Additive SMILES-based optimal descriptors in QSAR modelling bee toxicity: Using rare SMILES attributes to define the applicability domain

The VEGA Tool to Check the Applicability Domain Gives Greater Confidence in the Prediction of In Silico Models

A sound assessment of in silico models and their applicability domain can support the use of new approach methodologies (NAMs) in chemical risk assessment and requires increasing the users' confidence in this approach. Several approaches have been proposed to evaluate the applicability domain of such models, but their prediction power still needs a thorough assessment. In this context, the VEGA tool capable of assessing the applicability domain of in silico models is examined for a range of toxicological endpoints. The VEGA tool evaluates chemical structures and other features related to the predicted endpoints and is efficient in measuring applicability domain, enabling the user to identify less accurate predictions. This is demonstrated with many models addressing different endpoints, towards toxicity of relevance to human health, ecotoxicological endpoints, environmental fate, physicochemical and toxicokinetic properties, for both regression models and classifiers.

Unswerving modeling of hepatotoxicity of cadmium containing quantum dots using amalgamation of quasiSMILES, index of ideality of correlation, and consensus modeling

Liver toxicity of quantum dots varies with size, concentration, and other structural as well as experimental parameters. For modeling hepatotoxicity, the eclectic data associated with cadmium containing quantum dots have been used in the creation of quasiSMILES for their representation. The core diameter is normalized for wider applicability and the index of the ideality of correlation is applied to construct the better quantitative features toxicity relationship models. Total eight splits are created and the best model is obtained through split 1 with better prediction criteria of validation set objects. The values of all statistical criteria used in the quality determination of a QSAR model are within the specified range for all the eight toxicity models developed here. Factors like TGA ligand and 0.6-0.7 nm diameter are favorable for liver toxicity while L-cysteine ligand and 0.5-0.6 nm core diameter are helpful in the reduction of toxicity. Further, the intelligent consensus modeling process forms a total of 40 individual and 20 consensus models and the best individual and consensus models are 'Good' in MAE-based criteria. The consensus modeling enhances the prediction ability as well as the accuracy of the developed models and increases the applicability space of the built models for hepatotoxicity prediction of quantum dots.

Prediction of Biochemical Endpoints by the CORAL Software: Prejudices, Paradoxes, and Results

Quantitative structure-activity relationships (QSARs) for prediction of toxicological endpoints built up with the CORAL software are discussed. Prejudices related to these QSAR models are listed. Possible ways to improve the software are discussed.

In silico toxicology: computational methods for the prediction of chemical toxicity

Determining the toxicity of chemicals is necessary to identify their harmful effects on humans, animals, plants, or the environment. It is also one of the main steps in drug design. Animal models have been used for a long time for toxicity testing. However, in vivo animal tests are constrained by time, ethical considerations, and financial burden. Therefore, computational methods for estimating the toxicity of chemicals are considered useful. In silico toxicology is one type of toxicity assessment that uses computational methods to analyze, simulate, visualize, or predict the toxicity of chemicals. In silico toxicology aims to complement existing toxicity tests to predict toxicity, prioritize chemicals, guide toxicity tests, and minimize late-stage failures in drugs design. There are various methods for generating models to predict toxicity endpoints. We provide a comprehensive overview, explain, and compare the strengths and weaknesses of the existing modeling methods and algorithms for toxicity prediction with a particular (but not exclusive) emphasis on computational tools that can implement these methods and refer to expert systems that deploy the prediction models. Finally, we briefly review a number of new research directions in in silico toxicology and provide recommendations for designing in silico models. WIREs Comput Mol Sci 2016, 6:147-172. doi: 10.1002/wcms.1240 For further resources related to this article, please visit the WIREs website.

Amino substituted nitrogen heterocycle ureas as kinase insert domain containing receptor (KDR) inhibitors: Performance of structure–activity relationship approaches

A quantitative structure–activity relationship (QSAR) study was performed on a set of amino-substituted nitrogen heterocyclic urea derivatives. Two novel approaches were applied: (1) the simplified molecular input-line entry systems (SMILES) based optimal descriptors approach; and (2) the fragment-based simplex representation of molecular structure (SiRMS) approach. Comparison with the classic scheme of building up the model and balance of correlation (BC) for optimal descriptors approach shows that the BC scheme provides more robust predictions than the classic scheme for the considered pIC₅₀ of the heterocyclic urea derivatives. Comparison of the SMILES-based optimal descriptors and SiRMS approaches has confirmed good performance of both techniques in prediction of kinase insert domain containing receptor (KDR) inhibitory activity, expressed as a logarithm of inhibitory concentration (pIC50) of studied compounds.

