A Quantitative Structure-Activity Relationship (QSAR) Study of Anti-cancer Drugs

A very simple, strong, descriptive and interpretable model, based on a quantitative structure– activity relationship (QSAR), is developed using multiple linear regression approach and quantum chemical descriptors derived from HF theories using 6-31G* basis set for determination of the inhibit 50% of sensitive cell growth (pLD50) of some anti-cancer drugs. By molecular modeling and calculation of descriptors, two significant descriptors related to the pLD50 values of the anti-cancer drugs, were identified. A multiple linear regression (MLR) model based on 13 molecules as a training set has been developed for the prediction of the pLD50 of some anti-cancer drugs using these quantum chemical descriptors. The effects of these theoretical descriptors on the biological activity are discussed. A model with low prediction error and high correlation coefficient was obtained. This model was used for the prediction of the pLD50 values of some anti-cancer drugs. A multi-parametric equation containing maximum two descriptors at HF/6-31G* method with good statistical qualities (R2 train=0.915, Ftrain=54.43, Q2 LOO=0.891,R2 adj=0.899,Q2 LGO=0.879) was obtained by Multiple Linear Regression using stepwise method.

Author(s): S. Vahdani and Z. Bayat

Abstract | PDF

Share This Article