Drug Release Nanoparticle System Design: Data Set Compilation and Machine Learning Modeling

Magnetic nanoparticles (NPs) are gaining significant
interest in
the field of biomedical functional nanomaterials because of their
distinctive chemical and physical characteristics, particularly in
drug delivery and magnetic hyperthermia applications. In this paper,
we experimentally synthesized and characterized new Fe3O4-based NPs, functionalizing its surface with a 5-TAMRA
cadaverine modified copolymer consisting of PMAO and PEG. Despite
these advancements, many combinations of NP cores and coatings remain
unexplored. To address this, we created a new data set of NP systems
from public sources. Herein, 11 different AI/ML algorithms were used
to develop the predictive AI/ML models. The linear discriminant analysis
(LDA) and random forest (RF) models showed high values of sensitivity
and specificity (>0.9) in training/validation series and 3-fold
cross
validation, respectively. The AI/ML models are able to predict 14
output properties (CC50 (μM), EC50 (μM),
inhibition (%), etc.) for all combinations of 54
different NP cores classes vs. 25 different coats and vs. 41 different
cell lines, allowing the short listing of the best results for experimental
assays. The results of this work may help to reduce the cost of traditional
trial and error procedures.