Robust Prediction of Personalized Cell Recognition from a Cancer Population by a Dual Targeting Nanoparticle Library

Nanomaterials are used increasingly in diagnostics and therapeutics, particularly for malignancies. Efficient targeting of nanoparticles to specific cells is an important requirement for the development of successful nanoparticle-based theranostics and personalized medicines. Gold nanoparticles are surface modified using a library of small organic molecules, and optionally folate, to investigate their ability to target four cell lines from common cancers, three having high levels of folate receptors expression. Uptake of these nanoparticles varies widely with surface chemistriy and cell lines. Sparse machine learning methods are used to computationally model surface chemistry-uptake relationships, to make quantitative predictions of uptake for new nanoparticle surface chemistries, and to elucidate molecular aspects of the interactions. The combination of combinatorial surface chemistry modification and machine learning models will facilitate the rapid development of targeted theranostics. Efficient targeting of nanoparticles to specific cells is an important requirement for the development of successful nanoparticle-based cancer theranostics and personalized medicines. The cancer cell targeting ability of gold nanoparticles coated with a library of small organic molecules plus folate is modeled. Computational models can predict the degree of uptake of the nanoparticles as a function of surface chemistry.