were considered. The structural features influencing compounds to be soluble or nonsoluble in DMSO were also determined. The best models developed with the publicly available Enamine data set are freely available online at http://ochem.eu/article/33409.

The continuous molecular fields approach to building 3D-QSAR models

The continuous molecular fields (CMF) approach is based on the application of continuous functions for the description of molecular fields instead of finite sets of molecular descriptors (such as interaction energies computed at grid nodes) commonly used for this purpose. These functions can be encapsulated into kernels and combined with kernel-based machine learning algorithms to provide a variety of novel methods for building classification and regression structure-activity models, visualizing chemical datasets and conducting virtual screening. In this article, the CMF approach is applied to building 3D-QSAR models for 8 datasets through the use of five types of molecular fields (the electrostatic, steric, hydrophobic, hydrogen-bond acceptor and donor ones), the linear convolution molecular kernel with the contribution of each atom approximated with a single isotropic Gaussian function, and the kernel ridge regression data analysis technique. It is shown that the CMF approach even in this simplest form provides either comparable or enhanced predictive performance in comparison with state-of-the-art 3D-QSAR methods.

Combined QSAR studies of inhibitor properties of O-phosphorylated oximes toward serine esterases involved in neurotoxicity, drug metabolism and Alzheimer's disease

Oxime reactivation of serine esterases (EOHs) inhibited by organophosphorus (OP) compounds can produce O-phosphorylated oximes (POXs). Such oxime derivatives are of interest, because some of them can have greater anti-EOH potencies than the OP inhibitors from which they were derived. Accordingly, inhibitor properties of 58 POXs against four EOHs, along with pair-wise selectivities between them, have been analysed using different QSAR approaches. EOHs (with their abbreviations and consequences of inhibition in parentheses) comprised acetylcholinesterase (AChE: acute neurotoxicity; cognition enhancement), butyrylcholinesterase (BChE: inhibition of drug metabolism or stoichiometric scavenging of EOH inhibitors; cognition enhancement), carboxylesterase (CaE: inhibition of drug metabolism or stoichiometric scavenging of EOH inhibitors), and neuropathy target esterase (NTE: delayed neurotoxicity). QSAR techniques encompassed linear regression and backpropagation neural networks in conjunction with fragmental descriptors containing labelled atoms, Molecular Field Topology Analysis (MFTA), Comparative Molecular Similarity Index Analysis (CoMSIA), and molecular modelling. All methods provided mostly consistent and complementary information, and they revealed structural features controlling the 'esterase profiles', i.e. patterns of anti-EOH activities and selectivities of the compounds of interest. In addition, MFTA models were used to design a library of compounds having a cognition-enhancement esterase profile suitable for potential application to the treatment of Alzheimer's disease.

Machine learning methods for property prediction in chemoinformatics: Quo Vadis?

This paper is focused on modern approaches to machine learning, most of which are as yet used infrequently or not at all in chemoinformatics. Machine learning methods are characterized in terms of the "modes of statistical inference" and "modeling levels" nomenclature and by considering different facets of the modeling with respect to input/ouput matching, data types, models duality, and models inference. Particular attention is paid to new approaches and concepts that may provide efficient solutions of common problems in chemoinformatics: improvement of predictive performance of structure-property (activity) models, generation of structures possessing desirable properties, model applicability domain, modeling of properties with functional endpoints (e.g., phase diagrams and dose-response curves), and accounting for multiple molecular species (e.g., conformers or tautomers).

Online chemical modeling environment (OCHEM): web platform for data storage, model development and publishing of chemical information

The Online Chemical Modeling Environment is a web-based platform that aims to automate and simplify the typical steps required for QSAR modeling. The platform consists of two major subsystems: the database of experimental measurements and the modeling framework. A user-contributed database contains a set of tools for easy input, search and modification of thousands of records. The OCHEM database is based on the wiki principle and focuses primarily on the quality and verifiability of the data. The database is tightly integrated with the modeling framework, which supports all the steps required to create a predictive model: data search, calculation and selection of a vast variety of molecular descriptors, application of machine learning methods, validation, analysis of the model and assessment of the applicability domain. As compared to other similar systems, OCHEM is not intended to re-implement the existing tools or models but rather to invite the original authors to contribute their results, make them publicly available, share them with other users and to become members of the growing research community. Our intention is to make OCHEM a widely used platform to perform the QSPR/QSAR studies online and share it with other users on the Web. The ultimate goal of OCHEM is collecting all possible chemoinformatics tools within one simple, reliable and user-friendly resource. The OCHEM is free for web users and it is available online at http://www.ochem.eu.

Recent advances in fragment-based QSAR and multi-dimensional QSAR methods

This paper provides an overview of recently developed two dimensional (2D) fragment-based QSAR methods as well as other multi-dimensional approaches. In particular, we present recent fragment-based QSAR methods such as fragment-similarity-based QSAR (FS-QSAR), fragment-based QSAR (FB-QSAR), Hologram QSAR (HQSAR), and top priority fragment QSAR in addition to 3D- and nD-QSAR methods such as comparative molecular field analysis (CoMFA), comparative molecular similarity analysis (CoMSIA), Topomer CoMFA, self-organizing molecular field analysis (SOMFA), comparative molecular moment analysis (COMMA), autocorrelation of molecular surfaces properties (AMSP), weighted holistic invariant molecular (WHIM) descriptor-based QSAR (WHIM), grid-independent descriptors (GRIND)-based QSAR, 4D-QSAR, 5D-QSAR and 6D-QSAR methods.