QSPR Treatment of the Soil Sorption Coefficients of Organic Pollutants

Evaluation of a new series of pyrazole derivatives as a potent epidermal growth factor receptor inhibitory activity: QSAR modeling using quantum-chemical descriptors

Pyrazole derivatives correspond to a family of heterocycle molecules with important pharmacological and physiological applications. At present, we perform a density functional theory (DFT) calculations and a quantitative structure-activity relationship (QSAR) evaluation on a series of 1-(4,5-dihydro-1H-pyrazol-1-yl) ethan-1-one and 4,5-dihydro-1H-pyrazole-1-carbothioamide derivatives as an epidermal growth factor receptor (EGFR) inhibitory activity. We thus propose a virtual screening protocol based on a machine-learning study. This theoretical model relates the studied compounds' biological activity to their calculated physicochemical descriptors. Moreover, the linear regression function is used to validate the model via the evaluation of Q² _ext and Q² _cv parameters for external and internal validations, respectively. Our QSAR model shows a good correlation between observed activities IC₅₀ and predicted ones. Our model allows us to mitigate time-consuming problems and waste chemical and biological products in the preclinical phases.

Quantitative structure-property relationships for the calculation of the soil adsorption coefficient using machine learning algorithms with calculated chemical properties from open-source software

The soil adsorption coefficient (K_oc) is an environmental fate parameter that is essential for environmental risk assessment. However, obtaining K_oc requires a significant amount of time and enormous expenditure. Thus, it is necessary to efficiently estimate K_oc in the early stages of a chemical's development. In this study, a quantitative structure-property relationship (QSPR) model was developed using calculated physicochemical properties and molecular descriptors with the OPEn structure-activity/property Relationship App (OPERA) and Mordred software using the largest available K_oc dataset. Specifically, we compared the accuracies of the model using the light gradient boosted machine (LightGBM), a gradient boosting decision tree (GBDT) algorithm, with those of previous models. The experimental results suggested the potential to develop a QSPR model that will produce highly accurate K_oc values using molecular descriptors and physicochemical properties. Unlike previous studies, the use of a combination of LightGBM, OPERA and Mordred enables the prediction of K_oc for many chemicals with high accuracy. In this study, OPERA was used to calculate the physicochemical properties, and Mordred was used to calculate molecular descriptors. The wide range of chemicals covered by OPERA and Mordred enables the analysis of a diverse range of chemical compounds. We also report a method to tune the LightBGM program. The use of fast-processing software, such as LightGBM, enables parameter tuning of a method required to obtain best performance. Our research represents one of the few studies in the field of environmental chemistry to use LightGBM. Using physicochemical properties as well as molecular descriptors, we could develop highly accurate K_oc prediction models when compared to prior studies. In addition, our QSPR models may be useful for preliminary environmental risk assessment without incurring significant costs during the early chemical developmental stage.

Modelling of antiproliferative activity measured in HeLa cervical cancer cells in a series of xanthene derivatives

Cancer remains one of the leading causes of death in humans, and new drug substances are therefore being developed. Thus, the anti-cancer activity of xanthene derivatives has become an important topic in the development of new and potent anti-cancer drug substances. Previously published novel series of xanthen-3-one and xanthen-1,8-dione derivatives have been synthesized in one of our laboratories and showed anti-proliferative activity in HeLa cancer cell lines. This series serves as a good basis to develop quantitative structure-activity relationship (QSAR), to study the relations between anti-proliferative activity and chemical structures. A QSAR model has been derived that relies only on two-dimensional molecular descriptors, providing mechanistic insight into the anti-proliferative activity of xanthene derivatives. The model is validated internally and externally and additionally with the set of inactive compounds of the original data, confirming model applicability for the design and discovery of novel xanthene derivatives. The QSAR model is available at the QsarDB repository (http://dx.doi.10.15152/QDB.237).

