Performance of (consensus) kNN QSAR for predicting estrogenic activity in a large diverse set of organic compounds

A novel method (in the context of quantitative structure-activity relationship (QSAR)) based on the k nearest neighbour (kNN) principle, has recently been introduced for the derivation of predictive structure-activity relationships. Its performance has been tested for estimating the estrogen binding affinity of a diverse set of 142 organic molecules. Highly predictive models have been obtained. Moreover, it has been demonstrated that consensus-type kNN QSAR models, derived from the arithmetic mean of individual QSAR models were statistically robust and provided more accurate predictions than the great majority of the individual QSAR models. Finally, the consensus QSAR method was tested with 3D QSAR and log P data from a widely used steroid benchmark data set.     

On further application of r as a metric for validation of QSAR models

Validation is a crucial aspect for quantitative structure–activity relationship (QSAR) model development. External validation is considered, in general, as the most conclusive proof of predictive capacity of a QSAR model. In the absence of truly external data set, external validation is usually performed on test set compounds, which are members of the original data set but not used in model development exercise. In the case of small data sets, QSAR researchers experience problem in model development due to the fact that the developed models may be less reliable on account of the small number of training set compounds and such models may also show poor external predictability because the models may not have captured all necessary features required for the particular structure–activity relationships. The present paper attempts to show that ‘true r_(LOO)’ statistic calculated based on the model derived from the undivided data set with application of variable selection strategy at each cycle of leave‐one‐out (LOO) validation may reflect external validation characteristics of the developed model thus obviating the requirement of splitting of the data set into training and test sets. This approach may be helpful in the case of small data sets as it uses all available data for model development and validation thus making the resulting model more reliable. Copyright © 2009 John Wiley & Sons, Ltd.     

Structural investigations of anthranilimide derivatives by CoMFA and CoMSIA 3D-QSAR studies reveal novel insight into their structures toward glycogen phosphorylase inhibition

In the present work, three-dimensional quantitative structure–activity relationship (3-D QSAR) studies on a set of 70 anthranilimide compounds has been performed using docking-based as well as substructure-based molecular alignments. This resulted in the selection of more statistically relevant substructure-based alignment for further studies. Further, molecular models with good predictive power were derived using CoMFA (r ^2?=?0.997; Q ^2?=?0.578) and CoMSIA (r ^2?=?0.976; Q ^2?=?0.506), for predicting the biological activity of new compounds. The so-developed contour plots identified several key features of the compounds explaining wide activity ranges. Based on the information derived from the CoMFA contour maps, novel leads were proposed which showed better predicted activity with respect to the already reported systems. Thus, the present study not only offers a highly significant predictive QSAR model for anthranilimide derivatives as glycogen phosphorylase (GP) inhibitors which can eventually assist and complement the rational drug-design attempts, but also proposes a highly predictive pharmacophore model as a guide for further development of selective and more potent GP inhibitors as anti-diabetic agents.     

The definition of the molecular structure for potential anti-malaria agents by the Monte Carlo method

A series of 53 endochin analogs (4(1-H)-quinolone derivatives) with anti-malarial activity against the clinically relevant multidrug resistant malarial strain TM-90-C2B has been studied. The CORAL (http://www.insilico.eu/coral) software has been used as a tool to build up the quantitative structure–activity relationships (QSAR) for the anti-malaria activity. The QSAR models were calculated with the representation of the molecular structure by simplified molecular input-line entry system and by the molecular graph of atomic orbitals. The method for splitting data into the sub-training set, the calibration set, the test set, and the validation set is suggested. Three various splits were examined. Statistical quality of models for the validation sets (which are not involved in the building up models) is good. Structural indicators (alerts) for increase and decrease of the anti-malaria activity are defined.     

Qualitative and quantitative structure–activity relationship modelling for predicting blood-brain barrier permeability of structurally diverse chemicals

In this study, structure–activity relationship (SAR) models have been established for qualitative and quantitative prediction of the blood–brain barrier (BBB) permeability of chemicals. The structural diversity of the chemicals and nonlinear structure in the data were tested. The predictive and generalization ability of the developed SAR models were tested through internal and external validation procedures. In complete data, the QSAR models rendered ternary classification accuracy of >98.15%, while the quantitative SAR models yielded correlation (r²) of >0.926 between the measured and the predicted BBB permeability values with the mean squared error (MSE) <0.045. The proposed models were also applied to an external new in vitro data and yielded classification accuracy of >82.7% and r² > 0.905 (MSE < 0.019). The sensitivity analysis revealed that topological polar surface area (TPSA) has the highest effect in qualitative and quantitative models for predicting the BBB permeability of chemicals. Moreover, these models showed predictive performance superior to those reported earlier in the literature. This demonstrates the appropriateness of the developed SAR models to reliably predict the BBB permeability of new chemicals, which can be used for initial screening of the molecules in the drug development process.     

Predicting toxicity of benzene derivatives by molecular hologram derived quantitative structure–activity relationships (QSARS)

Holographic quantitative structure–activity relationship (HQSAR) is an emerging QSAR technique with the combined application of molecular hologram, which encodes the frequency of occurrence of various molecular fragment types, and the subsequent partial least squares (PLS) regression analysis. Based on molecular hologram, alignment-free QSAR models could be rapidly and easily developed with highly statistical significance and predictive ability. In this paper, the toxicity data for a series of 83 benzene derivatives to the autotrophic Chlorella vulgaris (IGC⁵⁰, negative logarithmic form of 6-h 50% population growth inhibition concentration in mmol/l) were subjected to HQSAR analysis and this resulted in a model with a high predictive ability. The robustness and predictive ability of the model were validated by “leave-one-out” (LOO) cross-validation procedure and an external testing set. The influence of fragment distinction parameters and fragment size on the quality of the HQSAR model have been also discussed.     

