Predictive Quantitative Structure-activity Relationship Models Research Articles

QSAR modeling of algal low level toxicity values of different phenol and aniline derivatives using 2D descriptors

The deposition of different types of phenol and aniline derivatives in the aquatic environment leads to toxicity to living organisms. Under such condition, evaluation of these toxicants is very much important. Due to non-availability of sufficient experimental data as well as sufficient number of Quantitative Structure-Activity Relationship (QSAR) models for the low level toxicity values for such pollutants, we have employed here the partial least squares (PLS) regression for the development of robust and predictive QSAR models using low level toxicity values against algal species. Here, we have used both Extended Topochemical Atom (ETA) and non-ETA indices as 2D descriptors for model development. The statistical validation parameters ensure the robustness and the predictivity of the developed models. From the insights of the final PLS models, it can be concluded that presence of nitro groups (in the ortho position to phenolic hydroxyl group increasing intramolecular hydrogen bonding capacity), presence of chlorine substituents (influencing lipophilicity) especially at the para position, oxygen and nitrogen at the topological distance three, aliphatic side chain (contributing to hydrophobicity), molecules with large size atoms and higher molecular bulk will increase the toxicity towards the algal species. On the other hand, the phenol ring without any substituent or with a polar substituent (like amino group), presence of chlorine at ortho-ortho or ortho-para position, absence of nitro group, presence of chlorine and oxygen at the topological distance three, presence of lower number of aliphatic groups will decrease the toxic effect towards the algal species.

QSAR models for the fumigant activity prediction of essential oils

The Quantitative Structure-Activity Relationships (QSAR) theory, which allows predicting the insecticidal activity of chemical compounds through calculations from the molecular structure, is applied on 23 essential oils composed of 402 structurally diverse compounds at different chemical compositions. A large number of 114,871 conformation-independent molecular descriptors are computed through different types of freely available open-source programs. Mixture descriptors are calculated based on molecular descriptors of the essential oil components and their composition. The best resulting three-descriptor linear regression models are established through the Replacement Method variable subset selection approach. The results obtained in the present work are interesting for predicting the fumigant activity of these essential oil complex mixtures, by means of simple non-conformational QSAR models.

A QSAR modeling approach for predicting myeloid antimicrobial peptides with high sequence similarity.

Microbial resistance to conventional antibiotics has led to a surge in antimicrobial peptide (AMP) rational design initiatives that rely heavily on algorithms with good prediction accuracy and sensitivity. We present a quantitative structure-activity relationship (QSAR) approach for predicting activity of cathelicidins, an AMP family with broad-spectrum activity. The best multiple linear regression model built against Escherichia coli ATCC 25922 could accurately predict activity of three rationally designed peptides CP, DP, and Mapcon, having high sequence similarity. On further experimental validation of the rationally designed peptides, CP was found to exhibit high antimicrobial activity with negligible hemolysis. Here, we provide CP, an AMP with potential therapeutic applications and a family-based QSAR model for AMP prediction.

Predictive QSAR models for the anti-cancer activity of topoisomerase IIα catalytic inhibitors against breast cancer cell line HCT15: GA-MLR and LS-SVM modeling

Structural analysis of topoisomerase IIα catalytic inhibitors exhibited anti-tumor properties to use them in cancer therapeutic procedures. In this study, a quantitative structure-activity relationship (QSAR) modeling including multiple linear regression (MLR) and least squares-support vector machine (LS-SVM) analysis was applied on a series of 46 synthesized xanthone derivatives as topoisomerase IIα inhibitors. It was aimed to predict half-maximal inhibitory activity (IC50) of the compounds against breast cancer cell line HCT15 using the best computational method with the least error prediction. Genetic algorithm multiple linear regression (GA-MLR) explored the functional parameters of the final models. The achieved QSAR models presented a reliable relationship between chemical structure properties as descriptors and the inhibitory activities of compounds. The models were confirmed using Leave one out-cross-validation (LOO-CV) method (for the best linear model including whole dataset R2 = 0.955, Q2 = 0.930, RMSE = 0.151, F = 115.593 and for the best non-linear model R2 = 0.981, Q2 = 0.971, RMSE = 0.099, F = 258.902). So, it was demonstrated that these models especially non-linear models are predictive models of high quality that can produce appropriate inhibitory activity prediction of the compounds to use them in pharmaceutical industries.

