Final Quantitative Structure-activity Relationship Research Articles

Machine learning models to predict ligand binding affinity for the orexin 1 receptor

The orexin 1 receptor (OX1R) is a G-protein coupled receptor that regulates a variety of physiological processes through interactions with the neuropeptides orexin A and B. Selective OX1R antagonists exhibit therapeutic effects in preclinical models of several behavioral disorders, including drug seeking and overeating. However, currently there are no selective OX1R antagonists approved for clinical use, fueling demand for novel compounds that act at this target. In this study, we meticulously curated a dataset comprising over 1300 OX1R ligands using a stringent filter and criteria cascade. Subsequently, we developed highly predictive quantitative structure-activity relationship (QSAR) models employing the optimized hyper-parameters for the random forest machine learning algorithm and twelve 2D molecular descriptors selected by recursive feature elimination with a 5-fold cross-validation process. The predictive capacity of the QSAR model was further assessed using an external test set and enrichment study, confirming its high predictivity. The practical applicability of our final QSAR model was demonstrated through virtual screening of the DrugBank database. This revealed two FDA-approved drugs (isavuconazole and cabozantinib) as potential OX1R ligands, confirmed by radiolabeled OX1R binding assays. To our best knowledge, this study represents the first report of highly predictive QSAR models on a large comprehensive dataset of diverse OX1R ligands, which should prove useful for the discovery and design of new compounds targeting this receptor.

Pesticide effect on earthworm lethality via interpretable machine learning

Earthworms are among the most important animals (invertebrates) for soil health. Many chemical substances released into nature for agricultural development, such as pesticides, may have unwanted effects on those organisms. However, it is essential to understand the extent of the impact of chemicals on soil health first and then make the proper decisions for regulatory or commercial purposes. We hypothesize that there is an expressible quantitative structure-activity relationship (QSAR) between the structure of pesticide compounds and the acute toxicity effect of earthworm species Eisenia fetida. The description of this relationship allows for a better assessment of the impact of chemicals on the said earthworm. To describe this relationship, a dataset of chemicals was collected from open-access sources to develop a mathematical model. A novel approach, combining genetic algorithm and Bayesian optimization, was used to select structural features into the model and to optimize model parameters. The final QSAR classification model was created with the Random Forest algorithm and exhibited good prediction Accuracy of 0.78 on training set and 0.80 on test set. The model representation follows FAIR principles and is available on QsarDB.org.

Rational eutectic solvent design by linking regular solution theory with QSAR modelling

Although eutectic solvents (ES), also widely termed as deep eutectic solvents (DES), have attracted significant interest in various chemical processes, the rational design of them remains challenging due to the difficulty in estimating eutectic formation. In this work, the regular solution theory (RST) and quantitative structure–activity relationship (QSAR) modelling are linked to the design of ES. The RST method meriting simplicity and solid physical basis is systematically examined for correlating the solid–liquid equilibria of 99 ES systems collected from literature. The QSAR model between the RST interaction parameters of these ES systems and the molecular descriptors of their constitutive components is developed through elaborate descriptor selection. With the final QSAR model based on 14 molecular descriptors, the eutectic temperature (Te) and composition (xe) of ES systems can be accurately predicted with mean absolute deviations of 13.89 K and 0.0973, respectively. The eutectic formation of novel component combinations can be readily predicted, thereby allowing novel ES design. As an example, from the combinations of all involved components in the collected database, 186 novel ES systems are identified and 99 of them are estimated to present as liquid under room temperature.

QSAR modelling of organic dyes for their acute toxicity in Daphnia magna using 2D-descriptors

ABSTRACT The present study reports quantitative structure-activity relationship (QSAR) models for 22 organic dyes spanning a broad chemical domain to predict their toxicity in Daphnia magna [log (1/EC50)]. Only two-dimensional descriptors with clear physicochemical meaning were used to construct the QSAR models. The process of development, validation, and interpretation of models adheres to the stringent recommendations of the Organization for Economic Cooperation and Development (OECD) guidelines. In this study, the multi-layered stepwise regression method and linear discriminant analysis (LDA) method were employed for the deployment of regression – and classification-based models respectively; however, the final regression-based QSAR models were obtained through the partial least squares (PLS) regression. Additionally, the applicability domain of the developed models was verified. The constructed models should be applicable in the absence of toxicity data of new or untested dye structures, particularly when the compounds fall within the developed models’ scope, and also implementable to develop more environmentally friendly alternatives.