A new strategy to improve the predictive ability of the local lazy regression and its application to the QSAR study of melanin‐concentrating hormone receptor 1 antagonists

In the quantitative structure‐activity relationship (QSAR) study, local lazy regression (LLR) can predict the activity of a query molecule by using the information of its local neighborhood without need to produce QSAR models a priori. When a prediction is required for a query compound, a set of local models including different number of nearest neighbors are identified. The leave‐one‐out cross‐validation (LOO‐CV) procedure is usually used to assess the prediction ability of each model, and the model giving the lowest LOO‐CV error or highest LOO‐CV correlation coefficient is chosen as the best model. However, it has been proved that the good statistical value from LOO cross‐validation appears to be the necessary, but not the sufficient condition for the model to have a high predictive power. In this work, a new strategy is proposed to improve the predictive ability of LLR models and to access the accuracy of a query prediction. The bandwidth of k neighbor value for LLR is optimized by considering the predictive ability of local models using an external validation set. This approach was applied to the QSAR study of a series of thienopyrimidinone antagonists of melanin‐concentrating hormone receptor 1. The obtained results from the new strategy shows evident improvement compared with the commonly used LOO‐CV LLR methods and the traditional global linear model. © 2009 Wiley Periodicals, Inc. J Comput Chem, 2010     

Combined 2D and 3D-QSAR,molecular modelling and docking studies of pyrazolodiazepinones as novel phosphodiesterase 2 inhibitors

Selective inhibition of phosphodiesterase 2 (PDE2) in cells where it is located elevates cyclic guanosine monophosphate (cGMP) and acts as novel analgesic with antinociceptive activity. Three-dimensional quantitative structure–activity relationship (QSAR) studies for pyrazolodiazepinone inhibitors exhibiting PDE2 inhibition were performed using comparative molecular field analysis (CoMFA), comparative molecular similarity indices analysis (CoMSIA) and Topomer CoMFA, and two-dimensional QSAR study was performed using a Hologram QSAR (HQSAR) method. QSAR models were generated using training set of 23 compounds and were validated using test set of nine compounds. The optimum partial least squares (PLS) for CoMFA-Focusing, CoMSIA-SDH, Topomer CoMFA and HQSAR models exhibited good ‘leave-one-out’ cross validated correlation coefficient (q²) of 0.790, 0.769, 0.840 and 0.787, coefficient of determination (r²) of 0.999, 0.964, 0.979 and 0.980, and high predictive power (r²_pred) of 0.796, 0.833, 0.820 and 0.803 respectively. Docking studies revealed that those inhibitors able to bind to amino acid Gln859 by cGMP binding orientation called ‘glutamine-switch’, and also bind to the hydrophobic clamp of PDE2 isoform, could possess high selectivity for PDE2. From the results of all the studies, structure–activity relationships and structural requirements for binding to active site of PDE2 were established which provide useful guidance for the design and future synthesis of potent PDE2 inhibitors.     

Impact assessment of the rational selection of training and test sets on the predictive ability of QSAR models

This study performed an analysis of the influence of the training and test set rational selection on the quality and predictively of the quantitative structure–activity relationship (QSAR) model. The study was carried out on three different datasets of Influenza Neuraminidase (H1N1) inhibitors. The three datasets were divided into training and test sets using three rational selection methods: based on k-means, Kennard–Stone algorithm and Activity and the results were compared with Random selection. Then, a total of 31,490 mathematical models were developed and those models that presented a determination coefficient higher than: r²_train > 0.8, r²_loo > 0.7, r²_test > 0.5 and minimum standard deviation (SD) and minimum root-mean square error (RMS) were selected. The selected models were validated using the internal leave-one-out method and the predictive capacity was evaluated by the external test set. The results indicate that random selection could lead to erroneous results. In return, a rational selection allows for obtaining more reliable conclusions. The QSAR models with major predictive power were found using the k-means algorithm and selection by activity.     

3D-Pharmacophore mapping of thymidine-based inhibitors of TMPK as potential antituberculosis agents

Tuberculosis (TB) is the primary cause of mortality among infectious diseases. Mycobacterium tuberculosis monophosphate kinase (TMPKmt) is essential to DNA replication. Thus, this enzyme represents a promising target for developing new drugs against TB. In the present study, the receptor-independent, RI, 4D-QSAR method has been used to develop QSAR models and corresponding 3D-pharmacophores for a set of 81 thymidine analogues, and two corresponding subsets, reported as inhibitors of TMPKmt. The resulting optimized models are not only statistically significant with r ² ranging from 0.83 to 0.92 and q ² from 0.78 to 0.88, but also are robustly predictive based on test set predictions. The most and the least potent inhibitors in their respective postulated active conformations, derived from each of the models, were docked in the active site of the TMPKmt crystal structure. There is a solid consistency between the 3D-pharmacophore sites defined by the QSAR models and interactions with binding site residues. Moreover, the QSAR models provide insights regarding a probable mechanism of action of the analogues.