TY - JOUR
ID - 110825
TI - Prediction of IC50 Values of 2âˆ’benzyloxybenzamide Derivatives using Multiple Linear Regression and Artificial Neural Network Methods
JO - Iranian Journal of Mathematical Chemistry
JA - IJMC
LA - en
SN - 2228-6489
AU - Masoomi Sefiddashti, Fariba
AU - Haddadi, Hedayat
AU - Asadpour, Saeid
AU - Ghanavati Nasab, Shima
AD - Department of Chemistry, Faculty of Sciences, Shahrekord University, P. O. Box 115, Shahrekord, Iran
Y1 - 2020
PY - 2020
VL - 11
IS - 3
SP - 179
EP - 199
KW - SMS2 inhibitor
KW - benzyloxy benzamide derivatives
KW - QSAR
KW - Multiple Linear Regression (MLR)
KW - Artificial neural network (ANN)
DO - 10.22052/ijmc.2020.217837.1483
N2 - In this study, six molecular descriptors were selected from a pool of variables using stepwise regression to built a QSAR model for a series of 2-benzyloxy benzamide derivatives as an SMS2 inhibitor to reduce atherosclerosis. Simple multiple linear regression (MLR) and a nonlinear method, artificial neural network (ANN), were used to modeling the bioactivities of the compounds. Modeling was carried out in total with 34 compounds of 2-benzyl oxybenzamide derivatives. PCA was used to divide the compounds into two groups of two training series and tests. The model was constructed with 27 combinations as training set, then the validity and predictive ability of the model were evaluated with the remaining 7 combinations. While the MLR provides an acceptable model for predictions, the ANN-based model significantly improves the predictive ability. In ANN model the average relative error (RE%) of prediction set is lower than 1% and square correlation coefficient (R2) is 0.9912.
UR - https://ijmc.kashanu.ac.ir/article_110825.html
L1 - https://ijmc.kashanu.ac.ir/article_110825_9ad7181fa7989d251569b505e68a3361.pdf
ER -