KinasePred: A Computational Tool for Small-Molecule Kinase Target Prediction

Abstract

Protein kinases are key regulators of cellular processes and critical therapeutic targets in diseases like cancer, making them a focal point for drug discovery efforts. In this context, we developed KinasePred, a robust computational workflow that combines machine learning and explainable artificial intelligence to predict the kinase activity of small molecules while providing detailed insights into the structural features driving ligand-target interactions. Our kinase-family predictive tool demonstrated significant performance, validated through virtual screening, where it successfully identified six kinase inhibitors. Target-focused operational models were subsequently developed to refine target-specific predictions, enabling the identification of molecular determinants of kinase selectivity. This integrated framework not only accelerates the screening and identification of kinase-targeting compounds but also supports broader applications in target identification, polypharmacology studies, and off-target effect analysis, providing a versatile tool for streamlining the drug discovery process.

Keywords: kinase; machine learning; virtual screening.

Figure 1

Results obtained from SHAP analysis for the ROCK2 inhibitor 1 (A), the BTK inhibitor 2 (B), and the GSK-3β inhibitor 3 (C) recently co-crystallized with their corresponding kinase target. The orange-colored moieties indicate a greater impact on the prediction.

Figure 2

Chemical structures of the eight molecules identified through virtual screening.

Figure 3

Success rates of single-target RF models in predicting kinase inhibitory activity for the 8 selected compounds (VS1–8). The success rate represents the percentage of correctly predicted kinase activities obtained for each compound against the 20 experimentally tested targets.