Understanding protein corona composition is essential for evaluating their potential applications in biomedicine. Relative protein abundance (RPA), accounting for the total proteins in the corona, is an important parameter for description. We comprehensively predicted RPA using multiple machine-learning algorithms. An accurate prediction of whether a protein was adsorbed on the nanoparticles (i.e., whether the RPA is greater than 0), a dichotomous prediction, was realized using multiple machine learning algorithms. The advantages and disadvantages of the different machine learning algorithms were analyzed using Shapley Additive exPlanations-based interpretable analysis. We selected machine learning algorithms to build regression models to predict the specific value of the RPA based on the classification prediction experience. After interpretable analysis, we gained insights into the differences in the learning pattern differences of machine-learning algorithms on protein corona information data.