The importance of molecular structures, endpoints’ values, and predictivity parameters in QSAR research: QSAR analysis of a series of estrogen receptor binders

Mechanistic QSAR modeling derived virtual screening, drug repurposing, ADMET and in-vitro evaluation to identify anticancer lead as lysine-specific demethylase 5a inhibitor

A lysine-specific demethylase is an enzyme that selectively eliminates methyl groups from lysine residues. KDM5A, also known as JARID1A or RBP2, belongs to the KDM5 Jumonji histone demethylase subfamily. To identify novel molecules that interact with the LSD5A receptor, we created a quantitative structure-activity relationship (QSAR) model. A group of 435 compounds was used in a study of the quantitative relationship between structure and activity to guess the IC50 values for blocking LASD5A. We used a genetic algorithm-multilinear regression-based quantitative structure-activity connection model to forecast the bioactivity (PIC50) of 1615 food and drug administration pharmaceuticals from the zinc database with the goal of repurposing clinically used medications. We used molecular docking, molecular dynamic simulation modelling, and molecular mechanics generalised surface area analysis to investigate the molecule's binding mechanism. A genetic algorithm and multi-linear regression method were used to make six variable-based quantitative structure-activity relationship models that worked well (R2 = 0.8521, Q2LOO = 0.8438, and Q2LMO = 0.8414). ZINC000000538621 was found to be a new hit against LSD5A after a quantitative structure-activity relationship-based virtual screening of 1615 zinc food and drug administration compounds. The docking analysis revealed that the hit molecule 11 in the KDM5A binding pocket adopted a conformation similar to the pdb-6bh1 ligand (docking score: -8.61 kcal/mol). The results from molecular docking and the quantitative structure-activity relationship were complementary and consistent. The most active lead molecule 11, which has shown encouraging results, has good absorption, distribution, metabolism, and excretion (ADME) properties, and its toxicity has been shown to be minimal. In addition, the MTT assay of ZINC000000538621 with MCF-7 cell lines backs up the in silico studies. We used molecular mechanics generalise borne surface area analysis and a 200-ns molecular dynamics simulation to find structural motifs for KDM5A enzyme interactions. Thus, our strategy will likely expand food and drug administration molecule repurposing research to find better anticancer drugs and therapies.Communicated by Ramaswamy H. Sarma.

Quantitative structure-activity relationship (QSAR) guides the development of dye removal by coagulation

QSAR modeling could be a promising tool for guiding the development of novel and cost-effective environmental technologies. As an example, it could be widely used to analyze the degradation rules of organic pollutants in various decomposition methods. However, a lack of systematic research on a particular removal method is significant in revealing the decomposition rule of pollutants more accurately and guiding industrial applications. In this study, six coagulation systems (MnO₂/Fe(OH)₃/AlCl₃/FeCl₃/CaCl₂/MgCl₂) were used as examples to remove 38 dyes under three pH conditions, and the characteristics and differences of these systems were explored by QSAR modeling. The results showed that the removal effect by MnO₂ under acidic and neutral conditions and Fe(OH)₃ under acidic conditions were quantitatively described mainly by bond order (BO) and Fukui index (f (+) and f (0)), which reflected that oxidative degradation dominated. In contrast, most of the critical parameters of other systems were molecular descriptors represented by ∑q(O) (the total charge of all the oxygen atoms in the molecule) and SAA (surface area of a molecule), which reflected that electrostatic adsorption and hydrogen-bond adsorption processes dominated.

Perceiving the Concealed and Unreported Pharmacophoric Features of the 5-Hydroxytryptamine Receptor Using Balanced QSAR Analysis

