Prediction of toxicity of nitrobenzenes using ab initio and least squares support vector machines

A novel procedure for selection of molecular descriptors: QSAR model for mutagenicity of nitroaromatic compounds

Nitroaromatic compounds (NACs) stand out as pervasive organic pollutants, prompting an imperative need to investigate their hazardous effects. Computational chemistry methods play a crucial role in this exploration, offering a safer and more time-efficient approach, mandated by various legislations. In this study, our focus lay on the development of transparent, interpretable, reproducible, and publicly available methodologies aimed at deriving quantitative structure-activity relationship models and testing them by modelling the mutagenicity of NACs against the Salmonella typhimurium TA100 strain. Descriptors were selected from Mordred and RDKit molecular descriptors, along with several quantum chemistry descriptors. For that purpose, the genetic algorithm (GA), as the most widely used method in the literature, and three alternative algorithms (Boruta, Featurewiz, and ForwardSelector) combined with the forward stepwise selection technique were used. The construction of models utilized the multiple linear regression method, with subsequent scrutiny of fitting and predictive performance, reliability, and robustness through various statistical validation criteria. The models were ranked by the Multi-Criteria Decision Making procedure. Findings have revealed that the proposed methodology for descriptor selection outperforms GA, with Featurewiz showing a slight advantage over Boruta and ForwardSelector. These constructed models can serve as valuable tools for the quick and reliable prediction of NACs mutagenicity.

Chemometrics for Selection, Prediction, and Classification of Sustainable Solutions for Green Chemistry—A Review

In this review, we present the applications of chemometric techniques for green and sustainable chemistry. The techniques, such as cluster analysis, principal component analysis, artificial neural networks, and multivariate ranking techniques, are applied for dealing with missing data, grouping or classification purposes, selection of green material, or processes. The areas of application are mainly finding sustainable solutions in terms of solvents, reagents, processes, or conditions of processes. Another important area is filling the data gaps in datasets to more fully characterize sustainable options. It is significant as many experiments are avoided, and the results are obtained with good approximation. Multivariate statistics are tools that support the application of quantitative structure–property relationships, a widely applied technique in green chemistry.

QM Calculations in ADMET Prediction

In recent years, there has been an increase in the application of quantum mechanics (QM) methods to describe properties related to the ADMET profile of small molecules. The application of these methods allows calculating useful descriptors and physiochemical properties contributing to ADMET prediction. Considering that QM methods are the only one that describe the electronic state of a molecules, such methods are particularly useful for studying the metabolism of drugs; furthermore, the introduction of mixed QM and molecular mechanics (QM/MM) is also increasing the understanding of drug interaction with cytochromes from a mechanistic point of view. Finally, combining the increase number of experimental data with machine learning algorithms and QM-derived descriptors allowed the creation of an end-user software capable of affecting the drug discovery process.

A simple approach for assessment of toxicity of nitroaromatic compounds without using complex descriptors and computer codes

A simple approach is introduced to assess the toxicity of nitroaromatic compounds in terms of an oral LD₅₀ dose (50% lethal dose) for rats. Most of the presented Quantitative Structure-Activity Relationship (QSAR) models for prediction of in vivo toxicity of nitroaromatics are calculated by quantum computing descriptors which are more difficult to interpret and apply, while the new model requires only the molecular structure of a desirable nitroaromatic compound. The novel model is based on the constitutional descriptors, such as the number of oxygen, sulphur, phosphorous and molecular fragments. Experimental data of 90 nitroaromatics are used to derive and test the new model as the logarithm of LD₅₀ values, i.e. -log (LD₅₀). Although it is based on only simple structural parameters, the reliability of the new model is also higher than the complex QSAR model because the values of the root-mean-square deviation (RMSD) of -log (LD₅₀) for the new and the outputs of the latest QSAR method are 0.342 and 0.377, respectively.