Prediction of Soil Adsorption Coefficient in Pesticides Using Physicochemical Properties and Molecular Descriptors by Machine Learning Models

The soil adsorption coefficient (K_OC ) plays an important role in environmental risk assessment of pesticide registration. Based on this risk assessment, applied and registered pesticides can be allowed in the European Union. Almost 1 yr is required to study and obtain the K_OC value of a pesticide. Furthermore, acquiring the K_OC requires a large cost. It is necessary to efficiently estimate the K_OC value in the early stages of pesticide development. In the present study, the experimental values of physicochemical properties and molecular descriptors of chemical structures were collected to develop a quantitative structure-property relationship (QSPR) model, and the prediction performance of the model was evaluated. More specifically, we compared the accuracies of models based on a gradient boosting decision tree, multiple linear regression, and support vector machine. The experimental results suggest that it is possible to develop a QSPR model with high accuracy using both the molecular descriptors calculated from the structural formula and experimental values of physicochemical properties from open literature and databases. Comparing to the previously established models, we achieved high prediction accuracy, fitness, and robustness by only using freeware. Therefore, our developed QSPR models can be useful preliminary risk assessment in the early developmental stages of pesticides. Environ Toxicol Chem 2020;39:1451-1459. © 2020 SETAC.

Mechanistic studies of congener-specific adsorption and bioaccumulation of polycyclic aromatic hydrocarbons and phthalates in soil by novel QSARs

Polycyclic aromatic hydrocarbons (PAHs) and phthalic acid esters (PAEs) which are structurally featured with one or more aromatic skeletons are often regarded as two important groups of organic pollutants due to the widespread distribution and notorious toxic effects in soils. Relative to the great number of structural analogues or congeners detected in soil, however, the soil adsorption and bioaccumulation of PAHs/PAEs by plant is far less studied for the insufficiency of experimental determinations or lack of insights into the inherent structural requirements. To mechanistically evaluate the congener-specific soil adsorption and bioaccumulation for PAHs/PAEs, the quantitative structure-activity relationships (QSARs) were successfully developed by density functional theory (DFT) computation and partial least squares (PLS) analysis. As verified with the higher cumulative variance coefficients and cross-validated correlation coefficients for strong stability, interpretability and predictability, the QSARs could be used for prediction of unknown adsorption potency or bioavailability within the specified applicability domain, respectively. It was indicated by QSAR that the structural requirements of PAHs/PAEs necessary for strengthening the soil adsorption were mainly attributed to the molecular polarizability and the associated dispersion interaction with soil. As regards the bioaccumulation by carrot, the aggravation of spherical polarity change of molecules and the involved electrostatic interaction with soil entity or electron transfer from the highest occupied molecular orbital (HOMO) of PAHs/PAEs was implied to be inherently decisive for the variance of bioavailability among congeners. Based on the holistic view of negative correlation relationship, the soil adsorption seemed to act as the forceful constraint in decreasing the bioaccumulation of PAHs/PAEs and could also be alternatively gauged as the preliminary evaluation of bioavailability and risks on soil ecosystem. It would thus help better understand the soil adsorption and bioaccumulation with the informative mechanistic insights and provide data support for ecological risk assessment of PAHs/PAEs in soils.

Chemical structure and correlation analysis of HIV-1 NNRT and NRT inhibitors and database-curated, published inhibition constants with chemical structure in diverse datasets

Human immunodeficiency virus (HIV-1) reverse transcriptase is a major target for designing anti-HIV drugs. Developed inhibitors are divided into non-nucleoside analog reverse-transcriptase inhibitors (NNRTIs) and nucleoside analog reverse-transcriptase inhibitors (NRTIs) depending on their mechanism. Given that many inhibitors have been studied and for many of them binding affinity constants have been calculated, it is beneficial to analyze the chemical landscape of these families of inhibitors and correlate these inhibition constants with molecular structure descriptors. For this, the HIV-1 RT data was retrieved from the ChEMBL database, carefully curated, and original literature verified, grouped into NRTIs and NNRTIs, analyzed using a hierarchical scaffold classification method and modelled with best multi-linear regression approach. Analysis of the HIV-1 NNRTIs subset results in ten different common structural parent types of oxazepanone, piperazinone, pyrazine, oxazinanone, diazinanone, pyridine, pyrrole, diazepanone, thiazole, and triazine. The same analysis for HIV-1 NRTIs groups structures into four different parent types of uracil, pyrimide, pyrimidione, and imidazole. Each scaffold tree corresponding to the parent types has been carefully analyzed and examined, and changes in chemical structure favorable to potency and stability are highlighted. For both subsets, descriptive and predictive QSAR models are derived, discussed and externally validated, revealing general trends in relationships between molecular structure and binding affinity constants in structurally diverse datasets. Data and QSAR models are available at the QsarDB repository (http://dx.doi.org/10.15152/QDB.202).

A review of quantitative structure-property relationships for the fate of ionizable organic chemicals in water matrices and identification of knowledge gaps

Many organic chemicals are ionizable by nature. After use and release into the environment, various fate processes determine their concentrations, and hence exposure to aquatic organisms. In the absence of suitable data, such fate processes can be estimated using Quantitative Structure-Property Relationships (QSPRs). In this review we compiled available QSPRs from the open literature and assessed their applicability towards ionizable organic chemicals. Using quantitative and qualitative criteria we selected the 'best' QSPRs for sorption, (a)biotic degradation, and bioconcentration. The results indicate that many suitable QSPRs exist, but some critical knowledge gaps remain. Specifically, future focus should be directed towards the development of QSPR models for biodegradation in wastewater and sediment systems, direct photolysis and reaction with singlet oxygen, as well as additional reactive intermediates. Adequate QSPRs for bioconcentration in fish exist, but more accurate assessments can be achieved using pharmacologically based toxicokinetic (PBTK) models. No adequate QSPRs exist for bioconcentration in non-fish species. Due to the high variability of chemical and biological species as well as environmental conditions in QSPR datasets, accurate predictions for specific systems and inter-dataset conversions are problematic, for which standardization is needed. For all QSPR endpoints, additional data requirements involve supplementing the current chemical space covered and accurately characterizing the test systems used.

Application of radial basis function neural network to predict soil sorption partition coefficient using topological descriptors

The soil sorption partition coefficient logK_oc is an indispensable parameter that can be used in assessing the environmental risk of organic chemicals. In order to predict soil sorption partition coefficient for different and even unknown compounds in a fast and accurate manner, a radial basis function neural network (RBFNN) model was developed. Eight topological descriptors of 800 organic compounds were used as inputs of the model. These 800 organic compounds were chosen from a large and very diverse data set. Generalized Regression Neural Network (GRNN) was utilized as the function in this neural network model due to its capability to adapt very quickly. Hence, it can be used to predict logK_oc for new chemicals, as well. Out of total data set, 560 organic compounds were used for training and 240 to test efficiency of the model. The obtained results indicate that the model performance is very well. The correlation coefficients (R2) for training and test sets were 0.995 and 0.933, respectively. The root-mean square errors (RMSE) were 0.2321 for training set and 0.413 for test set. As the results for both training and test set are extremely satisfactory, the proposed neural network model can be employed not only to predict logK_oc of known compounds, but also to be adaptive for prediction of this value precisely for new products that enter the market each year.

Measurement and ANN prediction of pH-dependent solubility of nitrogen-heterocyclic compounds

Based on the solubility of 25 nitrogen-heterocyclic compounds (NHCs) measured by saturation shake-flask method, artificial neural network (ANN) was employed to the study of the quantitative relationship between the structure and pH-dependent solubility of NHCs. With genetic algorithm-multivariate linear regression (GA-MLR) approach, five out of the 1497 molecular descriptors computed by Dragon software were selected to describe the molecular structures of NHCs. Using the five selected molecular descriptors as well as pH and the partial charge on the nitrogen atom of NHCs (QN) as inputs of ANN, a quantitative structure-property relationship (QSPR) model without using Henderson-Hasselbalch (HH) equation was successfully developed to predict the aqueous solubility of NHCs in different pH water solutions. The prediction model performed well on the 25 model NHCs with an absolute average relative deviation (AARD) of 5.9%, while HH approach gave an AARD of 36.9% for the same model NHCs. It was found that QN played a very important role in the description of NHCs and, with QN, ANN became a potential tool for the prediction of pH-dependent solubility of NHCs.

Measurement of baseline toxicity and QSAR analysis of 50 non-polar and 58 polar narcotic chemicals for the alga Pseudokirchneriella subcapitata

In this paper a set of homogenous experimental algal toxicity data was measured for 50 non-polar narcotic chemicals using the alga Pseudokirchneriella subcapitata in a closed test with a growth rate endpoint. Most of the tested compounds are high volume industrial chemicals that so far lacked published REACH-compliant algal growth inhibition values. The test protocol fulfilled the criteria set forth in the OECD guideline 201 and had the same sensitivity as the open test which allowed direct comparison of toxicity values. Baseline QSAR model for non-polar narcotic compounds was established and compared with previous analogous models. Multi-linear QSAR model was derived for the non-polar and 58 previously tested polar (anilines and phenols) narcotic compounds modulating hydrophobicity, molecular size, electronic and molecular stability effects coded in the molecular descriptors. Descriptors in the model were analyzed and applicability domain was assessed providing further guidelines for the in silico prediction purposes in decision support while performing risk assessment. QSAR models in the manuscript are available on-line through QsarDB repository for exploring and prediction services (http://hdl.handle.net/10967/106).