QSAR Modeling and Prediction of Triptan Binding Affinities

The purpose of this study was to use quantitative structure-activity relationships (QSARs) to identify new triptan molecules that selectively bind to h 5-HT1B and h 5-HT1D to a greater extent than to the similar h 5-HT1A receptor in order to identify novel compounds that could lead to an alternative and potentially superior migraine relief drug. Due to its possibility in migraine abortive properties, binding affinities to h 5-HT1F were also modeled. Binding affinities for 12 different triptan drugs and structurally similar substances were compiled from the literature, and descriptors were generated for those and other potential drug candidates using a variety of programs. The most significant descriptors were identified using a stepwise model, and the final QSARs were built for each activity with those descriptors, and a neural network. QSARs for all four activities were validated using a holdback method and were all found to be highly accurate. With these QSARs, activities of novel compounds similar to triptan drugs were predicted and three potential drug candidates were suggested.

Application of proteometric approach for identification of functional mutant sites to improve the binding affinity of anticancer biologic trastuzumab with its antigen human epidermal growth factor receptor 2.

The aim of the present study was to develop a linear regression model aiding to a quick scan of the most important sites for mutation of an anticancer biologic trastuzumab. The important sites identified on trastuzumab can be used to carry out site-directed mutagenesis to improve the binding affinity of the drug towards its antigen, human epidermal growth factor receptor 2 (HER2). This will lead to low dosage requirement of the drug for treating cancer patients, which in turn help to cut the cost and combat development of resistance. A quantitative structure-activity relationship (QSAR) model was built by multiple linear regressions using genetic algorithm-based feature selection (GA-MLR) method using 48 dependent variables (dissociation constant Kd ) and 226 independent variables (theoretical descriptors generated using a proteometrics approach). The final QSAR model selected in the study was more on the basis of ability to predict accurately independent test data and generalization ability of the model rather than mere statistical significance of the model. With combined analysis of descriptors presented in final QSAR model and most frequent descriptors pooled from all solution models, it was demonstrated that the modeling procedure was able to bring on the factors important for antigen-antibody interactions with an example of HER2-trastuzumab interaction reported in previous experimental studies. This paper will allow the prediction of the most preferable site to mutate for improving the binding affinity of trastuzumab with HER2 and also will be helpful in selecting most preferable amino acids to substitute in the selected site for mutations. This is the novel report on proteometrics approach with autocorrelation formalism for antibody engineering, which can be extended to other antibody-antigen pairs.

Ecotoxicological QSAR modelling of organic chemicals against Pseudokirchneriella subcapitata using consensus predictions approach

ABSTRACTThe present study provides robust consensus quantitative structure-activity relationship (QSAR) models developed from 334 organic chemicals covering a wide chemical domain for the prediction of effective concentrations of chemicals for 50% and 10% inhibition of algal growth. Only 2D descriptors with definite physicochemical meaning were employed for QSAR model building, whereas development, validation and interpretation were achieved following the strict Organization for Economic Co-operation and Development (OECD) recommended guidelines. Genetic algorithm along with stepwise approach was used in feature selection while the final QSAR models were derived using partial least squares regression technique. The applicability domain of the developed models was also checked. The obtained consensus models were then used to predict 64 organic chemicals having no definite observed responses while the confidence of predictions was checked by the ‘prediction reliability indicator’ tool. The developed models should be applicable for data gap filling in case of new or untested organic chemicals provided they fall within the domain of the model and can also be implemented to design safer alternatives to the environment.

Design and prediction of new acetylcholinesterase inhibitor via quantitative structure activity relationship of huprines derivatives.

Acetylcholinesterase (AChE) is an important enzyme in the pathogenesis of Alzheimer's disease (AD). Comparative quantitative structure-activity relationship (QSAR) analyses on some huprines inhibitors against AChE were carried out using comparative molecular field analysis (CoMFA), comparative molecular similarity indices analysis (CoMSIA), and hologram QSAR (HQSAR) methods. Three highly predictive QSAR models were constructed successfully based on the training set. The CoMFA, CoMSIA, and HQSAR models have values of r (2)=0.988, q (2)=0.757, ONC=6; r (2)=0.966, q (2)=0.645, ONC=5; and r (2)=0.957, q (2)=0.736, ONC=6. The predictabilities were validated using an external test sets, and the predictive r (2) values obtained by the three models were 0.984, 0.973, and 0.783, respectively. The analysis was performed by combining the CoMFA and CoMSIA field distributions with the active sites of the AChE to further understand the vital interactions between huprines and the protease. On the basis of the QSAR study, 14 new potent molecules have been designed and six of them are predicted to be more active than the best active compound 24 described in the literature. The final QSAR models could be helpful in design and development of novel active AChE inhibitors.