Hybrid connectionist model determines CO2-oil swelling factor

In-depth understanding of interactions between crude oil and CO₂ provides insight into the CO₂-based enhanced oil recovery (EOR) process design and simulation. When CO₂ contacts crude oil, the dissolution process takes place. This phenomenon results in the oil swelling, which depends on the temperature, pressure, and composition of the oil. The residual oil saturation in a CO₂-based EOR process is inversely proportional to the oil swelling factor. Hence, it is important to estimate this influential parameter with high precision. The current study suggests the predictive model based on the least-squares support vector machine (LS-SVM) to calculate the CO₂-oil swelling factor. A genetic algorithm is used to optimize hyperparameters (γ and σ ²) of the LS-SVM model. This model showed a high coefficient of determination (R ² = 0.9953) and a low value for the mean-squared error (MSE = 0.0003) based on the available experimental data while estimating the CO₂-oil swelling factor. It was found that LS-SVM is a straightforward and accurate method to determine the CO₂-oil swelling factor with negligible uncertainty. This method can be incorporated in commercial reservoir simulators to include the effect of the CO₂-oil swelling factor when adequate experimental data are not available.

Building up a QSAR model for toxicity toward Tetrahymena pyriformis by the Monte Carlo method: A case of benzene derivatives

Data on toxicity toward Tetrahymena pyriformis is indicator of applicability of a substance in ecologic and pharmaceutical aspects. Quantitative structure-activity relationships (QSARs) between the molecular structure of benzene derivatives and toxicity toward T. pyriformis (expressed as the negative logarithms of the population growth inhibition dose, mmol/L) are established. The available data were randomly distributed three times into the visible training and calibration sets, and invisible validation sets. The statistical characteristics for the validation set are the following: r(2)=0.8179 and s=0.338 (first distribution); r(2)=0.8682 and s=0.341 (second distribution); r(2)=0.8435 and s=0.323 (third distribution). These models are built up using only information on the molecular structure: no data on physicochemical parameters, 3D features of the molecular structure and quantum mechanics descriptors are involved in the modeling process.

A comprehensive QSPR model for dielectric constants of binary solvent mixtures

The dielectric constant is a key physicochemical property in solubility, chemical equilibrium and the synthesis of compounds in pharmaceutical/chemical sciences. In this context, a quantitative structure-property relationship (QSPR) model was designed from 3207 binary solvent mixtures by using 23 calculated experimental-theoretical descriptors including solvent fractions (f₁ and f₂), individual dielectric constants of solvents (dc₁ and dc₂), temperature, and Abraham and Hansen solvation parameters. The QSPR model was developed using a genetic algorithm based multiple linear regression (GA-MLR) and robust regression. Jackknifing was implemented for internal-external validation of the selected descriptors by GA containing f₁, f₂, dc₁ and dc₂. Implementation of jackknifing on the selected descriptors revealed that p values were close to zero. Consequently, the significance of selected descriptors was confirmed through the sign change point of view and their validity was verified. The model was evaluated using the r² and Q²_(F3) parameters as criteria of model prediction ability. The r² values were equal to 0.925 and 0.922, and Q²_(F3) were reported as 0.873 and 0.862 for the cross-validation and prediction steps, respectively. Finally, model performance was clearly acceptable to anticipate the modelling of dielectric constants for a wide range of binary solvent mixtures.

Machine learning for toxicity characterization of organic chemical emissions using USEtox database: Learning the structure of the input space

Toxicity characterization of chemical emissions in Life Cycle Assessment (LCA) is a complex task which usually proceeds via multimedia (fate, exposure and effect) models attached to models of dose-response relationships to assess the effects on target. Different models and approaches do exist, but all require a vast amount of data on the properties of the chemical compounds being assessed, which are hard to collect or hardly publicly available (especially for thousands of less common or newly developed chemicals), therefore hampering in practice the assessment in LCA. An example is USEtox, a consensual model for the characterization of human toxicity and freshwater ecotoxicity. This paper places itself in a line of research aiming at providing a methodology to reduce the number of input parameters necessary to run multimedia fate models, focusing in particular to the application of the USEtox toxicity model. By focusing on USEtox, in this paper two main goals are pursued: 1) performing an extensive exploratory analysis (using dimensionality reduction techniques) of the input space constituted by the substance-specific properties at the aim of detecting particular patterns in the data manifold and estimating the dimension of the subspace in which the data manifold actually lies; and 2) exploring the application of a set of linear models, based on partial least squares (PLS) regression, as well as a nonlinear model (general regression neural network--GRNN) in the seek for an automatic selection strategy of the most informative variables according to the modelled output (USEtox factor). After extensive analysis, the intrinsic dimension of the input manifold has been identified between three and four. The variables selected as most informative may vary according to the output modelled and the model used, but for the toxicity factors modelled in this paper the input variables selected as most informative are coherent with prior expectations based on scientific knowledge of toxicity factors modelling. Thus the outcomes of the analysis are promising for the future application of the approach to other portions of the model, affected by important data gaps, e.g., to the calculation of human health effect factors.