A Large-Scale Empirical Evaluation of Cross-Validation and External Test Set Validation in (Q)SAR

(Q)SAR model validation is essential to ensure the quality of inferred models and to indicate future model predictivity on unseen compounds. Proper validation is also one of the requirements of regulatory authorities in order to accept the (Q)SAR model, and to approve its use in real world scenarios as alternative testing method. However, at the same time, the question of how to validate a (Q)SAR model, in particular whether to employ variants of cross-validation or external test set validation, is still under discussion. In this paper, we empirically compare a k-fold cross-validation with external test set validation. To this end we introduce a workflow allowing to realistically simulate the common problem setting of building predictive models for relatively small datasets. The workflow allows to apply the built and validated models on large amounts of unseen data, and to compare the performance of the different validation approaches. The experimental results indicate that cross-validation produces higher performant (Q)SAR models than external test set validation, reduces the variance of the results, while at the same time underestimates the performance on unseen compounds. The experimental results reported in this paper suggest that, contrary to current conception in the community, cross-validation may play a significant role in evaluating the predictivity of (Q)SAR models.

Quantitative relationship between rate constants and molecular structure descriptors for the gas phase hydrogen abstraction reactions

The abstraction of hydrogen by general radicals has a wide role in environmental and also in technological processes because it results in reactive free radicals that play a vital role in atmospheric chemistry and also in biochemical processes. In addition to experimental studies, the theoretical modelling of this elementary reaction has been important for understanding and predicting respective rate constants. In this paper, molecular descriptors in the context of a QSAR approach are used to codify the relationship between molecular structure and rate constants. Unique experimental data is collected from the literature for the reaction R(i)• + R(j)H → R(i)H + R(j)•, where R(i)• = H• and R(j)• are diverse radicals. The four-parameter QSAR model (n = 34, r(2) = 0.81, r(2)(CV) = 0.74, r(2)(scr) = 0.12, s(2) = 0.19) is presented for the bimolecular rate constants, accompanied with model diagnostics and analysis of descriptors in the model.

On some aspects of validation of predictive quantitative structure-activity relationship models

The success of any quantitative structure-activity relationship model depends on the accuracy of the input data, selection of appropriate descriptors and statistical tools and, most importantly, the validation of the developed model. Validation is the process by which the reliability and relevance of a procedure are established for a specific purpose. This review focuses on the importance of validation of quantitative structure-activity relationship models and different methods of validation. Some important issues, such as internal versus external validation, method of selection of training set compounds and training set size, applicability domain, variable selection and suitable parameters to indicate external predictivity, are also discussed.

Comparative analysis of local and consensus quantitative structure-activity relationship approaches for the prediction of bioconcentration factor

Quantitative structure-activity relationships (QSARs) are broadly classified as global or local, depending on their molecular constitution. Global models use large and diverse training sets covering a wide range of chemical space. Local models focus on smaller structurally or chemically similar subsets that are conventionally selected by human experts or alternatively using clustering analysis. The current study focuses on the comparative analysis of different clustering algorithms (expectation-maximization, K-means and hierarchical) for seven different descriptor sets as structural characteristics and two rule-based approaches to select subsets for designing local QSAR models. A total of 111 local QSAR models are developed for predicting bioconcentration factor. Predictions from local models were compared with corresponding predictions from the global model. The comparison of coefficients of determination (r(2)) and standard deviations for local models with similar subsets from the global model show improved prediction quality in 97% of cases. The descriptor content of derived QSARs is discussed and analyzed. Local QSAR models were further consolidated within the framework of consensus approach. All different consensus approaches increased performance over the global and local models. The consensus approach reduced the number of strongly deviating predictions by evening out prediction errors, which were produced by some local QSARs.

