QD74 : Quantitative Structure – Activity Relationship Study Of Thiocarbamates Derivatives As New Class Of Non – Nucleoside HIV - Inhibitors
Thesis > Central Library of Shahrood University > Chemistry > MSc > 2010
Authors:
Abstarct: Non-nucleoside reverse transcxriptase inhibitors (NNRTIs) are a class of anti retroviral drugs used to treat HIV infection. NNRRTIs inhibit activity of reverse transcxriptase (RT), an enzyme that controls the replications of the genetic material of HIV. In the first section, Quantitative structure – activity relationship (QSAR) models were constructed for predicting the Anti-HIV activity of a set of phenethyl thiazole thiourea (PETT) analogs, as potent HIV-1 reverse transcxriptase inhibitors by calculated descxriptors. The stepwise multiple linear regression method was used to select the most important descxriptors. Then significant descxriptors were used as input for QSAR model generation using multiple linear regression (MLR) and artificial neural network (ANN). Data set was randomly divided into training set and test set including 39 and 10 compounds, respectively. Training set was used in the selection the best MLR and ANN models by cross validation technique. The validation study of the MLR and ANN models was performed using test set and leave-one-out technique. The results obtained for prediction of anti HIV activity of the test set by MLR and ANN models showed squared correlation coefficients of 0.766 and 0.913 respectively.
In the second section, MLR and ANN methods were used for modeling and accurate prediction of Anti-HIV activities for a set of O-[2-(2- hydroxyl carbonyl benzamido) ethyl]-N-aryl thiocarbamate derivatives. The data set was randomly divided into training and test set containing 25 and 7 chemical, respectively. Training set was used in the selection the best MLR and ANN models by cross validation technique. The prediction ability of the proposed models was evaluated by test set and leave-one-out method. The squared correlation coefficients obtained for test set by MLR and ANN models were 0.920 and 0.979, respectively. The results obtained showed proper prediction power of the proposed models.
Keywords:
#QSAR #Anti -HIV #Artificial neural network #Multiple Linear Regression Link
Keeping place: Central Library of Shahrood University
Visitor:
Keeping place: Central Library of Shahrood University
Visitor: