Abstarct: The c-Met receptor tyrosine kinase is one of the most important molecular targets involved in signaling pathways associated with cancer cell growth, proliferation, and mextastasis. Although crizotinib was approved by the U.S. Food and Drug Administration (FDA) as the first c-Met inhibitor, the emergence of drug resistance and its pharmacokinetic limitations have highlighted the need for the development of novel c-Met inhibitors. Among the promising candidates, tetrahydrobenzothiazole derivatives have attracted considerable attention due to their favorable structural characteristics and their ability to establish effective interactions with the active site of the c-Met receptor. However, the experimental evaluation of a large number of candidate compounds is both time-consuming and costly. Therefore, computational approaches offer an efficient strategy to accelerate the screening and rational design of novel anticancer agents. n the present study, a quantitative structure–activity relationship (QSAR) model was developed for tetrahydrobenzothiazole derivatives using the Adaptive Least Absolute Shrinkage and Selection Operator (Adaptive LASSO, ALASSO). This approach was employed simultaneously for molecular descxriptor selection and predictive linear model construction. The predictive performance of the developed model was subsequently assessed using several statistical validation criteria. The obtained results, including an external test set coefficient of determination (R²) of 0.78 and a leave-one-out cross-validation coefficient (Q²LOO) of 0.85, demonstrated satisfactory predictive ability and acceptable model robustness. baxsed on the ALASSO model and the selected key molecular descxriptors, several new tetrahydrobenzothiazole derivatives with potential enhanced anticancer activity were designed. Molecular docking simulations were then performed to investigate the binding modes of the designed compounds within the active site of the c-Met receptor and to evaluate their interactions with the target protein. The docking results revealed that the proposed compounds were capable of forming favorable non-covalent interactions, including hydrogen bonds, van der Waals interactions, and other stabilizing contacts with key amino acid residues located in the receptor binding pocket. Overall, the good agreement between the predictions of the ALASSO model and the molecular docking results confirms the reliability and predictive capability of the proposed computational strategy. Therefore, integrating Adaptive LASSO-baxsed QSAR modeling with molecular docking provides an effective and rational frxamework for the identification and design of novel c-Met inhibitors baxsed on tetrahydrobenzothiazole derivatives.