External Set Compounds Research Articles

In silico-based identification of new anti-pfdhfr drug candidates via 1,3,5-triazine derivatives

Quantitative structure-activity relationship study was used to investigate the relationship between anti-pfdhfr activity and structure of twenty-eight 1,3,5-triazine derivatives. We performed benchmark studies on the molecular geometry, electron properties of 1,3,5-triazine using semi-empirical(PM3), density functional theory and post Hartree-Fock methods. Followed by a QSAR study using multiple linear regression (MLR) and artificial neural networks (ANN). The QSAR models developed allow identify/describe the relationship between the biological activity of the molecules and their molecular descriptors (topological, physicochemical, electronic...). A further external set of compounds was used for validation where a high correlation between experimental and predicted anti-pfdhfr activity values is noticed. This QSAR study provides useful information for developing novel pfdhfr inhibitors. The set’s ADME properties and drug similarities, as well as newly produced compounds and reference ligand, were investigated. These findings would be extremely useful in guiding optimization for the development of new anti-pfdhfr drug candidates.

Development of a read-across-derived classification model for the predictions of mutagenicity data and its comparison with traditional QSAR models and expert systems

Mutagenicity is considered an important endpoint from the regulatory, environmental and medical points of view. Due to the wide number of compounds that may be of concern and the enormous expenses (in terms of time, money, and animals) associated with rodent mutagenicity bioassays, this endpoint is a major target for the development of alternative approaches for screening and prediction. The majority of old-aged expert systems and quantitative structure-activity relationship (QSAR) models may show reduced performance over time for their application on newer chemical candidates; thus, researchers constantly try to improve the modeling strategies. In our report, we initially performed traditional classification-based linear discriminant analysis (LDA) QSAR modeling using the benchmark Ames dataset of diverse chemicals (6512 compounds) to recognize the relationship between the molecules and their potential mutagenic behavior. The classical LDA QSAR model is developed from a selected set of 2D descriptors. The LDA QSAR model was developed by using a total of 31 descriptors identified from the analysis of the most discriminating features. Additionally, we have used similarity-derived features obtained from the read-across (RA) to develop an RA-based QSAR model. The developed RA-based LDA QSAR model has better predictivity, transferability, and interpretability compared to the LDA QSAR model, and it uses a very small number of descriptors compared to the classical QSAR model. Different machine learning (ML) models were also developed using the descriptors appearing in the read-across-based LDA QSAR model for comparative studies. We have checked the prediction quality of 216 true external set compounds using the novel similarity-derived RA model. The performance of the OECD toolbox is also compared with the RA-derived LDA QSAR model for a true external set. The current study aimed to explore the significance of the read-across-based algorithm and its application to the most current experimental mutagenicity data to complement already available expert systems.

Ecotoxicological QSAR modelling of the acute toxicity of fused and non-fused polycyclic aromatic hydrocarbons (FNFPAHs) against two aquatic organisms: Consensus modelling and comparison with ECOSAR

Fused and non-fused polycyclic aromatic hydrocarbons (FNFPAHs) are a type of organic compounds widely occurring in the environment that pose a potential hazard to ecosystem and public health, and thus receive extensive attention from various regulatory agencies. Here, quantitative structure-activity relationship (QSAR) models were constructed to model the ecotoxicity of FNFPAHs against two aquatic species, Daphnia magna and Oncorhynchus mykiss. According to the stringent OECD guidelines, we used genetic algorithm (GA) plus multiple linear regression (MLR) approach to establish QSAR models of the two aquatic toxicity endpoints: D. magna (48 h LC50) and O. mykiss (96 h LC50). The models were established using simple 2D descriptors with explicit physicochemical significance and evaluated using various internal/external validation metrics. The results clearly show that both models are statistically robust (QLOO2 = 0.7834 for D. magna and QLOO2 = 0.8162 for O. mykiss), have good internal fitness (R2 = 0.8159 for D. magna and R2 = 0.8626 for O. mykiss and external predictive ability (D. magna: Rtest2 = 0.8259, QFn2 = 0.7640∼0.8140, CCCtest = 0.8972; O. mykiss:Rtest2 = 0.8077, QFn2 = 0.7615∼0.7722, CCCtest = 0.8910). To prove the predictive performance of the developed models, an additional comparison with the standard ECOSAR tool obviously shows that our models have lower RMSE values. Subsequently, we utilized the best models to predict the true external set compounds collected from the PPDB database to further fill the toxicity data gap. In addition, consensus models (CMs) that integrate all validated individual models (IMs) were more externally predictive than IMs, of which CM2 has the best prediction performance towards the two aquatic species. Overall, the models presented here could be used to evaluate unknown FNFPAHs inside the domain of applicability (AD), thus being very important for environmental risk assessment under current regulatory frameworks.