Quantitative Structure-Activity Relationship Models for Predicting Inflammatory Potential of Metal Oxide Nanoparticles.

Background:Although substantial concerns about the inflammatory effects of engineered nanomaterial (ENM) have been raised, experimentally assessing toxicity of various ENMs is challenging and time-consuming. Alternatively, quantitative structure–activity relationship (QSAR) models have been employed to assess nanosafety. However, no previous attempt has been made to predict the inflammatory potential of ENMs.Objectives:By employing metal oxide nanoparticles (MeONPs) as a model ENM, we aimed to develop QSAR models for prediction of the inflammatory potential by their physicochemical properties.Methods:We built a comprehensive data set of 30 MeONPs to screen a proinflammatory cytokine interleukin (IL)-1 beta () release in THP-1 cell line. The in vitro hazard ranking was validated in mouse lungs by oropharyngeal instillation of six randomly selected MeONPs. We established QSAR models for prediction of MeONP-induced inflammatory potential via machine learning. The models were further validated against seven new MeONPs. Density functional theory (DFT) computations were exploited to decipher the key mechanisms driving inflammatory responses of MeONPs.Results:Seventeen out of 30 MeONPs induced excess production in THP-1 cells. In vivo disease outcomes were highly relevant to the in vitro data. QSAR models were developed for inflammatory potential, with predictive accuracy (ACC) exceeding 90%. The models were further validated experimentally against seven independent MeONPs (). DFT computations and experimental results further revealed the underlying mechanisms: MeONPs with metal electronegativity lower than 1.55 and positive were more likely to cause lysosomal damage and inflammation.Conclusions: released in THP-1 cells can be an index to rank the inflammatory potential of MeONPs. QSAR models based on were able to predict the inflammatory potential of MeONPs. Our approach overcame the challenge of time- and labor-consuming biological experiments and allowed for computational assessment of MeONP inflammatory potential by characterization of their physicochemical properties. https://doi.org/10.1289/EHP6508

The efficiency of ligand-receptor interaction information alone as new descriptors in QSAR modeling via random forest artificial neural network.

A new approach is introduced for the construction of a predictive quantitative structure-activity relationship model in which only ligand-receptor (LR) interaction features are used as relevant descriptors. This approach combines the benefit of the random forest (RF) as a new variable selection method with the intrinsic capability of the artificial neural network (ANN). The interaction information of the ligand-receptor (LR) complex was used as molecular docking descriptors. The most relevant descriptors were selected using the RF technique and used as inputs of ANN. The proposed RF ANN (RF-LM-ANN) method was optimized and then evaluated by the prediction of pEC50 for some of the azine derivatives as non-nucleoside reverse transcriptase inhibitors. RF-LM-ANN model under the optimal conditions was evaluated using internal (validation) and external test sets. The determination coefficients of the external test and validation sets were 0.88 and 0.89, respectively. The mean square deviation (MSE) values for the prediction of biological activities in the external test and validation sets were found to be 0.10 and 0.11, respectively. The results obtained demonstrated the good prediction ability and high generalizability of the proposed RF-LM-ANN model based on the MMDs alone.

Novel and Predictive QSAR Model for Steroidal and Nonsteroidal 5α- Reductase Type II Inhibitors.