A comparative QSAR study on the estrogenic activities of persistent organic pollutants by PLS and SVM

Quantitative structure-activity relationships (QSARs) were determined using partial least square (PLS) and support vector machine (SVM). The predicted values by the final QSAR models were in good agreement with the corresponding experimental values. Chemical estrogenic activities are related to atomic properties (atomic Sanderson electronegativities, van der Waals volumes and polarizabilities). Comparison of the results obtained from two models, the SVM method exhibited better overall performances. Besides, three PLS models were constructed for some specific families based on their chemical structures. These predictive models should be useful to rapidly identify potential estrogenic endocrine disrupting chemicals.

Quantitative Structure-Activity Relationship Analysis and a Combined Ligand-Based/Structure-Based Virtual Screening Study for Glycogen Synthase Kinase-3.

Glycogen synthase kinase-3 (GSK-3) is a multifunctional serine/threonine protein kinase which regulates a wide range of cellular processes, involving various signalling pathways. GSK-3β has emerged as an important therapeutic target for diabetes and Alzheimer's disease. To identify structurally novel GSK-3β inhibitors, we performed virtual screening by implementing a combined ligand-based/structure-based approach, which included quantitative structure-activity relationship (QSAR) analysis and docking prediction. To integrate and analyze complex data sets from multiple experimental sources, we drafted and validated a hierarchical QSAR method, which adopts a two-level structure to take data heterogeneity into account. A collection of 728 GSK-3 inhibitors with diverse structural scaffolds was obtained from published papers that used different experimental assay protocols. Support vector machines and random forests were implemented with wrapper-based feature selection algorithms to construct predictive learning models. The best models for each single group of compounds were then used to build the final hierarchical QSAR model, with an overall R(2) of 0.752 for the 141 compounds in the test set. The compounds obtained from the virtual screening experiment were tested for GSK-3β inhibition. The bioassay results confirmed that 2 hit compounds are indeed GSK-3β inhibitors exhibiting sub-micromolar inhibitory activity, and therefore validated our combined ligand-based/structure-based approach as effective for virtual screening experiments.

QSAR study on the histamine (H3) receptor antagonists using the genetic algorithm: Multi parameter linear regression

A quantitative structure activity relationship (QSAR) model has been produced for predicting antagonist potency of biphenyl derivatives as human histamine (H3) receptors. The molecular structures of the compounds are numerically represented by various kinds of molecular descriptors. The whole data set was divided into training and test sets. Genetic algorithm based multiple linear regression is used to select most statistically effective descriptors. The final QSAR model (N =24, R2=0.916, F = 51.771, Q2 LOO = 0.872, Q2 LGO = 0.847, Q2 BOOT = 0.857) was fully validated employing leaveone- out (LOO) cross-validation approach, Fischer statistics (F), Yrandomisation test, and predictions based on the test data set. The test set presented an external prediction power of R2 test=0.855. In conclusion, the QSAR model generated can be used as a valuable tool for designing similar groups of new antagonists of histamine (H3) receptors.

Predicting Skin Permeability of Chemical Substances using a Quantitative Structure-activity Relationship

Abstract The health hazard arising from skin exposure to toxic chemical was conventionally evaluated by determining the skin permeation coefficient ( Kp ) of chemical in the stratum corneum of human or animal cadaver skin. However, limited by constraints inherent in the technique, to date the Kp evaluation has been performed only insufficiently. This study defined a quantitative structure-activity relationship (QSAR) for Kp prediction and for characterization of, at a molecular level, the physicochemical properties involved in transdermal transport of chemical. One hundred and fifty-eight chemical substances of known Kp determined in vitro using human skin were selected in the QSAR development. The final QSAR consisted of four molecular descriptors, including those describing electrostatic interactions between electric quadrupoles of van der Waals forces, octanol-water partitioning of solute, similarity in antineoplastic property, and frequency of carbon-nitrogen bonding at a constant topological distance. The four-descriptor multiple linear regression model fit the observed Kp data with a R 2 of 0.828 and a mean percentage error of 18.8%, suggesting a capacity of this QSAR to serve as an alterative source of Kp information and a potential tool of dermal hazard characterization, particularly when experimentally determined Kp are not readily available.