Risk assessment of aromatic organic chemicals to T. pyriformis in environmental protection using regression-based QSTR and Read-Across algorithm

Hazardous aromatic compounds have a high probability of entering the surrounding environment, posing a threat to humans and other habitats. It is, thus, necessary to estimate the toxicity of these chemicals as a preventive measure before being marketed. The present study involves the development of in silico-based predictive 2D-QSTR models using a PLS regression approach for the exploration of the structural features responsible for the toxicity of T. pyriformis using simple and easily interpretable 2D descriptors employing a dataset containing 892 chemicals. The developed model was extensively validated by evaluating the model's reliability and predictability using internationally accepted external and internal validation metrics. We have also used the “Intelligent Consensus Predictor” tool and Read-Across software, which shows better results for test set compounds as compared with individual PLS models. We have also validated the models using a set of 383 external set compounds which are not used for the development of models. The results suggested that molecules with aliphatic aldehyde groups are much more toxic to the protozoan whereas chemicals containing C–N fragments at the topological distance 3 & 4, polar and alcoholic groups are less toxic to the protozoan. In conclusion, the developed QSTR and Read-Across models might be extremely beneficial as guides for researchers to estimate the toxicity profile of novel compounds against T. pyriformis.

QSPR modelling for investigation of different properties of aminoglycoside-derived polymers using 2D descriptors

ABSTRACT The quantitative structure‐property relationship (QSPR) method is commonly used to predict different physicochemical characteristics of interest of chemical compounds with an objective to accelerate the process of design and development of novel chemical compounds in the biotechnology and healthcare industries. In the present report, we have employed a QSPR approach to predict the different properties of the aminoglycoside-derived polymers (i.e. polymer DNA binding and aminoglycoside-derived polymers mediated transgene expression). The final QSPR models were obtained using the partial least squares (PLS) regression approach using only specific categories of two-dimensional descriptors and subsequently evaluated considering different internationally accepted validation metrics. The proposed models are robust and non-random, demonstrating excellent predictive ability using test set compounds. We have also developed different kinds of consensus models using several validated individual models to improve the prediction quality for external set compounds. The present findings provide new insight for exploring the design of an aminoglycoside-derived polymer library based on different identified physicochemical properties as well as predict their property before their synthesis.

In Silico Modeling of Small Molecule Carboxamides as Inhibitors of SARS-CoV 3CL Protease: An Approach Towards Combating COVID-19.

The quantitative structure-activity relationship (QSAR) approach is most widely used for the prediction of biological activity of potential medicinal compounds. A QSAR model is developed by correlating the information obtained from chemical structures (numerical descriptors/ independent variables) with the experimental response values (the dependent variable). In the current study, we have developed a QSAR model to predict the inhibitory activity of small molecule carboxamides against severe acute respiratory syndrome coronavirus (SARS-- CoV) 3CLpro enzyme. Due to the structural similarity of this enzyme with SARS-CoV-2, the causative organism of the recent pandemic, the former may be used for the development of therapies against coronavirus disease 19 (COVID-19). The final multiple linear regression (MLR) model was based on four two-dimensional descriptors with definite physicochemical meaning. The model was strictly validated using different internal and external quality metrics. The model showed significant statistical quality in terms of determination coefficient (R2=0.748, adjusted R2 or R2 adj = 0.700), cross-validated leave-one-out Q2 (Q2=0.628) and external predicted variance R2 pred = 0.723. The final validated model was used for the prediction of external set compounds as well as to virtually design a new library of small molecules. We have also performed a docking analysis of the most active and least active compounds present in the dataset for comparative analysis and to explain the features obtained from the 2D-QSAR model. The derived model may be useful to predict the inhibitory activity of small molecules within the applicability domain of the model only based on the chemical structure information prior to their synthesis and testing.

