QSAR modeling for the prediction of pGI 50 activity of compounds on LOX IMVI cell line and ligand-based design of potent compounds using in silico virtual screening

AbstractThe anti-melanoma activity (pGI50) values of 71 compounds from the National Cancer Institute (NCI) data bank on LOX IMVI cell line were modeled to illustrate the Quantitative structure –activity relationship (QSAR) of the compounds. The genetic function algorithm (GFA) has been used to select the most relevant descriptors so as to improve the performance of the QSAR model. The statistical significance of the model was verified based on the values of validation parameters such as\( R_{{{\text{train}} }}^{2} \) (0.867),\( R_{{{\text{adj}} }}^{2} \) (0.848),\( Q_{{{\text{cv}} }}^{2} \) (0.809) and\( R_{{{\text{test}} }}^{2} \) (0.749) needed to evaluate the robustness and strength of the model. The result of the internal and external validation of the model indicates that the model is good and could be used to predict pGI50 of anti-melanoma compounds on LOX IMVI cell line for which no experimental data are available. Compound 41 was selected using in-silico screening method as a template due to its good pGI50 (9.793) and was utilized to design new potent compounds, thereby enhancing the activity of the parent structure. Ten (10) new potent compounds were deigned and predicted using the proposed model. The predicted pGI50 of the majority of the designed analogous were more than the lead compound 41 used for the design and among which compoundN5 showed the best activity (pGI50=13.186). Thus, this study provides a valuable approach and new direction to novel drug discover...
Source: Network Modeling Analysis in Health Informatics and Bioinformatics - Category: Bioinformatics Source Type: research