Monte Carlo QSAR models for predicting organophosphate inhibition of acetycholinesterase

A series of 278 organophosphate compounds acting as acetylcholinesterase inhibitors has been studied. The Monte Carlo method was used as a tool for building up one-variable quantitative structure-activity relationship (QSAR) models for acetylcholinesterase inhibition activity based on the principle that the target endpoint is treated as a random event. As an activity, bimolecular rate constants were used. The QSAR models were based on optimal descriptors obtained from Simplified Molecular Input-Line Entry System (SMILES) used for the representation of molecular structure. Two modelling approaches were examined: (1) 'classic' training-test system where the QSAR model was built with one random split into a training, test and validation set; and (2) the correlation balance based QSAR models were built with two random splits into a sub-training, calibration, test and validation set. The DModX method was used for defining the applicability domain. The obtained results suggest that studied activity can be determined with the application of QSAR models calculated with the Monte Carlo method since the statistical quality of all build models was very good. Finally, structural indicators for the increase and the decrease of the bimolecular rate constant are defined. The possibility of using these results for the computer-aided design of new organophosphate compounds is presented.

A Combinational Strategy of Model Disturbance and Outlier Comparison to Define Applicability Domain in Quantitative Structural Activity Relationship

In order to define an applicability domain for quantitative structure-activity relationship modeling, a combinational strategy of model disturbance and outlier comparison is developed. An indicator named model disturbance index was defined to estimate the prediction error. Moreover, the information of the outliers in the training set was used to filter the unreliable samples in the test set based on "structural similarity". Chromatography retention indices data were used to investigate this approach. The relationship between model disturbance index and prediction error can be found. Also, the comparison between the outlier set and the test set could provide additional information about which unknown samples should be paid more attentions. A novel technique based on model population analysis was used to evaluate the validity of applicability domain. Finally, three commonly used methods, i.e. Leverage, descriptor range-based and model perturbation method, were compared with the proposed approach.

QSAR study and molecular design of open-chain enaminones as anticonvulsant agents

Present work employs the QSAR formalism to predict the ED₅₀ anticonvulsant activity of ringed-enaminones, in order to apply these relationships for the prediction of unknown open-chain compounds containing the same types of functional groups in their molecular structure. Two different modeling approaches are applied with the purpose of comparing the consistency of our results: (a) the search of molecular descriptors via multivariable linear regressions; and (b) the calculation of flexible descriptors with the CORAL (CORrelation And Logic) program. Among the results found, we propose some potent candidate open-chain enaminones having ED₅₀ values lower than 10 mg·kg⁻¹ for corresponding pharmacological studies. These compounds are classified as Class 1 and Class 2 according to the Anticonvulsant Selection Project.

A comparative QSAR on 1,2,5-thiadiazolidin-3-one 1,1-dioxide compounds as selective inhibitors of human serine proteinases

Selective inhibitors of target serine proteinases have a potential therapeutic role for the treatment of various inflammatory and related diseases. We develop a comparative quantitative structure-activity relationships based analysis on compounds embodying the 1,2,5-thiadiazolidin-3-one 1,1-dioxide scaffold. By means of classical Molecular Dynamics we obtain the conformation of each lowest-energy molecular structure from which we derive more than a thousand of structural descriptors necessary for building predictive QSAR models. We resort to two different modeling approaches with the purpose of testing the consistency of our results: (a) multivariable linear regressions based on the replacement method and forward stepwise regression, and (b) the calculation of flexible descriptors with the CORAL program. All the models are properly validated by means of standard procedures. The resulting QSAR models are supposed to be of great utility for the rational search and design (including synthesis and/or in vitro biochemical studies) of new effective non-peptidyl inhibitors of serine proteinases.

CORAL: QSPR models for solubility of [C60] and [C70] fullerene derivatives

Quantitative structure-property relationships (QSPRs) between the molecular structure of [C(60)] and [C(70)] fullerene derivatives and their solubility in chlorobenzene (mg/mL) have been established by means of CORAL (CORrelations And Logic) freeware. The CORAL models are based on representation of the molecular structure by simplified molecular input line entry system (SMILES). Three random splits into the training and the external validation sets have been examined. The ranges of statistical characteristics of these models are as follows: n = 18, r (2) = 0.748-0.815, s = 15.1 -17.5 (mg/mL), F = 47-71 (training set); n = 9, r (2) = 0.806-0.936, s = 12.5-17.5 (mg/mL), F = 29-103 (validation set).

Estimation of the applicability domain of kernel-based machine learning models for virtual screening

BACKGROUND

The virtual screening of large compound databases is an important application of structural-activity relationship models. Due to the high structural diversity of these data sets, it is impossible for machine learning based QSAR models, which rely on a specific training set, to give reliable results for all compounds. Thus, it is important to consider the subset of the chemical space in which the model is applicable. The approaches to this problem that have been published so far mostly use vectorial descriptor representations to define this domain of applicability of the model. Unfortunately, these cannot be extended easily to structured kernel-based machine learning models. For this reason, we propose three approaches to estimate the domain of applicability of a kernel-based QSAR model.

RESULTS

We evaluated three kernel-based applicability domain estimations using three different structured kernels on three virtual screening tasks. Each experiment consisted of the training of a kernel-based QSAR model using support vector regression and the ranking of a disjoint screening data set according to the predicted activity. For each prediction, the applicability of the model for the respective compound is quantitatively described using a score obtained by an applicability domain formulation. The suitability of the applicability domain estimation is evaluated by comparing the model performance on the subsets of the screening data sets obtained by different thresholds for the applicability scores. This comparison indicates that it is possible to separate the part of the chemspace, in which the model gives reliable predictions, from the part consisting of structures too dissimilar to the training set to apply the model successfully. A closer inspection reveals that the virtual screening performance of the model is considerably improved if half of the molecules, those with the lowest applicability scores, are omitted from the screening.

CONCLUSION

The proposed applicability domain formulations for kernel-based QSAR models can successfully identify compounds for which no reliable predictions can be expected from the model. The resulting reduction of the search space and the elimination of some of the active compounds should not be considered as a drawback, because the results indicate that, in most cases, these omitted ligands would not be found by the model anyway.

QSTR with extended topochemical atom (ETA) indices. 12. QSAR for the toxicity of diverse aromatic compounds to Tetrahymena pyriformis using chemometric tools

We have developed QSTR models for the toxicity of 384 diverse aromatic compounds to Tetrahymena pyriformis with recently introduced extended topochemical atom (ETA) indices and compared the ETA models with those derived from various non-ETA topological descriptors and also combined set of descriptors encompassing the ETA and non-ETA parameters. The data set was split into test (25% compounds of total data points) and training (remaining 75%) sets based on K-mean clustering technique. Different statistical analyses (factor analysis followed by multiple linear regression (FA-MLR), stepwise regression and partial least squares (PLS)) were performed with the training set compounds to develop QSTR models using the topological descriptors. All the developed models were cross-validated using leave-one-out (LOO) technique. The best models were selected on the basis of predicted R(2) values for test set compounds. The best models (based on external validation) developed from different techniques came from the combined set of descriptors. The above results indicate that the use of ETA descriptors with non-ETA descriptors improved the statistical quality of the non-ETA models. From the best models involving ETA parameters, it is observed that functionality of halogen atoms (hydrophobicity), volume parameter (bulk) and nitrogen containing functionalities (polarity) are important for developing QSTR models for the current data set. This study suggests that ETA parameters are sufficient power to encode chemical information contributing significantly to the toxicity of diverse aromatic compounds to T. pyriformis.

Additive SMILES-based carcinogenicity models: Probabilistic principles in the search for robust predictions

Optimal descriptors calculated with the simplified molecular input line entry system (SMILES) have been utilized in modeling of carcinogenicity as continuous values (logTD₅₀). These descriptors can be calculated using correlation weights of SMILES attributes calculated by the Monte Carlo method. A considerable subset of these attributes includes rare attributes. The use of these rare attributes can lead to overtraining. One can avoid the influence of the rare attributes if their correlation weights are fixed to zero. A function, limS, has been defined to identify rare attributes. The limS defines the minimum number of occurrences in the set of structures of the training (subtraining) set, to accept attributes as usable. If an attribute is present less than limS, it is considered “rare”, and thus not used. Two systems of building up models were examined: 1. classic training-test system; 2. balance of correlations for the subtraining and calibration sets (together, they are the original training set: the function of the calibration set is imitation of a preliminary test set). Three random splits into subtraining, calibration, and test sets were analysed. Comparison of abovementioned systems has shown that balance of correlations gives more robust prediction of the carcinogenicity for all three splits (split 1: r_test²=0.7514, s_test=0.684; split 2: r_test²=0.7998, s_test=0.600; split 3: r_test²=0.7192, s_test=0.728).

Nanomaterials – the Next Great Challenge for Qsar Modelers

In this final chapter a new perspective for the application of QSAR in the nanosciences is discussed. The role of nanomaterials is rapidly increasing in many aspects of everyday life. This is promoting a wide range of research needs related to both the design of new materials with required properties and performing a comprehensive risk assessment of the manufactured nanoparticles. The development of nanoscience also opens new areas for QSAR modelers. We have begun this contribution with a detailed discussion on the remarkable physical–chemical properties of nanomaterials and their specific toxicities. Both these factors should be considered as potential endpoints for further nano-QSAR studies. Then, we have highlighted the status and research needs in the area of molecular descriptors applicable to nanomaterials. Finally, we have put together currently available nano-QSAR models related to the physico-chemical endpoints of nanoparticles and their activity. Although we have observed many problems (i.e., a lack of experimental data, insufficient and inadequate descriptors), we do believe that application of QSAR methodology will significantly support nanoscience in the near future. Development of reliable nano-QSARs can be considered as the next challenging task for the QSAR community.