Chemometric Modelling of Heat Release Capacity, Total Heat Release and Char Formation of Polymers to Assess Their Flammability Characteristics.

The quantitative structure-property relationship (QSPR) approach has widely been used to predict several physicochemical properties of materials employing the information obtained from their chemical structures (numerical descriptors). In the present work, we have generated three individual QSPR models for three different endpoints for a large number of polymers in order to determine their fire retardant property such as heat release capacity, total heat release, and %Char, using the only two-dimensional descriptors with definite physicochemical meaning. Relevant subsets of descriptors were selected employing a genetic algorithm approach; subsequently, the selected descriptors were utilised for the identification of the best combination of the variables for the model generation, while the final models were developed employing the partial least squares (PLS) regression algorithm. The generated models were rigorously validated using various internationally accepted internal and external validation metrics. All the models showed promising statistical quality in terms of determination coefficient (0.802, 0.842 and 0.826), cross-validated leave-one-out Q2 (0.759, 0.810 and 0.752) and predictive R2pred or Q2ext (0.810, 0.900 and 0.847) for HRC (nTraining =62, nTest =28), THR (nTraining =64, nTest =21) and %char (nTraining =49, nTest =21) datasets, respectively. All the certified models were used for prediction of flammability characteristics of 37 external set compounds, and further, the quality of prediction was determined by using the PRI software tool. The final models of HRC, THR and %Char formation of polymers may be useful to predict the flammability characteristics of polymers quickly before their synthesis and used as a better alternative approach to the experimental testing of flammability of polymers.

Estimation of Random Accuracy and its Use in Validation of Predictive Quality of Classification Models within Predictive Challenges

Shortcomings of the correlation coefficient (Pearson's) as a measure for estimating and calculating the accuracy of predictive model properties are analysed. Here we discuss two such cases that can often occur in the application of the model in predicting properties of a new external set of compounds. The first problem in using the correlation coefficient is its insensitivity to the systemic error that must be expected in predicting properties of a novel external set of compounds, which is not a random sample selected from the training set. The second problem is that an external set can be arbitrarily large or small and have an arbitrary and uneven distribution of the measured value of the target variable, whose values are not known in advance. In these conditions, the correlation coefficient can be an overoptimistic measure of agreement of predicted values with the corresponding experimental values and can lead to a highly optimistic conclusion about the predictive ability of the model. Due to these shortcomings of the correlation coefficient, the use of standard error (root-mean-square-error) of prediction is suggested as a better quality measure of predictive capabilities of a model. In the case of classification models, the use of the difference between the real accuracy and the most probable random accuracy of the model shows very good characteristics in ranking different models according to predictive quality, having at the same time an obvious interpretation.

Prediction of two-dimensional gas chromatography time-of-flight mass spectrometry retention times of 160 pesticides and 25 environmental organic pollutants in grape by multivariate chemometrics methods

A quantitative structure–retention relation (QSRR) study was conducted on the retention times of 160 pesticides and 25 environmental organic pollutants in wine and grape. The genetic algorithm was used as descriptor selection and model development method. Modeling of the relationship between selected molecular descriptors and retention time was achieved by linear (partial least square; PLS) and nonlinear (kernel PLS: KPLS and Levenberg-Marquardt artificial neural network; L-M ANN) methods. The QSRR models were validated by cross-validation as well as application of the models to predict the retention of external set compounds, which did not have contribution in model development steps. Linear and nonlinear methods resulted in accurate prediction whereas more accurate results were obtained by L-M ANN model. The best model obtained from L-M ANN showed a good R2 value (determination coefficient between observed and predicted values) for all compounds, which was superior to those of other statistical models. This is the first research on the QSRR of the compounds in wine and grape against the retention time using the GA-KPLS and L-M ANN.