In this study, a novel quantitative structure activity relationship (QSAR) model has been developed for inhibitors of human 5-alpha reductase type II, which are used to treat benign prostate hypertrophy (BPH). The dataset consisted of 113 compounds-mainly nonsteroidal-with known inhibitory concentration. Then 3D structures of compounds were optimized and molecular structure descriptors were calculated. The stepwise multiple linear regression was used to select descriptors encoding the inhibitory activity of the compounds. Multiple linear regression (MLR) was used to build up the linear QSAR model. The results obtained revealed that the descriptors which best describe the activity were atom type electropological state, carbon type, radial distribution function (RDF), barysz matrix and molecular linear free energy relation. The suggested model could achieve satisfied square correlation coefficient of R2 = 0.72, higher than of many previous studies, indicating its superiority. Rigid validation criteria were met using external data with Q2 ˃ 0.5 and R2 = 0.75, reflecting the predictive power of the model. The QSAR model was applied for screening botanical components of herbal preparations used to treat BPH, and could predict the activity of some, among others, making reasonable attribution to the proposed effect of these preparations. Gamma tocopherol was found to be an active inhibitor, in consistence with many previous studies, anticipating the power of this model in the prediction of new candidate molecules and suggesting further investigations.

A novel strategy for prediction of human plasma protein binding using machine learning techniques

Plasma protein binding (PPB) is a key player of drug ADME (absorption, distribution, metabolism, elimination) behaviors, enabling PPB to have significant impact on drug efficacy and toxicity. As drug discovery enters the era of rational drug design, it is desirable to use in silico model to predict PPB so as to achieve rapid initial screening for potential candidate compounds prior to further time-consuming and costly in vitro and in vivo experimental assay. In this study, a global quantitative structure-activity relationship (QSAR) model of PPB was built on the basis of a large training set comprising more than 5000 compounds to represent large structural diversity. The uneven distribution of PPB was often rectified by two mathematical transformations of PPB but this led to a decrease in prediction accuracy at the lower binding level. To resolve this problem, we proposed a novel strategy to build models for different binding levels. The best model yielded much lower mean absolute error (MAE) of 0.076 on the test set than published models and the MAE was further reduced to 0.041 ​at the high level of binding (0.8–1). The models also performed excellent in the validation set containing some compounds from traditional Chinese medicine. In addition, the applicability domain was determined to identify new compounds which are appropriate for prediction using our built models. In conclusion, this study developed a novel strategy to construct robust QSAR model for PPB prediction which could be used by chemists to predict the PPB of candidate compounds efficiently and make structural modification in the early stage of drug development.

Benchmarking Small-Dataset Structure-Activity-Relationship Models for Prediction of Wnt Signaling Inhibition

Quantitative structure-activity relationship (QSAR) models based on machine learning algorithms are powerful tools to expedite drug discovery processes and therapeutics development. Given the cost in acquiring large-sized training datasets, it is useful to examine if QSAR analysis can reasonably predict drug activity with only a small-sized dataset (size <; 100) and benchmark these small-dataset QSAR models in application-specific studies. To this end, here we present a systematic benchmarking study on small-dataset QSAR models built for prediction of effective Wnt signaling inhibitors, which are essential to therapeutics development in prevalent human diseases (e.g., cancer). Specifically, we examined a total of 72 two-dimensional (2D) QSAR models based on 4 best-performing algorithms, 6 commonly used molecular fingerprints, and 3 typical fingerprint lengths. We trained these models using a training dataset (56 compounds), benchmarked their performance on 4 figures-of-merit (FOMs), and examined their prediction accuracy using an external validation dataset (14 compounds). Our data show that the model performance is maximized when: 1) molecular fingerprints are selected to provide sufficient, unique, and not overly detailed representations of the chemical structures of drug compounds; 2) algorithms are selected to reduce the number of false predictions due to class imbalance in the dataset; and 3) models are selected to reach balanced performance on all 4 FOMs. These results may provide general guidelines in developing high-performance small-dataset QSAR models for drug activity prediction.

