Tomocomd-Cardd, a novel approach for computer-aided ‘ rational’ drug design: I. Theoretical and experimental assessment of a promising method for computational screening and in silico design of new anthelmintic compounds

Summary In this work, the TOMOCOMD-CARDD approach has been applied to estimate the anthelmintic activity. Total and local (both atom and atom-type) quadratic indices and linear discriminant analysis were used to obtain a quantitative model that discriminates between anthelmintic and non-anthelmintic drug-like compounds. The obtained model correctly classified 90.37% of compounds in the training set. External validation processes to assess the robustness and predictive power of the obtained model were carried out. The QSAR model correctly classified 88.18% of compounds in this external prediction set. A second model was performed to outline some conclusions about the possible modes of action of anthelmintic drugs. This model permits the correct classification of 94.52% of compounds in the training set, and 80.00% of good global classification in the external prediction set. After that, the developed model was used in virtual in silicoscreening and several compounds from the Merck Index, Negwers handbook and Goodman and Gilman were identified by models as anthelmintic. Finally, the experimental assay of one organic chemical (G-1) by an in vivo test coincides fairly well (100) with model predictions. These results suggest that the proposed method will be a good tool for studying the biological properties of drug candidates during the early state of the drug-development process.     

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.     

Computational models to predict blood–brain barrier permeation and CNS activity

The blood-brain permeation of a structurally diverse set of 281 compounds was modeled using linear regression and a multivariate genetic partial least squares (G/PLS) approach. Key structural features affecting the logarithm of blood-brain partitioning (logBB) were captured through statistically significant quantitative structure-activity relationship (QSAR) models. These relationships reveal the importance of logP, polar surface area, and a variety of electrotopological indices for accurate predictions of logBB. The best models reveal an excellent correlation (r > 0.9) for a training set of 58 compounds. Likewise, the comparison of the average logBB values obtained from an ensemble of QSAR models with experimental values also verifies the statistical quality of the models (r > 0.9). The models provide good agreement (r approximately 0.7) between the predicted logBB values for 34 molecules in the external validation set and the experimental values. To further validate the models for use during the drug discovery process, a prediction set of 181 drugs with reported CNS penetration data was used. A >70% success rate is obtained by using any of the QSAR models in the qualitative prediction for CNS permeable (active) drugs. A lower success rate (approximately 60%) was obtained for the best model for CNS impermeable (inactive) drugs. Combining the predictions obtained from all the models (consensus) did not significantly improve the discrimination of CNS active and CNS inactive molecules. Finally, using the therapeutic classification as a guiding tool, the CNS penetration capability of over 2000 compounds in the Synthline database was estimated. The results were very similar to the smaller set of 181 compounds.     

Docking ligands into flexible and solvated macromolecules. 2. Development and application of fitted 1.5 to the virtual screening of potential HCV polymerase inhibitors

HCV NS5B polymerase is a validated target for the treatment of hepatitis C, known to be one of the most challenging enzymes for docking programs. In order to improve the low accuracy of existing docking methods observed with this challenging enzyme, we have significantly modified and updated F itted 1.0, a recently reported docking program, into F itted 1.5. This enhanced version is now applicable to the virtual screening of compound libraries and includes new features such as filters and pharmacophore- or interaction-site-oriented docking. As a first validation, F itted 1.5 was applied to the testing set previously developed for F itted 1.0 and extended to include hepatitis C virus (HCV) polymerase inhibitors. This first validation showed an increased accuracy as well as an increase in speed. It also shows that the accuracy toward HCV polymerase is better than previously observed with other programs. Next, application of F itted 1.5 to the virtual screening of the Maybridge library seeded with known HCV polymerase inhibitors revealed its ability to recover most of these actives in the top 5% of the hit list. As a third validation, further biological assays uncovered HCV polymerase inhibition for selected Maybridge compounds ranked in the top of the hit list.     

How to winnow actives from inactives: introducing molecular orthogonal sparse bigrams (MOSBs) and multiclass Winnow

In the present paper we combine the Winnow algorithm and an advanced scheme for feature generation into a tool for multiclass classification. The Winnow algorithm, specifically designed in the late 1980s to work well with high-dimensional data, by design ignores most of the irrelevant features for the scoring of each single training/test case. To augment the pool of available molecular features we use the Winnow algorithm in conjunction with a process that creates additional features from a set of given ones. We adapt a technique formerly employed in text classification termed "orthogonal sparse bigrams" and extend the use of that method to the domain of cheminformatics. Using circular molecular fingerprints as initial features, we create "molecular orthogonal sparse bigrams" (MOSBs) and report their successful application to the task of classification of bioactive molecules. Additionally, we introduce a memory-efficient way of bagging individual classifiers, avoiding the need to hold the complete training data set in memory. To compare the performance of our method with published results, we use the Hert data set of 8293 active molecules in 11 classes. We compare our method to Random Forest and find that our method not only is comparable or better in classification accuracy (up to 50% higher in MCC [Matthews correlation coefficient], 98% higher in fraction of correct predictions) but also is quicker to train (by a factor between 2 and 18, depending on the feature generation), more memory efficient, and able to cope more easily with large data sets when we seeded the actives into a pool of 94290 inactive molecules. It is shown that this method can be used with different fingerprints.     

Pharmacophore Mode lingand Virtual Screening to Design the Potential Influenza Virus Endonuclease Inhibitors

Influenza virus endonuclease is an attractive target for antiviral therapy in the treatment of influenza infection. The purpos e of this study is to design a novel antiviral agent with improved biological activities against the influenza virus endonuclease. In this study, chemical feature‐based 3D pharmacophore models were developed from 41 known influenza virus endonuclease inhibitors. The best quantitative pharmacohore model (Hypo 1), which consists of two hydrogen‐bond acceptors and two hydrophobic features, yields the highest correlation coefficient (R = 0.886). Hypo 1 was further validated by the cross validation method and the test set compounds. The application of this model for predicting the activities of 11 known influenza virus endonuclease inhibitors in the test set shows great success. The correlation coefficient of 0.942 and a cross validation of 95;% confidence level prove that this model is reliable in identifying structurally diverse compounds for influenza virus endonuclease inhibition. The most active compound (compound 1) from the training set was docked into the active site of the influenza virus endonuclease as an additional verification that the pharmacophore model is accurate. The docked conformation showed important hydrogen bond interactions between the compound and two amino acids, Lys 134 and Lys 137. After validation, this model was used to screen the NCI chemical database to identify new influenza virus endonuclease inhibitors. Our study shows that the to pranking compound out of the 10 newly identified compounds using fit value ranking has an estimated activity of 0.049 μM. These newly identified lead compounds can be further experimentally validated using in vitro techniques.     

Pharmacophore modeling and parallel screening for PPAR ligands

We describe the generation and validation of pharmacophore models for PPARs, as well as a large scale validation of the parallel screening approach by screening PPAR ligands against a large database of structure-based models. A large test set of 357 PPAR ligands was screened against 48 PPAR models to determine the best models for agonists of PPAR-alpha, PPAR-delta, and PPAR-gamma. Afterwards, a parallel screen was performed using the 357 PPAR ligands and 47 structure-based models for PPARs, which were integrated into a 1537 models comprising in-house pharmacophore database, to assess the enrichment of PPAR ligands within the PPAR hypotheses. For these purposes, we categorized the 1537 database models into 181 protein targets and developed a score that ranks the retrieved targets for each ligand. Thus, we tried to find out if the concept of parallel screening is able to predict the correct pharmacological target for a set of compounds. The PPAR target was ranked first more often than any other target. This confirms the ability of parallel screening to forecast the pharmacological active target for a set of compounds.