The 5-hydroxytryptamine receptor 6 (5-HT6) has gained attention as a target for developing therapeutics for Alzheimer’s disease, schizophrenia, cognitive dysfunctions, anxiety, and depression, to list a few. In the present analysis, a larger and diverse dataset of 1278 molecules covering a broad chemical and activity space was used to identify visual and concealed structural features associated with binding affinity for 5-HT6. For this, quantitative structure–activity relationships (QSAR) and molecular docking analyses were executed. This led to the development of a statistically robust QSAR model with a balance of excellent predictivity (R²_tr = 0.78, R²_ex = 0.77), the identification of unreported aspects of known features, and also novel mechanistic interpretations. Molecular docking and QSAR provided similar as well as complementary results. The present analysis indicates that the partial charges on ring carbons present within four bonds from a sulfur atom, the occurrence of sp3-hybridized carbon atoms bonded with donor atoms, and a conditional occurrence of lipophilic atoms/groups from nitrogen atoms, which are prominent but unreported pharmacophores that should be considered while optimizing a molecule for 5-HT6. Thus, the present analysis led to identification of some novel unreported structural features that govern the binding affinity of a molecule. The results could be beneficial in optimizing the molecules for 5-HT6.

Exploring the Prominent and Concealed Inhibitory Features for Cytoplasmic Isoforms of Hsp90 Using QSAR Analysis

Cancer is a major life-threatening disease with a high mortality rate in many countries. Even though different therapies and options are available, patients generally prefer chemotherapy. However, serious side effects of anti-cancer drugs compel us to search for a safer drug. To achieve this target, Hsp90 (heat shock protein 90), which is responsible for stabilization of many oncoproteins in cancer cells, is a promising target for developing an anti-cancer drug. The QSAR (Quantitative Structure–Activity Relationship) could be useful to identify crucial pharmacophoric features to develop a Hsp90 inhibitor. Therefore, in the present work, a larger dataset encompassing 1141 diverse compounds was used to develop a multi-linear QSAR model with a balance of acceptable predictive ability (Predictive QSAR) and mechanistic interpretation (Mechanistic QSAR). The new developed six-parameter model satisfies the recommended values for a good number of validation parameters such as R2tr = 0.78, Q2LMO = 0.77, R2ex = 0.78, and CCCex = 0.88. The present analysis reveals that the Hsp90 inhibitory activity is correlated with different types of nitrogen atoms and other hidden structural features such as the presence of hydrophobic ring/aromatic carbon atoms within a specific distance from the center of mass of the molecule, etc. Thus, the model successfully identified a variety of reported as well as novel pharmacophoric features. The results of QSAR analysis are further vindicated by reported crystal structures of compounds with Hsp90.

QSARINS-Chem standalone version: A new platform-independent software to profile chemicals for physico-chemical properties, fate, and toxicity

The new software QSARINS-Chem standalone version is a multiplatform tool, freely downloadable, for the in silico profiling of multiple properties and activities of organic chemicals. This software, which is based on the concept of the QSARINS-chem module embedded in the QSARINS software, has been fully redesigned and redeveloped in the Java™ language. In addition to a selection of models included in the old module, the new software predicts biotransformation rates and aquatic toxicities of pharmaceuticals and personal care products in multiple organisms, and offers a suite of tools for the analysis of predictions. Furthermore, a comprehensive and transparent database of molecular structures is provided. The new QSARINS-Chem standalone version is an informative and solid tool, which is useful to support the assessment of the potential hazard and risks related to organic chemicals and is dedicated to users which are interested in the application of QSARs to generate reliable predictions.

Machine Learning Strategies When Transitioning between Biological Assays

Machine learning is widely used in drug development to predict activity in biological assays based on chemical structure. However, the process of transitioning from one experimental setup to another for the same biological endpoint has not been extensively studied. In a retrospective study, we here explore different modeling strategies of how to combine data from the old and new assays when training conformal prediction models using data from hERG and Na_V assays. We suggest to continuously monitor the validity and efficiency of models as more data is accumulated from the new assay and select a modeling strategy based on these metrics. In order to maximize the utility of data from the old assay, we propose a strategy that augments the proper training set of an inductive conformal predictor by adding data from the old assay but only having data from the new assay in the calibration set, which results in valid (well-calibrated) models with improved efficiency compared to other strategies. We study the results for varying sizes of new and old assays, allowing for discussion of different practical scenarios. We also conclude that our proposed assay transition strategy is more beneficial, and the value of data from the new assay is higher, for the harder case of regression compared to classification problems.