Chemometric modeling of aquatic toxicity of contaminants of emerging concern (CECs) in Dugesia japonica and its interspecies correlation with daphnia and fish: QSTR and QSTTR approaches

The contaminants of emerging concern (CEC) are universally detected in surface water and soil. They can affect the wild life, and their subsequent translocation through the food chain can affect human health, which is an issue of serious concern. Very few amounts of ecotoxicological data are available on the environmental behavior and ecotoxicity of CEC, thus modeling approaches are essential to bridge the existing gap in experimental data. In this present study, we have developed quantitative structure-toxicity relationship (QSTR) models using a data set of 75 compounds for the prediction of aquatic ecotoxicity of CECs on fresh water planarian (Dugesia japonica) by partial least squares (PLS) regression algorithm using simple molecular descriptors selected by genetic algorithm approach. We also explore the correlations between toxicity against D. japonica and those against daphnia (D. magna) and fish (P. promelas), and these were improved on addition of a few molecular descriptors (B08[C-O] and B09[N-O] in case of daphnia and C-006 and H-052 in case of fish) which allowed us to develop predictive interspecies quantitative structure toxicity-toxicity relationship (QSTTR) models, allowing to extrapolate data from one endpoint to another endpoint. The QSTR (Q2LOO ranging from 0.630 to 0.720 and R2pred ranging from 0.723 to 0.798) and QSTTR (Q2LOO = 0.60 and 0.67, R2pred = 0.88 and 0.84) models have desirable statistical qualities and acceptable internal and external validation measures, meeting rigorous criteria of different validation metrics and showing acceptability for regulatory purposes as proposed by Organization for Economic Cooperation and Development (OECD). Consensus predictions were also performed based on multiple models generated in this study by using the “Intelligent Consensus Predictor” (ICP) tool to enhance the prediction quality for external set compounds.

Toxic Colors: The Use of Deep Learning for Predicting Toxicity of Compounds Merely from Their Graphic Images.

The majority of computational methods for predicting toxicity of chemicals are typically based on "nonmechanistic" cheminformatics solutions, relying on an arsenal of QSAR descriptors, often vaguely associated with chemical structures, and typically employing "black-box" mathematical algorithms. Nonetheless, such machine learning models, while having lower generalization capacity and interpretability, typically achieve a very high accuracy in predicting various toxicity endpoints, as unambiguously reflected by the results of the recent Tox21 competition. In the current study, we capitalize on the power of modern AI to predict Tox21 benchmark data using merely simple 2D drawings of chemicals, without employing any chemical descriptors. In particular, we have processed rather trivial 2D sketches of molecules with a supervised 2D convolutional neural network (2DConvNet) and demonstrated that the modern image recognition technology results in prediction accuracies comparable to the state-of-the-art cheminformatics tools. Furthermore, the performance of the image-based 2DConvNet model was comparatively evaluated on an external set of compounds from the Prestwick chemical library and resulted in experimental identification of significant and previously unreported antiandrogen potentials for several well-established generic drugs.

Identifying natural compounds as multi-target-directed ligands against Alzheimer’s disease: an in silico approach

Alzheimer’s disease (AD) is a multi-factorial disease, which can be simply outlined as an irreversible and progressive neurodegenerative disorder with an unclear root cause. It is a major cause of dementia in old aged people. In the present study, utilizing the structural and biological activity information of ligands for five important and mostly studied vital targets (i.e. cyclin-dependant kinase 5, β-secretase, monoamine oxidase B, glycogen synthase kinase 3β, acetylcholinesterase) that are believed to be effective against AD, we have developed five classification models using linear discriminant analysis (LDA) technique. Considering the importance of data curation, we have given more attention towards the chemical and biological data curation, which is a difficult task especially in case of big data-sets. Thus, to ease the curation process we have designed Konstanz Information Miner (KNIME) workflows, which are made available at http://teqip.jdvu.ac.in/QSAR_Tools/. The developed models were appropriately validated based on the predictions for experiment derived data from test sets, as well as true external set compounds including known multi-target compounds. The domain of applicability for each classification model was checked based on a confidence estimation approach. Further, these validated models were employed for screening of natural compounds collected from the InterBioScreen natural database (https://www.ibscreen.com/natural-compounds). Further, the natural compounds that were categorized as ‘actives’ in at least two classification models out of five developed models were considered as multi-target leads, and these compounds were further screened using the drug-like filter, molecular docking technique and then thoroughly analyzed using molecular dynamics studies. Finally, the most potential multi-target natural compounds against AD are suggested.