Toxicophore exploration as a screening technology for drug design and discovery: techniques, scope and limitations

Toxicity is a common drawback of newly designed chemotherapeutic agents. With the exception of pharmacophore-induced toxicity (lack of selectivity at higher concentrations of a drug), the toxicity due to chemotherapeutic agents is based on the toxicophore moiety present in the drug. To date, methodologies implemented to determine toxicophores may be broadly classified into biological, bioanalytical and computational approaches. The biological approach involves analysis of bioactivated metabolites, whereas the computational approach involves a QSAR-based method, mapping techniques, an inverse docking technique and a few toxicophore identification/estimation tools. Being one of the major steps in drug discovery process, toxicophore identification has proven to be an essential screening step in drug design and development. The paper is first of its kind, attempting to cover and compare different methodologies employed in predicting and determining toxicophores with an emphasis on their scope and limitations. Such information may prove vital in the appropriate selection of methodology and can be used as screening technology by researchers to discover the toxicophoric potentials of their designed and synthesized moieties. Additionally, it can be utilized in the manipulation of molecules containing toxicophores in such a manner that their toxicities might be eliminated or removed.

Microwave-assisted of dispersive liquid-liquid microextraction and spectrophotometric determination of uranium after optimization based on Box-Behnken design and chemometrics methods

In this study an analytical procedure based on microwave-assisted dispersive liquid-liquid microextraction (MA-DLLME) and spectrophotometric coupled with chemometrics methods is proposed to determine uranium. In the proposed method, 4-(2-pyridylazo) resorcinol (PAR) is used as a chelating agent, and chloroform and ethanol are selected as extraction and dispersive solvent. The optimization strategy is carried out by using two level full factorial designs. Results of the two level full factorial design (2(4)) based on an analysis of variance demonstrated that the pH, concentration of PAR, amount of dispersive and extraction solvents are statistically significant. Optimal condition for three variables: pH, concentration of PAR, amount of dispersive and extraction solvents are obtained by using Box-Behnken design. Under the optimum conditions, the calibration graphs are linear in the range of 20.0-350.0 ng mL(-1) with detection limit of 6.7 ng mL(-1) (3δB/slope) and the enrichment factor of this method for uranium reached at 135. The relative standard deviation (R.S.D.) is 1.64% (n=7, c=50 ng mL(-1)). The partial least squares (PLS) modeling was used for multivariate calibration of the spectrophotometric data. The orthogonal signal correction (OSC) was used for preprocessing of data matrices and the prediction results of model, with and without using OSC, were statistically compared. MA-DLLME-OSC-PLS method was presented for the first time in this study. The root mean squares error of prediction (RMSEP) for uranium determination using PLS and OSC-PLS models were 4.63 and 0.98, respectively. This procedure allows the determination of uranium synthesis and real samples such as waste water with good reliability of the determination.

In silico de novo design of novel NNRTIs: a bio-molecular modelling approach

Six novel NNRTIs (DABO) with high efficacy are designed by assessing the interaction potential and structural requirements using chemometric analyses (SVM, BPNN and MLR) on structural descriptors.

AN IMPROVED QSPR STUDY OF REVERSE FACTOR OF NANOPARTICLES IN ROADSIDE ATMOSPHERE ON KERNEL PARTIAL LEAST SQUARES AND GENETIC ALGORITHM

Thermal desorption-comprehensive two-dimensional gas chromatography high-resolution time-of-flight mass spectrometry (TD–GC × GC–HRTOF-MS) is one of the most powerful tools in analytical nanoparticle compounds. Genetic algorithm and partial least square (GA-PLS) and kernel PLS (GA-KPLS) models were used to investigate the correlation between reverse factor (RF) and descriptors for 50 nanoparticles fraction with a diameter of 29–58 nm in roadside atmosphere which obtained by TD–GC×GC–HRTOF-MS. The correlation coefficient leave-group-out cross validation (LGO-CV (Q2)) of prediction for the GA-PLS and GA-KPLS models for training and test sets were (0.761 and 0.718) and (0.825 and 0.814), respectively, revealing the reliability of these models. This is the first research on the quantitative structure-property relationship (QSPR) of the nanoparticles in roadside atmosphere using the GA-PLS and GA-KPLS.