A QSAR study for 2-(4-aminophenyl)benzothiazoles: using DFT optimisation of geometry of molecules

Quantitative structure–activity relationships (QSARs) have been established for two sets of antitumour drugs 2-(4-aminophenyl)benzothiazoles (APBT). Constitutional, geometrical, topological, electronic descriptors (computed at the B3LYP/6-31G** level) and some empirical descriptors related to the hypophilicity were computed and analysed. Multiple regression analysis led to a set of equations that reflected the weight of each of the studied descriptors. The most relevant of these descriptors were grouped, and a new multiple regressions analysis was carried out and we arrived at the final QSAR models. A validation set of 11 APBT were selected, and their activities were computed using the proposed QSAR model. The correlation between the predicted and observed activities was excellent. The resulting best models exhibited good q 2 and r 2 values up to 0.867 and 0.954.

Antiproliferative Pt(IV) complexes: synthesis, biological activity, and quantitative structure–activity relationship modeling

Several Pt(IV) complexes of the general formula [Pt(L)2(L')2(L'')2] [axial ligands L are Cl-, RCOO-, or OH-; equatorial ligands L' are two am(m)ine or one diamine; and equatorial ligands L'' are Cl- or glycolato] were rationally designed and synthesized in the attempt to develop a predictive quantitative structure-activity relationship (QSAR) model. Numerous theoretical molecular descriptors were used alongside physicochemical data (i.e., reduction peak potential, Ep, and partition coefficient, log Po/w) to obtain a validated QSAR between in vitro cytotoxicity (half maximal inhibitory concentrations, IC50, on A2780 ovarian and HCT116 colon carcinoma cell lines) and some features of Pt(IV) complexes. In the resulting best models, a lipophilic descriptor (log Po/w or the number of secondary sp3 carbon atoms) plus an electronic descriptor (Ep, the number of oxygen atoms, or the topological polar surface area expressed as the N,O polar contribution) is necessary for modeling, supporting the general finding that the biological behavior of Pt(IV) complexes can be rationalized on the basis of their cellular uptake, the Pt(IV)-->Pt(II) reduction, and the structure of the corresponding Pt(II) metabolites. Novel compounds were synthesized on the basis of their predicted cytotoxicity in the preliminary QSAR model, and were experimentally tested. A final QSAR model, based solely on theoretical molecular descriptors to ensure its general applicability, is proposed.

SAR of Cu (II) Thiosemicarbazone Complexes as Hypoxic Imaging Agents: MM3 Analysis and Prediction of Biologic Properties

Copper(II) bis(thiosemicarbazone) are very useful for blood flow and hypoxic imaging. The aim of this study was to identify structure-activity relationships (SARs) within a series of analogues with different substitution patterns in the ligands, in order to design improved hypoxia imaging agents and elucidate hypoxia selectivity mechanisms. Genetic algorithms (GAs) were used to develop specific copper metal-ligand force field parameters for the MM3 force-field calculations. These new parameters produced results in good agreement with experiment and previously reported copper metal-ligand parameters. A successful quantitative SAR (QSAR) for predicting the several classes of Cu(II)-chelating ligands was built using a training set of 21 Cu(II) complexes. The QSAR exhibited a correlation between the predicted and experimental test set. The QSAR preformed with great accuracy; r(2) = 0.95 and q(2) = 0.90 utilizing a leave-one-out cross-validation with multiple linear regression analysis to find correlation between different calculated molecular descriptors of these complexes. The final QSAR mathematical models were found as the following: Log P = {3.01698 (+/-0.0590)} - LUMO {0.1248 (+/-0.068)} + MR {0.3219 (+/-0.086)} n = 21 |r| = 0.972 s = 0.188 F = 98.102 The resulting models could act as an efficient strategy for estimating the hypoxic conditions through imaging and provide some insights into the structural features related to the biological activity of these compounds.

QSAR modeling of some substituted benzimidazole as Angotensin II AT1 receptor antagonist

A quantitative structure activity relationship (QSAR) analysis of a set 33 benzimidazole analogues as angiotensin (AT) II AT1 receptor antagonists was performed to explore substitutional requirements for a favorable receptor drug interaction. The QSAR models were generated by using Fuzita ban analysis and Hansch analysis. Stepwise regression was performed to derive a predictive model. The predictive ability of the model developed was assessed by using a test set of 11 compounds. The internal (correlation coefficient r2) and external consistency (predictive r2) of the final Hansch QSAR model were 0.68 and 0.46, respectively. The internal (correlation coefficient r2) consistency of the Fujita-ban model was 0.572 and CH2COOH group at the seventh position is significant in increasing AII antagonistic activity. Ovality (Steric), Lumo and total energy (electronic), and Bend energy (thermodynamic) are significant descriptors that govern the AII antagonistic activity.

