Entity

Time filter

Source Type

Laxmi Nagar, India

Singh K.P.,Academy of Scientific and Innovative Research | Singh K.P.,Indian Institute of Toxicology Research | Gupta S.,Academy of Scientific and Innovative Research | Gupta S.,Indian Institute of Toxicology Research | Basant N.,Kanban Systems Pvt. Ltd.
Chemometrics and Intelligent Laboratory Systems | Year: 2015

The permeability of the molecules through the cultured Caco-2 cells is an established in vitro method for the assessment of the absorption of oral drugs. The computational approach for predicting the cellular permeability of molecules may potentiate the screening of new drugs. In this study, gradient boosted tree (GBT) approach based qualitative and quantitative structure-activity relationship (SAR) models have been established for binary classification (moderate-poor and highly permeable) and permeability prediction of molecules using the Caco-2 cell dataset. The structural diversity of the chemicals and nonlinear structure in the considered data were tested by the similarity index and Brock-Dechert-Scheinkman statistics. The external predictive power of the developed SAR models was evaluated through the internal and external validation procedures recommended in QSAR literature. In complete data, the qualitative SAR model rendered classification accuracy of 99.26%, while the quantitative SAR model yielded a correlation (R2) of 0.917 between the measured and predicted permeability values with the mean squared error (MSE) of 0.08. The results suggest for the appropriateness of the developed SAR models to reliably predict the cellular permeability of diverse chemicals in Caco-2 cells and can be useful tools for initial screening of molecules in the drug development process. © 2014 Elsevier B.V.


Gupta S.,Indian Institute of Toxicology Research | Basant N.,Kanban Systems Pvt. Ltd. | Singh K.P.,Indian Institute of Toxicology Research
Combustion Theory and Modelling | Year: 2015

This study reports linear chemometric methods for identification of explosives and prediction of their characteristic parameters using a set of descriptors derived for 244 chemicals. Linear discriminant analysis and k-means clustering methods were developed for discriminating the ideal, non-ideal, and non-explosives, whereas logistic regression and partial least squares regression methods were developed for predicting the detonation parameters. Classification models yielded misclassification of 10.66 and 9.84% in complete data, and regression models predicted detonation velocity and pressure with correlation values of 0.876, 0.861, 0.879 and 0.836 in complete data. These models can be used for predicting the behaviour of new chemicals. © 2015 Taylor & Francis.


Gupta S.,Academy of Scientific and Innovative Research | Gupta S.,Indian Institute of Toxicology Research | Basant N.,Kanban Systems Pvt. Ltd. | Singh K.P.,Academy of Scientific and Innovative Research | Singh K.P.,Indian Institute of Toxicology Research
SAR and QSAR in Environmental Research | Year: 2015

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. © 2015, © 2015 Taylor & Francis.


Gupta S.,Indian Institute of Toxicology Research | Basant N.,Kanban Systems Pvt. Ltd. | Singh K.P.,Indian Institute of Toxicology Research
SAR and QSAR in Environmental Research | Year: 2015

The hazardous dose of a chemical (HD50) is an emerging and acceptable test statistic for the safety/risk assessment of chemicals. Since it is derived using the experimental toxicity values of the chemical in several test species, it is highly cumbersome, time and resource intensive. In this study, three machine learning-based QSARs were established for predicting the HD50 of chemicals in warm-blooded species following the OECD guidelines. A data set comprising HD50 values of 957 chemicals was used to develop SDT, DTF and DTB QSAR models. The diversity in chemical structures and nonlinearity in the data were verified. Several validation coefficients were derived to test the predictive and generalization abilities of the constructed QSARs. The chi-path descriptors were identified as the most influential in three QSARs. The DTF and DTB performed relatively better than SDT model and yielded r2 values of 0.928 and 0.959 between the measured and predicted HD50 values in the complete data set. Substructure alerts responsible for the toxicity of the chemicals were identified. The results suggest the appropriateness of the developed QSARs for reliably predicting the HD50 values of chemicals, and they can be used for screening of new chemicals for their safety/risk assessment for regulatory purposes. © 2015 Taylor & Francis.


Basant N.,Kanban Systems Pvt. Ltd. | Gupta S.,Indian Institute of Toxicology Research | Singh K.P.,Indian Institute of Toxicology Research
Journal of Molecular Liquids | Year: 2015

The ionic liquids (ILs) constitute a group of novel chemicals that have potential industrial applications. Designing of safer ILs is among the priorities of the chemists and toxicologists today. Computational approaches have been considered appropriate methods for prior safety assessment of the chemicals. The present study is an attempt to investigate the chemical attributes of a wide variety of ILs towards their inhibitory potential of acetyl cholinesterase enzyme (AChE) through the development of predictive qualitative and quantitative structure-activity relationship (SAR) models in light of the OECD principles. Here, machine learning based cascade correlation network (CCN) and support vector machine (SVM) SAR models were established for qualitative and quantitative prediction of the AChE inhibition potential of ILs. Diversity and nonlinearity of the considered dataset were evaluated. The CCN and SVM models were constructed using simple descriptors and validated with external data. Predictive power of these SAR models was established through deriving several stringent parameters recommended for QSAR studies. The developed SAR models exhibited better statistical confidence than those in the previously reported studies. The models identified the structural elements of the ILs responsible for the AChE inhibition, and hence could be useful tools in designing of safer and green ILs. © 2015 Published by Elsevier B.V.

Discover hidden collaborations