Abstract
Hierarchical QSAR technology (HiT QSAR) was used for consensus QSAR modelling of 65 SIRT1 activators. Simplex representation of molecular structure (SiRMS) has been used for descriptor generation. The predictive QSAR models were developed using the partial least squares (PLS) method. The QSAR models were built up according to OECD principles. One hundred rounds of Y-scrambling were performed for each selected model to exclude chance correlations. A successful consensus model (r2 = 0.830, = 0.754) was obtained from the five best QSAR models. Leverage, ellipsoid and local tree domain of applicability (DA) approaches have been used for evaluation of the quality of predictions. Molecular fragments responsible for an increase and decrease of the activation properties have been determined by mechanistic interpretation of the developed QSAR model.
Acknowledgments
We would like to express our thanks to Central Instrumental Laboratory, GJU S&T, Hisar, India for providing financial support under DST-Purse program [Ref. #2017/353]. The authors are grateful to Dr. V.E. Kuz’min for providing the HiT QSAR software. We are thankful to Alessandro Pedretti, Dipartimento di Scienze Farmaceutiche, Facoltà di Scienze del Farmaco, Università degli Studi di Milano, Italy for providing the VEGA ZZ software. We would also like to thank the Drug Theoretics and Cheminformatics (DTC) Laboratory, Jadavpur University, India for providing the XternalValidationPlus 1.2 Tool for external validation, available at http://dtclab.webs.com/software-tools.