Validated quantitative structure–activity relationship analysis of a series of 2-aminothiazole based p56 Lck inhibitors

In this study, the quantitative structure–activity relationship (QSAR) of a series of 2-aminothiazole based Lck inhibitors was investigated. The key structural features responsible for the inhibition activities were discussed in detail. A population of 100 rigorously validated linear QSAR models were established based on the descriptors calculated in DRAGON program and selected by genetic algorithm (GA). A total of 36 descriptors were involved in all the QSAR models. Then the common descriptors appeared in all the models were extracted to build the final QSAR model. As a result, the final 8-parameter QSAR model was established. After analysis of the eight descriptors, some advice was proposed to help the design of possible novel inhibitors with higher bioactivity.

Probing the Anticancer Activity of Nucleoside Analogues: A QSAR Model Approach Using an Internally Consistent Training Set

The cancer research community has begun to address the in silico modeling approaches, such as quantitative structure-activity relationships (QSAR), as an important alternative tool for screening potential anticancer drugs. With the compilation of a large dataset of nucleosides synthesized in our laboratories, or elsewhere, and tested in a single cytotoxic assay under the same experimental conditions, we recognized a unique opportunity to attempt to build predictive QSAR models. Here, we report a systematic evaluation of classification models to probe anticancer activity, based on linear discriminant analysis along with 2D-molecular descriptors. This strategy afforded a final QSAR model with very good overall accuracy and predictability on external data. Finally, we search for similarities between the natural nucleosides, present in RNA/DNA, and the active nucleosides well-predicted by the model. The structural information then gathered and the QSAR model per se shall aid in the future design of novel potent anticancer nucleosides.

Comparative QSAR studies on peptide deformylase inhibitors

Comparative quantitative structure-activity relationship (QSAR) analyses of peptide deformylase (PDF) inhibitors were performed with a series of previously published (British Biotech Pharmaceuticals, Oxford, UK) reverse hydroxamate derivatives having antibacterial activity against Escherichia coli PDF, using 2D and 3D QSAR methods, comparative molecular field analysis (CoMFA), comparative molecular similarity indices analysis (CoMSIA), and hologram QSAR (HQSAR). Statistically reliable models with good predictive power were generated from all three methods (CoMFA r (2) = 0.957, q (2) = 0.569; CoMSIA r (2) = 0.924, q (2) = 0.520; HQSAR r (2) = 0.860, q (2) = 0.578). The predictive capability of these models was validated by a set of compounds that were not included in the training set. The models based on CoMFA and CoMSIA gave satisfactory predictive r (2) values of 0.687 and 0.505, respectively. The model derived from the HQSAR method showed a low predictability of 0.178 for the test set. In this study, 3D prediction models showed better predictive power than 2D models for the test set. This might be because 3D information is more important in the case of datasets containing compounds with similar skeletons. Superimposition of CoMFA contour maps in the active site of the PDF crystal structure showed a meaningful correlation between receptor-ligand binding and biological activity. The final QSAR models, along with information gathered from 3D contour and 2D contribution maps, could be useful for the design of novel active inhibitors of PDF.

Human protein tyrosine phosphatase 1B inhibitors: QSAR by genetic function approximation

Protein tyrosine phosphatase 1B (PTP 1B), a negative regulator of insulin receptor signaling system, has emerged as a highly validated, attractive target for the treatment of non-insulin dependent diabetes mellitus (NIDDM) and obesity. As a result there is a growing interest in the development of potent and specific inhibitors for this enzyme. This quantitative structure-activity relationship (QSAR) study for a series of formylchromone derivatives as PTP 1B inhibitors was performed using genetic function approximation (GFA) technique. The QSAR models were developed using a training set of 29 compounds and the predictive ability of the QSAR model was evaluated against a test set of 7 compounds. The internal and external consistency of the final QSAR model was 0.766 and 0.785. The statistical quality of QSAR models was assessed by statistical parameters r2, (crossvalidated r2), (predictive r2) and lack of fit (LOF) measure. The results indicate that PTP 1B inhibitory activity of the formylchromone derivatives is strongly dependent on electronic, thermodynamic and shape related parameters.