Nutritional implications of ginger: chemistry, biological activities and signaling pathways

Ginger (Zingiber officinale Roscoe) has been used as a food, spice, supplement and flavoring agent and in traditional medicines due to its beneficial characteristics such as pungency, aroma, nutrients and pharmacological activity. Ginger and ginger extracts were reported to have numerous effects, such as those on diabetes and metabolic syndrome, cholesterol levels and lipid metabolism, and inflammation, revealed by epidemiological studies. To understand the beneficial characteristics of ginger, especially its physiological and pharmacological activities at the molecular level, the biological effects of ginger constituents, such as monoterpenes (cineole, citral, limonene and α/β-pinenes), sesquiterpenes (β-elemene, farnesene and zerumbone), phenolics (gingerols, [6]-shogaol, [6]-paradol and zingerone) and diarylheptanoids (curcumin), and the associated signaling pathways are summarized. Ginger constituents are involved in biological activities, such as apoptosis, cell cycle/DNA damage, chromatin/epigenetic regulation, cytoskeletal regulation and adhesion, immunology and inflammation, and neuroscience, and exert their effects through specific signaling pathways associated with cell functions/mechanisms such as autophagy, cellular metabolism, mitogen-activated protein kinase and other signaling, and development/differentiation. Estrogens, such as phytoestrogens, are one of the most important bioactive materials in nature, and the molecular mechanisms of estrogen actions and the assays to detect them have been discussed. The molecular mechanisms of estrogen actions induced by ginger constituents and related applications, such as the chemoprevention of cancers, and the improvement of menopausal syndromes, osteoporosis, endometriosis, prostatic hyperplasia, polycystic ovary syndrome and Alzheimer's disease, were summarized by a comprehensive search of references to understand more about their health benefits and associated health risks.

Principles of QSAR Modeling

At the end of her academic career, the author summarizes the main aspects of QSAR modeling, giving comments and suggestions according to her 23 years' experience in QSAR research on environmental topics. The focus is mainly on Multiple Linear Regression, particularly Ordinary Least Squares, using a Genetic Algorithm for variable selection from various theoretical molecular descriptors, but the comments can be useful also for other QSAR methods. The need for rigorous validation, also external, and for applicability domain check to guarantee predictivity and reliability of QSAR models is particularly highlighted. The commented approach is the “predictive” one, based on chemometrics, and is usefully applied to the prioritization of environmental pollutants. All the discussed points and the author's ideas are implemented in the software QSARINS, as a legacy to the QSAR community.

Quinoxalinones Based Aldose Reductase Inhibitors: 2D and 3D-QSAR Analysis

In the present work, 2D- and 3D-quantitative structure-activity relationship (QSAR) analysis has been employed for a diverse set of eighty-nine quinoxalinones to identify the pharmacophoric features with significant correlation with the aldose reductase inhibitory activity. Using genetic algorithm (GA) as a variable selection method, multivariate linear regression (MLR) models were derived using a pool of molecular descriptors. All the six-descriptor based GA-MLR QSAR models are statistically robust with coefficient of determination (R² )>0.80 and cross-validated R² >0.77. The derived GA-MLR models were thoroughly validated using internal and external and Y-scrambling techniques. The CoMFA like model, which is based on a combination of steric and electrostatic effects and graphically inferred using contour plots, is highly robust with R² >0.93 and cross-validated R² >0.73. The established QSAR and CoMFA like models are proficient in identify key pharmacophoric features that govern the aldose reductase inhibitory activity of quinoxalinones.