Synthesis, biological evaluation and molecular modeling of a novel series of 7-azaindole based tri-heterocyclic compounds as potent CDK2/Cyclin E inhibitors

From four molecules, inspired by the structural features of fascaplysin, with an interesting potential to inhibit cyclin-dependent kinases (CDKs), we designed a new series of tri-heterocyclic derivatives based on 1H-pyrrolo[2,3-b]pyridine (7-azaindole) and triazole heterocycles. Using a Huisgen type [3 + 2] cycloaddition as the convergent key step, 24 derivatives were synthesized and their biological activities were evaluated. Comparative molecular field analysis (CoMFA), based on three-dimensional quantitative structure–activity relationship (3D-QSAR) studies, was conducted on a series of 30 compounds from the literature with high to low known inhibitory activity towards CDK2/cyclin E and was validated by a test set of 5 compounds giving satisfactory predictive r2 value of 0.92. Remarkably, it also gave a good prediction of pIC50 for our tri-heterocyclic series which reinforce the validation of this model for the pIC50 prediction of external set compounds. The most promising compound, 43, showed a micro-molar range inhibitory activity against CDK2/cyclin E and also an antiproliferative and proapoptotic activity against a panel of cancer cell lines.

Structural findings of quinolone carboxylic acids in cytotoxic, antiviral, and anti-HIV-1 integrase activity through validated comparative molecular modeling studies

Validated comparative 2D- and 3D-QSAR modeling and docking studies were performed for forty-five quinolone carboxylic acids having cytotoxic, antiviral, and anti-HIV-1 IN activity. Statistically significant 2D-QSAR model was developed through MLR and PLS analyses on unsplitted as well as splitted dataset and validated. The models were validated on external set compounds. Chemical potential, Mulliken charge at C8, and ETSA index at C3 are important for cytotoxicity. Global hardness, electrophilic frontier electron density at C10, ETSA index at O21, and C13 play pivotal role for antiviral activity. Mulliken charge at C5, ETSA index at C14, RTSA index at C8, and C13 and LUMO density on C7 are important for anti-HIV-1 IN activity. HQSAR study suggested that maximum contributing fragments include C2 and C14 and substitutions at C13 and C14 for anti-HIV-1 IN activity and antiviral activity, respectively. The positively contributing fragments include C8, C9, C10, C11, and C16 are beneficial for cytotoxicity. CoMFA study suggested that favorable steric region located near C14 is important for anti-HIV-1 IN activity, steric factor at C8 substitution is important for antiviral and cytotoxicity activities. CoMSIA study correlates the steric region found in CoMFA study; hydrophobic favorable regions are located around C8 and near C13. For antiviral activity, unfavorable hydrogen bond acceptor region is observed near C8 substitution, favorable hydrogen bond acceptor region is observed at N1 substitution. For cytotoxic activity, favorable electrostatic region is located around quinolone and benzene ring. Docking study suggested that Glu152, Gln148, and Asn155 residues of the HIV-1 integrase enzyme bind with the molecule.

Quantitative Structure-Property Relationship Study for Prediction of Flash Point of Some Organic Compounds Based On SW-MLR Method

A quantitative structure-property relationship (QSPR) model was developed for prediction of logFP values of some of organic compounds based on their molecular descriptors. In this study, we have attempted to develop a simple and fast multiple linear regression (MLR) model with high accuracy and precision. The molecular descriptors, which cover different information of molecular structures, were calculated by Dragon software. The most feasible descriptors were selected using stepwise selection. The QSPR model was validated by external set compounds without any contribution in model development step. The accuracy of the suggested model is illustrated using cross-validation, validation through an external test set and Y-randomization. The obtained multivariate linear three descriptors model by MLR has correlation coefficient (R2=0.905, Q2LGO = 0.844, Q2LGO=0.833, REP%=-7.807, F=47.626). All molecular descriptors which have entered in this model are calculated from chemical structure of any molecule. This model was used for the prediction of the flash point values of some organic compounds which were not used in the modeling procedure.