QSAR models for analgesic activity prediction of terpenes and their derivatives

In the present study, quantitative structure-activity relationship (QSAR) models were developed to predict analgesic activity of some mono-/bicyclic terpenoids and their esters with neurotransmitter amino acids. All the models were developed using structural descriptors calculated by SiRMS approach based on the simplex representation of the molecular structure. Log P, molecular refraction, electronegativity, and molecular mass were used as integral descriptors additionally to calculated 2D simplex descriptors. Predictive QSAR models were obtained using the partial least squares (PLS) method. The analysis of structural factors influence on the manifestation of analgesic activity for studied compounds was carried out in the following pharmacological tests: capsaicin, formalin, allylisothiocyanate, and “hot plate” tests. We found that the most significant contribution to analgesic action in all pharmacological tests exhibited molecular fragments representing menthol and borneol residues. Also, we may conclude that –OH group substitution in terpenoid molecules for GABA or glycine residues leads to enhancement of analgesic effect due to the presence of additional highly reactive C=O and N–H groups playing the role of H-bond donors/acceptors.

Open-source QSAR models for pKa prediction using multiple machine learning approaches

BackgroundThe logarithmic acid dissociation constant pKa reflects the ionization of a chemical, which affects lipophilicity, solubility, protein binding, and ability to pass through the plasma membrane. Thus, pKa affects chemical absorption, distribution, metabolism, excretion, and toxicity properties. Multiple proprietary software packages exist for the prediction of pKa, but to the best of our knowledge no free and open-source programs exist for this purpose. Using a freely available data set and three machine learning approaches, we developed open-source models for pKa prediction.MethodsThe experimental strongest acidic and strongest basic pKa values in water for 7912 chemicals were obtained from DataWarrior, a freely available software package. Chemical structures were curated and standardized for quantitative structure–activity relationship (QSAR) modeling using KNIME, and a subset comprising 79% of the initial set was used for modeling. To evaluate different approaches to modeling, several datasets were constructed based on different processing of chemical structures with acidic and/or basic pKas. Continuous molecular descriptors, binary fingerprints, and fragment counts were generated using PaDEL, and pKa prediction models were created using three machine learning methods, (1) support vector machines (SVM) combined with k-nearest neighbors (kNN), (2) extreme gradient boosting (XGB) and (3) deep neural networks (DNN).ResultsThe three methods delivered comparable performances on the training and test sets with a root-mean-squared error (RMSE) around 1.5 and a coefficient of determination (R2) around 0.80. Two commercial pKa predictors from ACD/Labs and ChemAxon were used to benchmark the three best models developed in this work, and performance of our models compared favorably to the commercial products.ConclusionsThis work provides multiple QSAR models to predict the strongest acidic and strongest basic pKas of chemicals, built using publicly available data, and provided as free and open-source software on GitHub.

Quantitative Structure-Activity Relationship Study of Camptothecin Derivatives as Anticancer Drugs Using Molecular Descriptors.

A Quantitative Structure-Activity Relationship (QSAR) has been widely developed to derive a correlation between chemical structures of molecules to their known activities. In the present investigation, QSAR models have been carried out on 76 Camptothecin (CPT) derivatives as anticancer drugs to develop a robust model for the prediction of physicochemical properties. A training set of 60 structurally diverse CPT derivatives was used to construct QSAR models for the prediction of physiochemical parameters such as Van der Waals surface area (SvdW), Van der Waals Volume (VvdW), Molar Refractivity (MR) and Polarizability (α). The QSAR models were optimized using Multiple Linear Regression (MLR) analysis. A test set of 16 compounds was evaluated using the defined models. The Genetic Algorithm And Multiple Linear Regression Analysis (GA-MLR) were used to select the descriptors derived from the Dragon software to generate the correlation models that relate the structural features to the studied properties. QSAR models were used to delineate the important descriptors responsible for the properties of the CPT derivatives. The statistically significant QSAR models derived by GA-MLR analysis were validated by Leave-One-Out Cross-Validation (LOOCV) and test set validation methods. The multicollinearity and autocorrelation properties of the descriptors contributed in the models were tested by calculating the Variance Inflation Factor (VIF) and the Durbin-Watson (DW) statistics. The predictive ability of the models was found to be satisfactory. Thus, QSAR models derived from this study may be helpful for modeling and designing some new CPT derivatives and for predicting their activity.

