An ANN-Based QSAR Model to Predict Anti-Staphylococcus aureus Activity of Oxadiazoles

Methods: After drawing structures (۱۰۲) in ChemDraw, structure optimization was done inGaussian ۰۹. Descriptors were generated by Dragon (۳۲۶۰ for each compound). Feature selectionwas done by SPSS modeller and ۳۰۰ descriptors were selected. GMDH shell software was used tocreate a predictive model. PLS was also performed using crossval.m and pls.m that were availablein MATLAB ۲۰۱۴ toolbox to generate another modelResults: In this study, a previously-synthesized oxadiazole library was used to build a QSARmodel based on the Group Method of Data Handling (GMDH) method and Partial Least Squares(PLS) regression. Owing to their high correlation coefficients (R۲) for test and training data, bothmethods are sufficiently reliable. In this study, the active compounds of the library were used asa template to design new chemical compounds predicted to have a great anti-Staphylococcusaureus (S. aureus) activity according to PLS, GMDH, and docking methods. GMDH and PLS arehighly flexible such that they can include other information like absorption, distribution, metabolism,and excretion (ADMT) and toxicity.Conclusion: The selected methods can be used to handle huge amounts of data from a large libraryof chemical compounds and help research and development (R&D) process. Additionally,the designed model and the proposed compounds can help other researchers to find the bestanti- Staphylococcus aureus chemical compounds.