Abstract
Cathepsin L (CatL) is a critical protease involved in cleaving the spike protein of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), facilitating viral entry into host cells. Inhibition of CatL is essential for preventing SARS-CoV-2 cell entry, making it a potential therapeutic target for drug development. Six QSAR models were established to predict the inhibitory activity (expressed as IC(50) values) of candidate compounds against CatL. These models were developed using statistical method heuristic methods (HMs), the evolutionary algorithm gene expression programming (GEP), and the ensemble method random forest (RF), along with the kernel-based machine learning algorithm support vector regression (SVR) configured with various kernels: radial basis function (RBF), linear-RBF hybrid (LMIX2-SVR), and linear-RBF-polynomial hybrid (LMIX3-SVR). The particle swarm optimization algorithm was applied to optimize multi-parameter SVM models, ensuring low complexity and fast convergence. The properties of novel CatL inhibitors were explored through molecular docking analysis. The LMIX3-SVR model exhibited the best performance, with an R2 of 0.9676 and 0.9632 for the training set and test set and RMSE values of 0.0834 and 0.0322. Five-fold cross-validation R5-fold2 = 0.9043 and leave-one-out cross-validation Rloo2 = 0.9525 demonstrated the strong prediction ability and robustness of the model, which fully proved the correctness of the five selected descriptors. Based on these results, the IC(50) values of 578 newly designed compounds were predicted using the HM model, and the top five candidate compounds with the best physicochemical properties were further verified by Property Explorer Applet (PEA). The LMIX3-SVR model significantly advances QSAR modeling for drug discovery, providing a robust tool for designing and screening new drug molecules. This study contributes to the identification of novel CatL inhibitors, which aids in the development of effective therapeutics for SARS-CoV-2.