Parameters Influencing Gene Delivery Efficiency of PEGylated Chitosan Nanoparticles: Experimental and Modeling Approach

Experimentation of nanomedicine is labor-intensive, time-consuming, and requires costly laboratory consumables. Constructing a reliable mathematical model for such systems also challenging due to the difficulties in gathering sufficient number data points. Artificial neural networks (ANNs) are indicated as an efficient approach investigate cause-effect relationships predict output variables. Herein, ANN adapted into plasmid DNA (pDNA) encapsulated PEGylated chitosan nanoparticles cross-linked with sodium tripolyphosphate (TPP) effects critical parameters on transfection efficiencies nanoparticles. The developed based experimental results three independent input variables: 1) polyethylene glycol (PEG) molecular weight, 2) PEG concentration, 3) nanoparticle along one variable percentage green fluorescent protein (GFP) expression, which refers efficiency. constructed further validated leave-p-out cross-validation method. indicate that has good prediction capability influential capturing different groups. Overall, this study reveals could be tool nanoparticle-mediated gene delivery impacts detail reduced effort cost.