QSAR Analysis of a Series of Hydantoin-based Androgen Receptor Modulators and Corresponding Binding Affinities

Androgen receptor (AR), a member of the nuclear hormone receptor superfamily of intracellular ligand-dependent transcription factors, plays an indispensable role in normal male development through the regulation of androgen through the binding with endogenous androgens. Inappropriate amounts of androgens have a severe adverse effect on men. Excessive androgen may contribute to accelerate prostatic hypertrophy, even prostate cancer, while the absence of androgen may result in reduced muscle mass and strength, decreased bone mass, low energy, diminished sexual function and an increased risk of osteoporosis and fracture. In these cases, androgen receptor modulators are important to maintain the normal biological function of AR. So androgen receptor modulators are necessary for human being to improve their happy life index. To explore the relationships between molecular structures and corresponding binding abilities to aid the new AR modulator design, multiple linear regressions (MLR) are employed to analyze a series of hydantoin analogues, which can bind to androgen receptor acting as AR modulators. The obtained optimum model presents wonderful reliabilities and strong predictive abilities with R² =0.858, Q L O O 2 =0.822, Q L M O 2 =0.813, Q F 1 2 =0.840, Q F 2 2 =0.807, Q F 3 2 =0.814, CCC=0.893, respectively. The derived model can be used to predict the binding abilities of unknown chemicals and may help to design novel molecules with better AR affinity activity.

Descriptor Selection via Log-Sum Regularization for the Biological Activities of Chemical Structure

The quantitative structure-activity relationship (QSAR) model searches for a reliable relationship between the chemical structure and biological activities in the field of drug design and discovery. (1) Background: In the study of QSAR, the chemical structures of compounds are encoded by a substantial number of descriptors. Some redundant, noisy and irrelevant descriptors result in a side-effect for the QSAR model. Meanwhile, too many descriptors can result in overfitting or low correlation between chemical structure and biological bioactivity. (2) Methods: We use novel log-sum regularization to select quite a few descriptors that are relevant to biological activities. In addition, a coordinate descent algorithm, which uses novel univariate log-sum thresholding for updating the estimated coefficients, has been developed for the QSAR model. (3) Results: Experimental results on artificial and four QSAR datasets demonstrate that our proposed log-sum method has good performance among state-of-the-art methods. (4) Conclusions: Our proposed multiple linear regression with log-sum penalty is an effective technique for both descriptor selection and prediction of biological activity.

Novel group-based QSAR and combinatorial design of CK-1δ inhibitors as neuroprotective agents

Background

Tar DNA binding protein 43 (TDP-43) hyperphosphorylation, caused by Casein kinase 1 (CK-1) protein isoforms, is associated with the onset and progression of Amyotrophic Lateral Sclerosis (ALS). Among the reported isoforms and splice variants of CK-1 protein superfamily, CK-1δ is known to phosphorylate different serine and threonine sites on TDP-43 protein in vitro and thus qualifies as a potential target for ALS treatment.

Results

The developed GQSAR (group based quantitative structure activity relationship) model displayed satisfactory statistical parameters for the dataset of experimentally reported N-Benzothiazolyl-2-Phenyl Acetamide derivatives. A combinatorial library of molecules was also generated and the activities were predicted using the statistically sound GQSAR model. Compounds with higher predicted inhibitory activity were screened against CK-1δ that resulted in to the potential novel leads for CK-1δ inhibition.

Conclusions

In this study, a robust fragment based QSAR model was developed on a congeneric set of experimentally reported molecules and using combinatorial library approach, a series of molecules were generated from which we report two top scoring, CK-1δ inhibitors i.e., CHC (6-benzyl-2-cyclopropyl-4-{[(4-cyclopropyl-6-ethyl-1,3-benzothiazol-2-yl)carbamoyl]methyl}j-3-fluorophenyl hydrogen carbonate) and DHC (6-benzyl-4-{[(4-cyclopropyl-6-ethyl-1,3-benzothiazol-2-yl)carbamoyl]methyl}-2-(decahydronaphthalen-1-yl)-3-hydroxyphenyl hydrogen carbonate) with binding energy of −6.11 and −6.01 kcal/mol, respectively.