Linear and Nonlinear QSAR Study of N2 and O6 Substituted Guanine Derivatives as Cyclin-Dependent Kinase 2 Inhibitors

The inhibitory activities (pIC50) of N2 and O6 substituted guanine derivatives as cyclin-dependent kinase 2 (CDK2) inhibitors have been successfully modeled using calculated molecular descriptors. Two linear (MLR) and nonlinear (ANN) methods were utilized for construction of models to predict the pIC50 activities of those compounds. The QSAR models were validated by cross-validation (leave-one-out) as well as application of the models for prediction of pIC50 of external set compounds. Also, the models were validated by calculation of statistical parameters and Y-randomization test. Two methods provided accurate predictions, although more accurate results were obtained by ANN model. The mean-squared errors (MSEs) for validation and test sets of MLR are 0.065, 0.069 and of ANN are 0.017 and 0.063, respectively.

Structure-based 3D-QSAR models and dynamics analysis of novel N-benzyl pyridinone as p38α MAP kinase inhibitors for anticytokine activity

A novel series of anticytokine N-benzyl pyridinone derivatives that targets p38α MAP kinase has been analyzed by utilizing a combination of molecular modeling techniques. Statistically significant structure-based 3D-QSAR models were generated for both CoMFA and CoMSIA, and validated through acceptable predictive ability to support both internal and external set of compounds. Structural changes within the protein key backbone residues (Met109 and Gly110), DFG loop position, and side chain movements (Lys53 and Asn114) as resulted by different substituents on these inhibitors were also examined by molecular dynamics simulation. The protocol applied in this study could be helpful to rationalize potent compounds with better inhibitory activity and selectivity profiles against p38α MAP kinase.

Quantitative Structure-Retention Index Relationship (QSRIR) Study of Monomethylalkanes on the Methylsilicone OV-1 Stationary Phase

A back-propagation artificial neural network (ANN) is used to create a model of gas chromatography retention indices for a data set of 196 monomethylalkanes on the methylsilicone OV-1 stationary phase. Multlinear regression (MLR) model of the same data is developed for comparison. The quantitative structure-property relationship (QSPR) models are validated by cross-validation as well as application of the models for prediction of retention indices of external set of compounds which do not have contribution to model development steps. The models are also validated by statistical parameters and Y-randomization. Both linear and non-linear methods provide accurate predictions. The mean-squared errors (MSE) for validation and test sets for MLR are 18.44 and 28.96, and those for ANN are 2.24 and 4.21, respectively.

QSPR predictions of heat of fusion of organic compounds using Bayesian regularized artificial neural networks

Computational approaches for the prediction of environmental pollutants' properties have great potential in rapid environmental risk assessment and management with reduced experimental cost. A quantitative structure–property relationship (QSPR) study was conducted to predict the heat of fusion of a set of organic compounds that have adverse effect on the environment. The forward selection (FS) strategy was used for descriptors selection. We examined the feasibility of using multiple linear regression (MLR), artificial neural networks (ANN) and Bayesian regularized artificial neural networks (BRANN) as linear and nonlinear methods. The QSPR models were validated by an external set of compounds that were not used in the model development stage. All models reliably predicted the heat of fusion of the organic compounds under study, whereas more accurate results were obtained by the BRANN model.

Prediction of the Hildebrand parameter of various solvents using linear and nonlinear approaches

The Hildebrand solubility parameter ( δ) provides a numerical estimate of the degree of interaction between materials, and can be a good indication of solubility. In this work, a small number of physicochemical variables were appropriately selected from a pool of Dragon descriptors and correlated with the Hildebrand thermodynamic parameter of compounds previously studied as organic solvents of buckminsterfullerene (C 60), using multiple linear regression and support vector machines. Models were validated using an external set of compounds and the statistical parameters obtained revealed the high prediction performance of all models, especially the one based on nonlinear regression. These findings provide useful information about which solvent and corresponding characteristics are important for solubility studies of e.g. this increasingly useful carbon allotrope.