Accurate prediction of the toxicity of benzoic acid compounds in mice via oral without using any computer codes

Most of benzoic acid derivatives are toxic, which may cause serious public health and environmental problems. Two novel simple and reliable models are introduced for desk calculations of the toxicity of benzoic acid compounds in mice via oral LD(50) with more reliance on their answers as one could attach to the more complex outputs. They require only elemental composition and molecular fragments without using any computer codes. The first model is based on only the number of carbon and hydrogen atoms, which can be improved by several molecular fragments in the second model. For 57 benzoic compounds, where the computed results of quantitative structure-toxicity relationship (QSTR) were recently reported, the predicted results of two simple models of present method are more reliable than QSTR computations. The present simple method is also tested with further 324 benzoic acid compounds including complex molecular structures, which confirm good forecasting ability of the second model.

Development predictive QSAR models for artemisinin analogues by various feature selection methods: a comparative study

Quantitative structure-activity relationship (QSAR) models were derived for 179 analogues of artemisinin, a potent antimalarial agent. The activities of these compounds were investigated by means of multiple linear regression (MLR). To select relevant descriptors, several methods including stepwise selection, successive projection algorithm and an ant colony optimization algorithm (called memorized_ACS) were employed. A wide variety of molecular descriptors belonging to various structural properties were calculated for each molecule. Two matrixes (D1 and D2) of molecular properties were built. The D1 matrix included the calculated descriptors and the D2 matrix contained the first to third orders of the calculated descriptors and the logarithm of absolute values of the calculated descriptors. For both data matrixes, significant QSAR models were obtained by the memorized_ACS algorithm. The reactive and PEOE (partial equalization of orbital electronegativity) descriptors represented the highest impact on the antimalarial activity. The PEOE descriptors belong to partial charge descriptors and the reactive descriptor is an indicator of the presence of the reactive groups in the molecule. The best MLR model has a training error of 0.71 log RA units (r (2 )= 0.81) and a prediction error of 0.48 log RA units (r (2) = 0.88).

Estimation of the physicochemical properties of PCDD/Fs using three-dimensional holographic vector of atomic interaction field

Polychlorinated dibenzo-p-dioxins and dibenzofurans (PCDD/Fs) are a group of important persistent organic pollutants. In the present study, the three-dimensional holographic vector of atomic interaction field (3D-HoVAIF) method is used to describe the chemical structures of PCDD/Fs. After variable screening using a stepwise multiple regression (SMR) technique, the linear relationships among six physicochemical properties of PCDD/Fs and 3D-HoVAIF descriptors are built using a partial least-squares (PLS) regression model. The results show that the 3D-HoVAIF descriptors can be used to express the quantitative structure-property relationships of PCDD/Fs. The predictive capabilities of the models have also been confirmed by leave-one-out cross-validation. The optimum model has been used to estimate values for PCDD/Fs for which no experimental data on physicochemical properties are available. Supplemental materials are available for this article. Go to the publisher's online edition of Journal of Environmental Science and Health: Part A to view the free supplemental file.

QSPR prediction of flash point of esters by means of GFA and ANFIS

A quantitative structure property relationship (QSPR) study was performed to develop a model for prediction of flash point of esters based on a diverse set of 95 components. The most five important descriptors were selected from a set of 1124 descriptors to build the QSPR model by means of a genetic function approximation (GFA). For considering the nonlinear behavior of these molecular descriptors, adaptive neuro-fuzzy inference system (ANFIS) method was used. The ANFIS and GFA squared correlation coefficient for testing set was 0.969 and 0.965, respectively. The results obtained showed the ability of developed GFA and ANFIS for prediction of flash point of esters.