Multiple Linear Regressions by Maximizing the Likelihood under Assumption of Generalized Gauss-Laplace Distribution of the Error

Multiple linear regression analysis is widely used to link an outcome with predictors for better understanding of the behaviour of the outcome of interest. Usually, under the assumption that the errors follow a normal distribution, the coefficients of the model are estimated by minimizing the sum of squared deviations. A new approach based on maximum likelihood estimation is proposed for finding the coefficients on linear models with two predictors without any constrictive assumptions on the distribution of the errors. The algorithm was developed, implemented, and tested as proof-of-concept using fourteen sets of compounds by investigating the link between activity/property (as outcome) and structural feature information incorporated by molecular descriptors (as predictors). The results on real data demonstrated that in all investigated cases the power of the error is significantly different by the convenient value of two when the Gauss-Laplace distribution was used to relax the constrictive assumption of the normal distribution of the error. Therefore, the Gauss-Laplace distribution of the error could not be rejected while the hypothesis that the power of the error from Gauss-Laplace distribution is normal distributed also failed to be rejected.

Predictive Modeling of Estrogen Receptor Binding Agents Using Advanced Cheminformatics Tools and Massive Public Data

Estrogen receptors (ERα) are a critical target for drug design as well as a potential source of toxicity when activated unintentionally. Thus, evaluating potential ERα binding agents is critical in both drug discovery and chemical toxicity areas. Using computational tools, e.g., Quantitative Structure-Activity Relationship (QSAR) models, can predict potential ERα binding agents before chemical synthesis. The purpose of this project was to develop enhanced predictive models of ERα binding agents by utilizing advanced cheminformatics tools that can integrate publicly available bioassay data. The initial ERα binding agent data set, consisting of 446 binders and 8307 non-binders, was obtained from the Tox21 Challenge project organized by the NIH Chemical Genomics Center (NCGC). After removing the duplicates and inorganic compounds, this data set was used to create a training set (259 binders and 259 non-binders). This training set was used to develop QSAR models using chemical descriptors. The resulting models were then used to predict the binding activity of 264 external compounds, which were available to us after the models were developed. The cross-validation results of training set [Correct Classification Rate (CCR) = 0.72] were much higher than the external predictivity of the unknown compounds (CCR = 0.59). To improve the conventional QSAR models, all compounds in the training set were used to search PubChem and generate a profile of their biological responses across thousands of bioassays. The most important bioassays were prioritized to generate a similarity index that was used to calculate the biosimilarity score between each two compounds. The nearest neighbors for each compound within the set were then identified and its ERα binding potential was predicted by its nearest neighbors in the training set. The hybrid model performance (CCR = 0.94 for cross validation; CCR = 0.68 for external prediction) showed significant improvement over the original QSAR models, particularly for the activity cliffs that induce prediction errors. The results of this study indicate that the response profile of chemicals from public data provides useful information for modeling and evaluation purposes. The public big data resources should be considered along with chemical structure information when predicting new compounds, such as unknown ERα binding agents.

Development and Validation of Decision Forest Model for Estrogen Receptor Binding Prediction of Chemicals Using Large Data Sets

Some chemicals in the environment possess the potential to interact with the endocrine system in the human body. Multiple receptors are involved in the endocrine system; estrogen receptor α (ERα) plays very important roles in endocrine activity and is the most studied receptor. Understanding and predicting estrogenic activity of chemicals facilitates the evaluation of their endocrine activity. Hence, we have developed a decision forest classification model to predict chemical binding to ERα using a large training data set of 3308 chemicals obtained from the U.S. Food and Drug Administration's Estrogenic Activity Database. We tested the model using cross validations and external data sets of 1641 chemicals obtained from the U.S. Environmental Protection Agency's ToxCast project. The model showed good performance in both internal (92% accuracy) and external validations (∼ 70-89% relative balanced accuracies), where the latter involved the validations of the model across different ER pathway-related assays in ToxCast. The important features that contribute to the prediction ability of the model were identified through informative descriptor analysis and were related to current knowledge of ER binding. Prediction confidence analysis revealed that the model had both high prediction confidence and accuracy for most predicted chemicals. The results demonstrated that the model constructed based on the large training data set is more accurate and robust for predicting ER binding of chemicals than the published models that have been developed using much smaller data sets. The model could be useful for the evaluation of ERα-mediated endocrine activity potential of environmental chemicals.

