QSAR of Antitrypanosomal Activities of Polyphenols and their Analogues using Multiple Linear Regression and Artificial Neural Networks.

QSAR of Antitrypanosomal Activities of Polyphenols and their Analogues using Multiple Linear Regression and Artificial Neural Networks. Comb Chem High Throughput Screen. 2014 Aug 4; Authors: Rastija V, Masand VH Abstract In order to find quantitative-structure relationship for the antitrypanosomal activities (against Trypanosma brucei rhodesiense) of polyphenols that belong to the different structural groups, the multiple linear regression (MLR) and artificial neural networks (ANN) were employed. Analysis was performed on the two different size of training set (59 % and 78 % molecules in the training set), and the better MLR and ANN models was obtained for data set with the smaller training set. The best MLR model obtained with the five descriptors (R3m+, GAP, DISPv, HATS2m, JGI2) was able to account only 74 % of the variance of antitrypanosomal activities of the training set and achieved a high internal, but low external prediction. Nonlinearities of the best obtained ANN model compared with the linear model has improved the coefficient of determination to the 98.6 %, and shown the better external predictive ability. The obtained models show relevance of the distance between oxygen atoms in molecules of polyphenols, as well as stability of molecules, measured by difference between the energy of the highest occupied molecular orbital and the energy of the lowest unoccupied molecular orbital (GAP), for their activity. PMID: 25...
Source: Combinatorial Chemistry and High Throughput Screening - Category: Chemistry Authors: Tags: Comb Chem High Throughput Screen Source Type: research