Prediction of wood property in Chinese Fir based on visible/near-infrared spectroscopy and least square-support vector machine

A method for the quantification of density of Chinese Fir samples based on visible/near-infrared (vis-NIR) spectrometry and least squares-support vector machine (LS-SVM) was proposed. Sample set partitioning based on joint x-y distances (SPXY) algorithm was used for dividing calibration and prediction samples, it is of value for prediction of property involving complex matrices. A stepwise procedure is employed to select samples according to their differences in both x (instrumental responses) and y (predicted parameter) spaces. For comparison, the models were also constructed by Kennard-Stone method, as well as by using the duplex and random sampling methods for subset partitioning. The results revealed that the SPXY algorithm may be an advantageous alternative to the other three strategies. To validate the reliability of LS-SVM, comparisons were made among other modeling methods such as support vector machine (SVM) and partial least squares (PLS) regression. Satisfactory models were built using LS-SVM, with lower prediction errors and superior performance in relation to SVM and PLS. These results showed possibility of building robust models to quantify the density of Chinese Fir using near-infrared spectroscopy and LS-SVM combined SPXY algorithm as a nonlinear multivariate calibration procedure.

A novel QSPR model for prediction of lower flammability limits of organic compounds based on support vector machine

A quantitative structure-property relationship (QSPR) study is suggested for the prediction of lower flammability limits (LFLs) of organic compounds. Various kinds of molecular descriptors were calculated to represent the molecular structures of compounds, such as topological, charge, and geometric descriptors. Genetic algorithm was employed to select optimal subset of descriptors that have significant contribution to the overall LFL property. The novel chemometrics method of support vector machine was employed to model the possible quantitative relationship between these selected descriptors and LFL. The resulted model showed high prediction ability that the obtained root mean square error and average absolute error for the whole dataset were 0.069 and 0.051vol.%, respectively. The results were also compared with those of previously published models. The comparison results indicate the superiority of the presented model and reveal that it can be effectively used to predict the LFL of organic compounds from the molecular structures alone.

Current mathematical methods used in QSAR/QSPR studies

This paper gives an overview of the mathematical methods currently used in quantitative structure-activity/property relationship (QASR/QSPR) studies. Recently, the mathematical methods applied to the regression of QASR/QSPR models are developing very fast, and new methods, such as Gene Expression Programming (GEP), Project Pursuit Regression (PPR) and Local Lazy Regression (LLR) have appeared on the QASR/QSPR stage. At the same time, the earlier methods, including Multiple Linear Regression (MLR), Partial Least Squares (PLS), Neural Networks (NN), Support Vector Machine (SVM) and so on, are being upgraded to improve their performance in QASR/QSPR studies. These new and upgraded methods and algorithms are described in detail, and their advantages and disadvantages are evaluated and discussed, to show their application potential in QASR/QSPR studies in the future.

How not to develop a quantitative structure-activity or structure-property relationship (QSAR/QSPR)

Although thousands of quantitative structure-activity and structure-property relationships (QSARs/QSPRs) have been published, as well as numerous papers on the correct procedures for QSAR/QSPR analysis, many analyses are still carried out incorrectly, or in a less than satisfactory manner. We have identified 21 types of error that continue to be perpetrated in the QSAR/QSPR literature, and each of these is discussed, with examples (including some of our own). Where appropriate, we make recommendations for avoiding errors and for improving and enhancing QSAR/QSPR analyses.

Simultaneous spectrophotometric determination of mercury and palladium with Thio-Michler's Ketone using partial least squares regression and orthogonal signal correction

A simple, novel and sensitive spectrophotometric method was described for simultaneous determination of mercury and palladium. The method is based on the complex formation of mercury and palladium with Thio-Michler's Ketone (TMK) at pH 3.5. All factors affecting on the sensitivity were optimized and the linear dynamic range for determination of mercury and palladium found. The simultaneous determination of mercury and palladium mixtures by using spectrophotometric method is a difficult problem, due to spectral interferences. By multivariate calibration methods such as partial least squares (PLS), it is possible to obtain a model adjusted to the concentration values of the mixtures used in the calibration range. Orthogonal signal correction (OSC) is a preprocessing technique used for removing the information unrelated to the target variables based on constrained principal component analysis. OSC is a suitable preprocessing method for PLS calibration of mixtures without loss of prediction capacity using spectrophotometric method. In this study, the calibration model is based on absorption spectra in the 360-660 nm range for 25 different mixtures of mercury and palladium. Calibration matrices were containing 0.025-1.60 and 0.05-0.50 microg mL(-1) of mercury and palladium, respectively. The RMSEP for mercury and palladium with OSC and without OSC were 0.013, 0.006 and 0.048, 0.030, respectively. This procedure allows the simultaneous determination of mercury and palladium in synthetic and real matrix samples good reliability of the determination.