Estrogenic endocrine disruptors: Molecular mechanisms of action

A comprehensive summary of more than 450 estrogenic chemicals including estrogenic endocrine disruptors is provided here to understand the complex and profound impact of estrogen action. First, estrogenic chemicals are categorized by structure as well as their applications, usage and effects. Second, estrogenic signaling is examined by the molecular mechanism based on the receptors, signaling pathways, crosstalk/bypassing and autocrine/paracrine/homeostatic networks involved in the signaling. Third, evaluation of estrogen action is discussed by focusing on the technologies and protocols of the assays for assessing estrogenicity. Understanding the molecular mechanisms of estrogen action is important to assess the action of endocrine disruptors and will be used for risk management based on pathway-based toxicity testing.

Inside of the Linear Relation between Dependent and Independent Variables

Simple and multiple linear regression analyses are statistical methods used to investigate the link between activity/property of active compounds and the structural chemical features. One assumption of the linear regression is that the errors follow a normal distribution. This paper introduced a new approach to solving the simple linear regression in which no assumptions about the distribution of the errors are made. The proposed approach maximizes the probability of observing the event according to the random error. The use of the proposed approach is illustrated in ten classes of compounds with different activities or properties. The proposed method proved reliable and was showed to fit properly the observed data compared to the convenient approach of normal distribution of the errors.

Comparative performance of descriptors in a multiple linear and Kriging models: a case study on the acute toxicity of organic chemicals to algae

This study presents quantitative structure-toxicity relationship (QSTR) models on the toxicity of 91 organic compounds to Chlorella vulgaris using multiple linear regression (MLR) and Kriging techniques. The molecular descriptors were calculated using SPARTAN and DRAGON programs, and descriptor selection was made by "all subset" method available in the QSARINS software. MLR and Kriging models developed with the same descriptors were compared. In addition to these models, Kriging method was used for descriptor selection, and model development. The selected descriptors showed the importance of hydrophobicity, molecular weight and atomic ionization state in describing the toxicity of a diverse set of chemicals to C. vulgaris. A QSTR model should be associated with appropriate measures of goodness-of-fit, robustness, and predictivity in order to be used for regulatory purpose. Therefore, while the internal performances (goodness-of-fit and robustness) of the models were determined by using a training set, the predictive abilities of the models were determined by using a test set. The results of the study showed that while MLR method is easier to apply, the Kriging method was more successful in predicting toxicity.

QSARINS-chem: Insubria datasets and new QSAR/QSPR models for environmental pollutants in QSARINS

A database of environmentally hazardous chemicals, collected and modeled by QSAR by the Insubria group, is included in the updated version of QSARINS, software recently proposed for the development and validation of QSAR models by the genetic algorithm-ordinary least squares method. In this version, a module, named QSARINS-Chem, includes several datasets of chemical structures and their corresponding endpoints (physicochemical properties and biological activities). The chemicals are accessible in different ways (CAS, SMILES, names and so forth) and their three-dimensional structure can be visualized. Some of the QSAR models, previously published by our group, have been redeveloped using the free online software for molecular descriptor calculation, PaDEL-Descriptor. The new models can be easily applied for future predictions on chemicals without experimental data, also verifying the applicability domain to new chemicals. The QSAR model reporting format (QMRF) of these models is also here downloadable. Additional chemometric analyses can be done by principal component analysis and multicriteria decision making for screening and ranking chemicals to prioritize the most dangerous.

Molecular structure-adsorption study on current textile dyes

This study was performed to investigate the adsorption of a diverse set of textile dyes onto granulated activated carbon (GAC). The adsorption experiments were carried out in a batch system. The Langmuir and Freundlich isotherm models were applied to experimental data and the isotherm constants were calculated for 33 anthraquinone and azo dyes. The adsorption equilibrium data fitted more adequately to the Langmuir isotherm model than the Freundlich isotherm model. Added to a qualitative analysis of experimental results, multiple linear regression (MLR), support vector regression (SVR) and back propagation neural network (BPNN) methods were used to develop quantitative structure-property relationship (QSPR) models with the novel adsorption data. The data were divided randomly into training and test sets. The predictive ability of all models was evaluated using the test set. Descriptors were selected with a genetic algorithm (GA) using QSARINS software. Results related to QSPR models on the adsorption capacity of GAC showed that molecular structure of dyes was represented by ionization potential based on two-dimensional topological distances, chromophoric features and a property filter index. Comparison of the performance of the models demonstrated the superiority of the BPNN over GA-MLR and SVR models.

