The protein corona (PC) has widely been demonstrated to impact the pharmacokinetics, safety, and efficiency of nanoparticle (NP) systems for clinical applications such as drug or vaccine delivery. However, a comprehensive understanding of PC formation and its overall impact on biological behavior remains challenging due to the wide range of possible physicochemical and experimental parameters that may impact NP-PC formation and interactions, leaving important patterns difficult to identify. Machine learning (ML) algorithms have increasingly been used to analyze datasets and identify patterns that govern NP-PC interactions, showing great potential to enhance NP-PC experimental and pharmacological analysis. In this review, we conducted a systemic literature review for ML-based NP-PC analyses in PubMed and Web of Science between 1 January 2000 to 1 November 2025. We discuss key developments in the identified ML workflows for the prediction of NP-PC interactions, including PC composition and formation dynamics as well as pharmacological and toxicologically relevant endpoints like NP biodistribution and cellular uptake. We also highlight future perspectives in the field, such as improving dataset diversity, analytical protocol harmonization, and model transparency. We aim to guide future research toward more robust and informative ML approaches for optimizing NP design and predicting nano-bio interactions.
Canchola et al. (Tue,) studied this question.