Machine Learning-Based Virtual Screening and Molecular Simulation Approaches Identified Novel Potential Inhibitors for Cancer Therapy

Cyclin-dependent kinase 2 (CDK2) is a promising target for cancer treatment, developing new effective CDK2 inhibitors of great significance in anticancer therapy. The involvement tumorigenesis has been debated, but recent evidence suggests that specifically inhibiting could be beneficial treating certain tumors. This approach remains attractive the development drugs. Several small-molecule targeting have reached clinical trials, selective inhibitor yet to discovered. In this study, we conducted machine learning-based drug designing search candidate CDK2. Machine learning models, including k-NN, SVM, RF, and GNB, were created detect active inactive target. models assessed using 10-fold cross-validation ensure their accuracy reliability. These methods are highly suitable classifying compounds as either or through virtual screening extensive compound libraries. Subsequently, techniques employed analyze test dataset obtained from zinc database. A total 25 with 98% predicted against docked into CDK2’s site. Finally, three selected based on good docking score, and, along reference compound, underwent MD simulation. Gaussian naïve Bayes model yielded superior results compared other models. top hits exhibited enhanced stability compactness compound. conclusion, our study provides valuable insights identifying refining lead inhibitors.