Assessment of hydroxylated metabolites of polychlorinated biphenyls as potential xenoestrogens: a QSAR comparative analysis∗

Alternative methods, including quantitative structure-activity relationships (QSAR), are being used increasingly when appropriate data for toxicity evaluation of chemicals are not available. Approximately 40 mono-hydroxylated polychlorinated biphenyls (OH-PCBs) have been identified in humans. They represent a health and environmental concern because some of them have been shown to have agonist or antagonist interactions with human hormone receptors. This could lead to modulation of steroid hormone receptor pathways and endocrine system disruption. We performed QSAR analyses using available estrogenic activity (human estrogen receptor ER alpha) data for 71 OH-PCBs. The modelling was performed using multiple molecular descriptors including electronic, molecular, constitutional, topological, and geometrical endpoints. Multiple linear regressions and recursive partitioning were used to best fit descriptors. The results show that the position of the hydroxyl substitution, polarizability, and meta adjacent un-substituted carbon pairs at the phenolic ring contribute towards greater estrogenic activity for these chemicals. These comparative QSAR models may be used for predictive toxicity, and identification of health consequences of PCB metabolites that lack empirical data. Such information will help prioritize such molecules for additional testing, guide future basic laboratory research studies, and help the health/risk assessment community understand the complex nature of chemical mixtures.

Chemometric model for predicting retention indices of constituents of essential oils

Quantitative structure-retention relationships (QSRRs) model was developed for predicting the gas chromatography retention indices of 169 constituents of essential oils. The ordered predictors selection algorithm was used to select three descriptors (one constitutional index and two edge adjacency indices) from 4885 descriptors. The final QSRR model (model M3) with three descriptors was internal and external validated. The leave-one-out cross-validation, leave-many-out cross-validation, bootstrapping, and y-randomization test indicated the final model is robust and have no chance correlation. The external validations indicated that the model M3 showed a good predictive power. The mechanistic interpretation of QSRR model was carried out according to the definition of descriptors. The results show that the larger molecular weight, the greater the values of retention indices. More compact structures have stronger intermolecular interactions between the components of essential oils and the capillary column. Therefore, the result meets the five principles recommended by the Organization for Economic Co-operation and Development (OECD) for validation of QSRR model, and it is expected the model can effectively predict retention indices of the essential oils.

QSAR Modeling is not "Push a Button and Find a Correlation": A Case Study of Toxicity of (Benzo-)triazoles on Algae

A case study of toxicity of (benzo)triazoles ((B)TAZs) to the algae Pseudokirchneriella subcapitata is used to discuss some problems and solutions in QSAR modeling, particularly in the environmental context. The relevance of data curation (not only of experimental data, but also of chemical structures and input formats for the calculation of molecular descriptors), the crucial points of QSAR model validation and the potential application for new chemicals (internal robustness, exclusion of chance correlation, external predictivity, applicability domain) are described, while developing MLR-OLS models based on molecular descriptors, calculated by various QSAR software tools (commercial DRAGON, free PaDEL-Descriptor and QSPR-THESAURUS). Additionally, the utility of consensus models is highlighted. This work summarizes a methodology for a rigorous statistical approach to obtain reliable QSAR predictions, also for a large number of (B)TAZs in the ECHA preregistration list of REACH (even if starting from limited experimental data availability), and has evidenced some ambiguities and discrepancies related to SMILES notations from different databases; furthermore it highlighted some general problems related to QSAR model generation and was useful in the implementation of the PaDEL-Descriptor software.