QSAR and molecular docking studies on 4-quinoline carboxylic acid derivatives as inhibition of vesicular stomatitis virus replication

The current study describes the development of in silico models based on quantitative structure-activity relationship (QSAR) analysis has been performed on 4-quinoline carboxylic acid derivatives as inhibition capacity of vesicular stomatitis virus replication in Madin Darby canine kidney epithelial cells. A highly descriptive and predictive QSAR model was obtained through the calculation of alignment-independent descriptors using MOE 2009.10 software. For a training set of 20 compounds, the partial least squares analyses result in a model which displays a squared correlation coefficient (r2) of 0.913. Validation of this model was performed using leave-one-out (q2) of 0.842. This model gives (r2pre) of 0.889 for a test set of five compounds. Docking studies were performed for 25 compounds to investigate the mode of interaction between 4-quinoline carboxylic acid derivatives and the active site of the human dihydroorotate dehydrogenase.

Chemistry-Wide Association Studies (CWAS): A Novel Framework for Identifying and Interpreting Structure-Activity Relationships.

Quantitative structure-activity relationships (QSAR) models are often seen as a "black box" because they are considered difficult to interpret. Meanwhile, qualitative approaches, e.g., structural alerts (SA) or read-across, provide mechanistic insight, which is preferred for regulatory purposes, but predictive accuracy of such approaches is often low. Herein, we introduce the chemistry-wide association study (CWAS) approach, a novel framework that both addresses such deficiencies and combines advantages of statistical QSAR and alert-based approaches. The CWAS framework consists of the following steps: (i) QSAR model building for an end point of interest, (ii) identification of key chemical features, (iii) determination of communities of such features disproportionately co-occurring more frequently in the active than in the inactive class, and (iv) assembling these communities to form larger (and not necessarily chemically connected) novel structural alerts with high specificity. As a proof-of-concept, we have applied CWAS to model Ames mutagenicity and Stevens-Johnson Syndrome (SJS). For the well-studied Ames mutagenicity data set, we identified 76 important individual fragments and assembled co-occurring fragments into SA both replicative of known as well as representing novel mutagenicity alerts. For the SJS data set, we identified 29 important fragments and assembled co-occurring communities into SA including both known and novel alerts. In summary, we demonstrate that CWAS provides a new framework to interpret predictive QSAR models and derive refined structural alerts for more effective design and safety assessment of drugs and drug candidates.

Optimal Piecewise Linear Regression Algorithm for QSAR Modelling.

Quantitative Structure-Activity Relationship (QSAR) models have been successfully applied to lead optimisation, virtual screening and other areas of drug discovery over the years. Recent studies, however, have focused on the development of models that are predictive but often not interpretable. In this article, we propose the application of a piecewise linear regression algorithm, OPLRAreg, to develop both predictive and interpretable QSAR models. The algorithm determines a feature to best separate the data into regions and identifies linear equations to predict the outcome variable in each region. A regularisation term is introduced to prevent overfitting problems and implicitly selects the most informative features. As OPLRAreg is based on mathematical programming, a flexible and transparent representation for optimisation problems, the algorithm also permits customised constraints to be easily added to the model. The proposed algorithm is presented as a more interpretable alternative to other commonly used machine learning algorithms and has shown comparable predictive accuracy to Random Forest, Support Vector Machine and Random Generalised Linear Model on tests with five QSAR data sets compiled from the ChEMBL database.

