Extending the identification of structural features responsible for anti-SARS-CoV activity of peptide-type compounds using QSAR modelling
Vijay Hariram Masand, Vesna Rastija, Meghshyam K. Patil, Ajaykumar Gandhi, A. Chapolikar · SAR and QSAR in environmental research · 2020
A quantitative structure–activity relationship (QSAR) model was built from a dataset of 54 peptide-type compounds as SARS-CoV inhibitors. The analysis was executed to identify prominent and hidden structural features that govern anti-SARS-CoV activity. The QSAR model was derived from the genetic algorithm–multi-linear regression (GA-MLR) methodology. This resulted in the generation of a statistically robust and highly predictive model. In addition, it satisfied the OECD principles for QSAR validation. The model was validated thoroughly and fulfilled the threshold values of a battery of statistical parameters (e.g. r2 = 0.87, Q2loo = 0.82). The derived model is successful in identifying many atom-pairs as important structural features that govern the anti-SARS-CoV activity of peptide-type compounds. The newly developed model has a good balance of descriptive and statistical approaches. Consequently, the present work is useful for future modifications of peptide-type compounds for SARS-CoV and SARS-CoV-2 activity.