Showing papers by "Surendra Kumar published in 2017"
TL;DR: A quantitative structure activity relationship (QSAR) model was developed by a forward stepwise multiple linear regression method to predict the activity of withanolide analogs against human breast cancer and the results of the present study may help in the designing of lead compound with improved activity.
Abstract: Withanolides are a group of pharmacologically active compounds present in most prodigal amounts in roots and leaves of Withania somnifera (Indian ginseng), one of the most important medicinal plants of Indian traditional practice of medicine. Withanolides are steroidal lactones (highly oxygenated C-28 phytochemicals) and have been reported to exhibit immunomodulatory, anticancer and other activities. In the present study, a quantitative structure activity relationship (QSAR) model was developed by a forward stepwise multiple linear regression method to predict the activity of withanolide analogs against human breast cancer. The most effective QSAR model for anticancer activity against the SK-Br-3 cell showed the best correlation with activity (r2=0.93 and rCV2 =0.90). Similarly, cross-validation regression coefficient (rCV2=0.85) of the best QSAR model against the MCF7/BUS cells showed a high correlation (r2=0.91). In particular, compounds CID_73621, CID_435144, CID_301751 and CID_3372729 have a marked antiproliferative activity against the MCF7/BUS cells, while 2,3-dihydrowithaferin A-3-beta-O-sulfate, withanolide 5, withanolide A, withaferin A, CID_10413139, CID_11294368, CID_53477765, CID_135887, CID_301751 and CID_3372729 have a high activity against the Sk-Br-3 cells compared to standard drugs 5-fluorouracil (5-FU) and camptothecin. Molecular docking was performed to study the binding conformations and different bonding behaviors, in order to reveal the plausible mechanism of action behind higher accumulation of active withanolide analogs with β-tubulin. The results of the present study may help in the designing of lead compound with improved activity.
54 citations
TL;DR: This study provides machine learning-based classification models for the carcinogenicity and mutagenicity of chemicals and finds the best models based on the random forest approach correctly classify more than 70% of compounds in the test set.
11 citations
01 Jan 2017
TL;DR: Considering the classification accuracy obtained by SVM clustering with mean band power features in most of the EEG channels of motor cortex, it can be suggested that the noninvasive EEG signals can be considered as a tool for development of an automated online diagnostic system for the chronic alcoholic condition.
Abstract: In this study, the magnitude and spatial distribution of frequency spectrum in the resting electroencephalogram (EEG) were examined to address the classification of alcoholism in the central nervous system. The EEG signals for chronic alcoholic conditions taken from motor cortex region were divided into five sub-frequency band and Hilbert Huang Transform is applied for feature extraction of the EEG signals. Since the extracted feature has large data dimension, it is reduced using Linear Discriminate Analysis. Support Vector Machine has been used for classification. Highest Classification accuracy 76.67% has been seen in the central (CZ) and left central (C3) and left parietal (P3) hemisphere when the classifier was tested with 150 EEG epochs of two seconds. In present results CZ, C3, P3 focal area of brain shown the better classification accuracy, which can be concludes as the persons with chronic alcoholism are having hyper active zone in comparison with control. Considering the classification accuracy obtained by SVM clustering with mean band power features in most of the EEG channels of motor cortex, it can be suggested that the noninvasive EEG signals can be considered as a tool for development of an automated online diagnostic system for the chronic alcoholic condition.