Predictions of Gibbs free energies for the adsorption of polyaromatic and nitroaromatic environmental contaminants on carbonaceous materials: efficient computational approach

The adsorption of benzene, polycyclic aromatic hydrocarbons (PAHs), and nitroaromatic compounds (NACs) on the carbonaceous surfaces from the gas phase and water solution was investigated. Several different levels of theory were applied, including DFT-, MP2-, and CCSD(T)-based methods, to find an approach that is computationally inexpensive and can provide accurate thermodynamic parameters for studied adsorption phenomena. The methods and techniques used (including cluster and periodic approximations) were evaluated on the basis of comparison with available experimental data. The optimized structures of calculated complexes are obtained, and the interaction energies and Gibbs free energies are predicted. Good agreement was revealed for the theoretical and experimental adsorption energies of benzene and PAHs adsorbed on the carbon surfaces. The adsorption of benzene, PAHs, and NACs on carbon is suggested to be effective from the gas phase for all studied compounds and for PAHs and NACs also from water solution at room temperature.

Linear and non-linear relationships between soil sorption and hydrophobicity: model, validation and influencing factors

The hydrophobic parameter represented by the octanol/water partition coefficient (logP) is commonly used to predict the soil sorption coefficient (K(oc)). However, a simple non-linear relationship between logK(oc) and logP has not been reported in the literature. In the present paper, soil sorption data for 701 compounds was investigated. The results show that logK(oc) is linearly related to logP for compounds with logP in the range of 0.5-7.5 and non-linearly related to logP for the compounds in a wide range of logP. A non-linear model has been developed between logK(oc) and logP for a wide range of compounds in the training set. This model was validated in terms of average error (AE), average absolute error (AAE) and root-mean squared error (RMSE) by using an external test set with 107 compounds. Nearly the same predictive capacity was observed in comparison with existing models. However, this non-linear model is simple, and uses only one parameter. The best model developed in this paper is a non-linear model with six correction factors for six specific classes of compounds. This model can well predict logK(oc) for 701 diverse compounds with AAE = 0.37. The reasons for systemic deviations in these groups may be attributed to the difference of sorption mechanism for hydrophilic/polar compounds, low solubility for highly hydrophobic compounds, hydrolysis of esters in solution, volatilization for volatile compounds and highly experimental errors for compounds with extremely high or low sorption coefficients.

Quantitative structure-activity relationship analysis of acute toxicity of diverse chemicals to Daphnia magna with whole molecule descriptors

Quantitative structure-activity relationship analysis and estimation of toxicological effects at lower-mid trophic levels provide first aid means to understand the toxicity of chemicals. Daphnia magna serves as a good starting point for such toxicity studies and is also recognized for regulatory use in estimating the risk of chemicals. The ECOTOX database was queried and analysed for available data and a homogenous subset of 253 compounds for the endpoint LC50 48 h was established. A four-parameter quantitative structure-activity relationship was derived (coefficient of determination, r (2) = 0.740) for half of the compounds and internally validated (leave-one-out cross-validated coefficient of determination, [Formula: see text] = 0.714; leave-many-out coefficient of determination, [Formula: see text] = 0.738). External validation was carried out with the remaining half of the compounds (coefficient of determination for external validation, [Formula: see text] = 0.634). Two of the descriptors in the model (log P, average bonding information content) capture the structural characteristics describing penetration through bio-membranes. Another two descriptors (energy of highest occupied molecular orbital, weighted partial negative surface area) capture the electronic structural characteristics describing the interaction between the chemical and its hypothetic target in the cell. The applicability domain was subsequently analysed and discussed.

Statistical external validation and consensus modeling: a QSPR case study for Koc prediction

The soil sorption partition coefficient (log K(oc)) of a heterogeneous set of 643 organic non-ionic compounds, with a range of more than 6 log units, is predicted by a statistically validated QSAR modeling approach. The applied multiple linear regression (ordinary least squares, OLS) is based on a variety of theoretical molecular descriptors selected by the genetic algorithms-variable subset selection (GA-VSS) procedure. The models were validated for predictivity by different internal and external validation approaches. For external validation we applied self organizing maps (SOM) to split the original data set: the best four-dimensional model, developed on a reduced training set of 93 chemicals, has a predictivity of 78% when applied on 550 validation chemicals (prediction set). The selected molecular descriptors, which could be interpreted through their mechanistic meaning, were compared with the more common physico-chemical descriptors log K(ow) and log S(w). The chemical applicability domain of each model was verified by the leverage approach in order to propose only reliable data. The best predicted data were obtained by consensus modeling from 10 different models in the genetic algorithm model population.