Background: Molecular structures hold a wealth of knowledge that can be applied further. The information was decoded using a traditional Quantitative Structure-Activity Relationship (QSAR) approach based on the descriptors. A mono substituted series of Glucokinase-Glucokinase Regulatory Protein Inhibitors (GK-GKRP/GCKR) was the subject of the study. AIM: A new chemical will be created using this knowledge. To determine the suggested compound's binding pattern, docking tests will be carried out. Material and methods: In the present study, both linear and nonlinear statistical methods were sequentially applied. These methods included multiple linear regression (MLR), partial least squares (PLS), and artificial neural networks (ANN). The created model was evaluated using a variety of statistical techniques to clearly demonstrate its dependability and accuracy. Result: The various statistical parameters s value: 0.37, F-value: 64.61, r: 0.92, r2: 0.84 and r2CV: 0.80 demonstrated the predictive capability and resilience of the model using the training set. The validation of training set was carried out using test set. Conclusion: The model sheds light on the different descriptors chosen for the current investigation. The current work not only demonstrates the role that different substituents play in biological activity, but it also suggests modifications that could be made to the design of new effective compounds to increase selectivity and decrease toxicity.