Real external predictivity of QSAR models: how to evaluate it? Comparison of different validation criteria and proposal of using the concordance correlation coefficient

The main utility of QSAR models is their ability to predict activities/properties for new chemicals, and this external prediction ability is evaluated by means of various validation criteria. As a measure for such evaluation the OECD guidelines have proposed the predictive squared correlation coefficient Q(2)(F1) (Shi et al.). However, other validation criteria have been proposed by other authors: the Golbraikh-Tropsha method, r(2)(m) (Roy), Q(2)(F2) (Schüürmann et al.), Q(2)(F3) (Consonni et al.). In QSAR studies these measures are usually in accordance, though this is not always the case, thus doubts can arise when contradictory results are obtained. It is likely that none of the aforementioned criteria is the best in every situation, so a comparative study using simulated data sets is proposed here, using threshold values suggested by the proponents or those widely used in QSAR modeling. In addition, a different and simple external validation measure, the concordance correlation coefficient (CCC), is proposed and compared with other criteria. Huge data sets were used to study the general behavior of validation measures, and the concordance correlation coefficient was shown to be the most restrictive. On using simulated data sets of a more realistic size, it was found that CCC was broadly in agreement, about 96% of the time, with other validation measures in accepting models as predictive, and in almost all the examples it was the most precautionary. The proposed concordance correlation coefficient also works well on real data sets, where it seems to be more stable, and helps in making decisions when the validation measures are in conflict. Since it is conceptually simple, and given its stability and restrictiveness, we propose the concordance correlation coefficient as a complementary, or alternative, more prudent measure of a QSAR model to be externally predictive.

Structure-based quantitative structure–activity relationship modeling of estrogen receptor β-ligands

Background: A variety of chemotypes have been studied as estrogen receptor (ER) β-selective ligands for potential drugs against various indications, including neurodegenerative diseases. Their structure–activity relationship data and the x-ray structures of the ERβ ligand-binding domain bound with different ligands have become available. Thus, it is vitally important for future development of ERβ-selective ligands that robust quantitative structure–activity relationship (QSAR) models be built. Methods/results: We employed a newly developed structure-based QSAR method (structure-based pharmacophore keys QSAR) that utilizes both the structure–activity relationship data and the 3D structural information of ERβ, as well as a robust QSAR workflow to analyze 37 ligands. Four sets of QSAR models were obtained, among which approximately 30 models afforded high (>0.60) training-r2 and test set-R2 statistics. Conclusion: We have obtained an ensemble of predictive models of ERβ ligands that will be useful in the future discovery of novel ERβ-selective molecules.

First computational chemistry multi-target model for anti-Alzheimer, anti-parasitic, anti-fungi, and anti-bacterial activity of GSK-3 inhibitors in vitro, in vivo, and in different cellular lines

In the work described here, we developed the first multi-target quantitative structure-activity relationship (QSAR) model able to predict the results of 42 different experimental tests for GSK-3 inhibitors with heterogeneous structural patterns. GSK-3β inhibitors are interesting candidates for developing anti-Alzheimer compounds. GSK-3β are also of interest as anti-parasitic compounds active against Plasmodium falciparum, Trypanosoma brucei, and Leishmania donovani; the causative agents for Malaria, African Trypanosomiasis and Leishmaniosis. The MARCH-INSIDE technique was used to quickly calculate total and local polarizability, n-octanol/water partition coefficients, refractivity, van der Waals area and electronegativity values to 4,508 active/non-active compounds as well as the average values of these indexes for active compounds in 42 different biological assays. Both the individual molecular descriptors and the average values for each test were used as input for a linear discriminant analysis (LDA). We discovered a classification function which used in training series correctly classifies 873 out of 1,218 GSK-3 cases of inhibitors (97.4%) and 2,140 out of 2,163 cases of non-active compounds (86.1%) in the 42 different tests. In addition, the model correctly classifies 285 out of 406 GSK-3 inhibitors (96.3%) and 710 out of 721 cases of non-active compounds (85.4%) in external validation series. The result is important because, for the first time, we can use a single equation to predict the results of heterogeneous series of organic compounds in 42 different experimental tests instead of developing, validating, and using 42 different QSAR models. Lastly, a double ordinate Cartesian plot of cross-validated residuals (first ordinate), standard residuals (second ordinate), and leverages (abscissa) defined the domain of applicability of the model as a squared area within ± 2 band for residuals and a leverage threshold of h = 0.0044.