QSAR Study on Antioxidant Tripeptides and the Antioxidant Activity of the Designed Tripeptides in Free Radical Systems.

In this study, quantitative structure-activity relationship (QSAR) models were determined based on 91 antioxidant tripeptides. We firstly adopted the stepwise regression (SWR) method for selecting key variables without autocorrelation and then utilized multiple linear regression (MLR), support vector machine (SVM), random forest (RF), and partial least square regression (PLS) to develop predictive QSAR models based on the screened variables. The results demonstrated that all the established models have good reliability (R2train > 0.86, Q2train > 0.70) and relatively good predictability (R2test > 0.88). The contribution of amino acid residues was calculated from the stepwise regression combined with multiple linear regression (SWR-MLR) method model that shows Trp, Tyr, or Cys at C-terminus is favorable for antioxidant activity of tripeptides. Nineteen antioxidant tripeptides were designed based on SWR-MLR models, and the antioxidant activity of these tripeptides were evaluated using three antioxidant assays in free radical systems (1,1-diphenyl-2-picrylhydrazyl (DPPH) radical scavenging capacity, trolox equivalent antioxidant capacity assay, and the ferric reducing antioxidant power assay). The experimental antioxidant activities of these tripeptides were higher than the calculated/predicted activity values of the QSAR models. The QSAR models established can be used to identify and screen novel antioxidant tripeptides with high activity.

Classical and 3D QSAR studies of larvicidal monoterpenes against Aedes aegypti: new molecular insights for the rational design of more active compounds

Monoterpenes are compounds found on essential oils of diverse plants, with biological activities such as repellent, insecticidal and larvicidal against some organism and microorganism species. Dengue, Chikungunya, and Zika are important public health problems caused by viruses, which are transmitted by the bite of Aedes aegypti mosquitoes. One of the most common strategies to combat these diseases is the control of the vector proliferation, by physical and chemical methods. Thus, the design, synthesis, and test of the compounds with larvicidal profile have emerged as an important research line. In this paper, we present the use of computational approaches to provide robust, predictive, and conveniently interpretable quantitative structure-activity relationships models, involving a series of 55 monoterpenes and structurally related compounds, which presented larvicidal activity against females of Aedes aegypti, expressed by IC50. Through the proposition and analysis of 2D and 3D molecular descriptors, consistent and easily understood molecular bases about larvicidal activity are provided, for the proposition of new molecules with more active profile. Theoretical geometry optimization of the 55 compounds was performed using the PM6 semiempirical Hamiltonian, followed by B3LYP/6-31+G(d) level of theory, using Gaussian 09W® package. A set of classical descriptors was obtained from Dragon® software for each compound and submitted to a variable selection procedure, using the Ordered Predictors Selector (OPS) algorithm, considering larvicidal (pIC50) activities previously reported. Then, a 3D quantitative structure-activity relationship (QSAR) investigation was performed by Open3DQSAR program, using the same values of activity, for the investigation of sterical and electrostatic molecular fields. For classical QSAR, five descriptors were selected as the most important, providing a robust and predictive QSAR model via multiple linear regression (MLR). In addition, a good 3D-QSAR model was found, with a clear interpretation of the physical sense of the fields, according to the classical model. Molecules with more elongated structures contain a six-membered ring with 1,4 substitution pattern, highest lipophilicity, less volume on a central moiety, and lateral hydrophobic chain at six-membered ring, tend to be more actives.

