Abstract: Receptor tyrosine kinases (RTKs) are key regulators of cellular functions, such as differentiation, migration and proliferation. Dysregulated RTK activity is a contributor for various different diseases, including neurological disorders and cancer. Small molecule inhibitors are often used as therapeutic drugs for patients with conditions involving constitutively active RTKs, however their development is very costly and time-consuming. We developed two extremely randomized trees machine learning models to predict small molecule pKi and pIC50 values, which are measures of inhibitory potency against RTKs. Our models achieved high accuracy, with Pearson’s correlation coefficients of 0.762 and 0.768 for pKi and pIC50, respectively, on independent validation test sets. We also identified the molecular features that influence the inhibitory effects of small molecules on RTKs, such as graph-based features, providing insights for drug design.