A Quantitative Structure Activity Relationship (QSAR) study has been attempted on ciprofloxacin derivatives as potent anti-lung cancer. QSAR models were derived with the aid of multi-linear regression (MLR) approach using topological, molecular shape, electronic and structural descriptors. The predictive ability of the QSAR models generated were validated and the best model selected has squared correlation coefficient (R2) of 0.954801, adjusted squared correlation coefficient (Radj) of 0.939265, Leave one out (LOO) cross validation coefficient (Q_cv^2) value of 0.907523. The external validation set used for confirming the predictive power of the model has its R2pred of 0.8387. The QSAR models point out that AATSC2m, VR3_Dzp and BIC2 are the important descriptors effectively describing the bioactivity of these compounds.

The toxicity and high resistance to the commercially sold breast-cancer drugs have become more alarming and the demand to produce new and less toxic breast-cancer drugs arises. In silico studies was carried out on some quinoline derivatives to investigate their reported activities against breast cancer and thereby generate a model with a better activity against breast cancer. The chemical structures of the compounds were optimized using Spartan software at Density Functional Theory (DFT) level, utilizing the B3LYP/ 6-31G * basis set. Four QSAR models were generated using Multi-Linear Regression (MLR) and Genetic Function Approximation (GFA) method. Equation one was chosen as the best model based on the validation parameters. The validation parameters was found to be statistically significant with square correlation coefficient (R 2 ) of 0.9853, adjusted square correlation coefficient ( ) of 0.9816, cross validation coefficient ( ) of 0.9727 and an external correlation coefficient square ( ) of 0.6649 was used to validate the model. The built model was a good and robust one for it passed the minimum requirement for generating a QSAR model. k e y w o r d s QSAR model Model validations Breast cancer