Effect of dissolved organic matter on pre-equilibrium passive sampling: A predictive QSAR modeling study

Pre-equilibrium passive sampling is a simple and promising technique for studying sampling kinetics, which is crucial to determine the distribution, transfer and fate of hydrophobic organic compounds (HOCs) in environmental water and organisms. Environmental water samples contain complex matrices that complicate the traditional calibration process for obtaining the accurate rate constants. This study proposed a QSAR model to predict the sampling rate constants of HOCs (polycyclic aromatic hydrocarbons (PAHs), polychlorinated biphenyls (PCBs) and pesticides) in aqueous systems containing complex matrices. A homemade flow-through system was established to simulate an actual aqueous environment containing dissolved organic matter (DOM) i.e. humic acid (HA) and (2-Hydroxypropyl)-β-cyclodextrin (β-HPCD)), and to obtain the experimental rate constants. Then, a quantitative structure-activity relationship (QSAR) model using Genetic Algorithm-Multiple Linear Regression (GA-MLR) was found to correlate the experimental rate constants to the system state including physicochemical parameters of the HOCs and DOM which were calculated and selected as descriptors by Density Functional Theory (DFT) and Chem 3D. The experimental results showed that the rate constants significantly increased as the concentration of DOM increased, and the enhancement factors of 70-fold and 34-fold were observed for the HOCs in HA and β-HPCD, respectively. The established QSAR model was validated as credible (RAdj.2=0.862) and predictable (Q2=0.835) in estimating the rate constants of HOCs for complex aqueous sampling, and a probable mechanism was developed by comparison to the reported theoretical study. Main finding of the workThe present study established a QSAR model of passive sampling rate constants and calibrated the effect of DOM on the sampling kinetics.

Evaluation of the antioxidant properties of curcumin derivatives by genetic function algorithm

The prevalence of degenerative diseases in recent time has triggered extensive research on their control. This condition could be prevented if the body has an efficient antioxidant mechanism to scavenge the free radicals which are their main causes. Curcumin and its derivatives are widely employed as antioxidants. The free radical scavenging activities of curcumin and its derivatives have been explored in this research by the application of quantitative structure activity relationship (QSAR). The entire data set was optimized at the density functional theory (DFT) level using the Becke's three-parameter Lee-Yang-Parr hybrid functional (B3LYP) in combination with the 6-311G∗ basis set. The training set was subjected to QSAR studies by genetic function algorithm (GFA). Five predictive QSAR models were developed and statistically subjected to both internal and external validations. Also the applicability domain of the developed model was accessed by the leverage approach. Furthermore, the variation inflation factor, (VIF), mean effect (MF) and the degree of contribution (DC) of each descriptor in the resulting model were calculated. The developed models met all the standard requirements for acceptability upon validation with highly impressive results (R=0.965,R2=0.931,Q2(RCV2)=0.887,Rpred2=0.844,cRp2=0.842s=0.226,rmsep=0.362). Based on the results of this research, the most crucial descriptor that influence the free radical scavenge of the curcumins is the nsssN (count of atom-type E-state: >N-) descriptor with DC and MF values of 12.980 and 0.965 respectively.

Quantitative Structure Activity Relationship Analysis of Coumarins as Free Radical Scavengers by Genetic Function Algorithm

The antioxidant properties of coumarin derivatives using the 2,2ˈ -diphenyl-1- picrylhydrazyl (DPPH) radical scavenging assay were investigated by the application of Quantitative Structure Activity Relationship (QSAR) studies. The molecular structures were optimized and submitted for the generation of quantum chemical and molecular descriptors. Genetic Function Algorithm (GFA) was employed in model development. Also the applicability domain of the developed models were accessed by the leverage approach. The Variation Inflation Factor (VIF), Mean Effect (MF) and Degree of Contribution (DC) of these descriptors were estimated. Five predictive QSAR models were developed and subjected to various validation tests. The developed models gave highly encouraging results upon validation (R=0.938, R^2=0.879, Q^2=0.845, 〖R^2〗_pred=0.700 and cR_p^2= 0.832. This research indicates that the most crucial descriptors that influence the free radical scavenging activities and essential in the design of new set of the coumarin antioxidants are the HBDCount (hydrogen-bond donor count), AATS3e (Average Broto-Moreau autocorrelation - lag 3 / weighted by Sanderson electronegativities), and the MW (Molecular weight) descriptors.