Modelling and optimization of nanovector synthesis for applications in drug delivery systems

TL;DR

This paper reviews the use of AI and metaheuristic algorithms in optimizing nanovector synthesis for drug delivery, highlighting neural networks' modeling advantages and effective metaheuristics like cuckoo search.

Contribution

It systematically evaluates AI and metaheuristic methods for nanovector synthesis, compares their performance, and discusses sample size estimation for AI models.

Findings

Neural networks outperform linear regression and response surface methodology in modeling NV properties.

Cuckoo search and symbiotic organism search are the most effective metaheuristic algorithms.

Limited studies compare AI or metaheuristic algorithms directly, and sample size calculation methods are lacking.

Abstract

Nanovectors (NVs), based on nanostructured matter such as nanoparticles (NPs), have proven to perform as excellent drug delivery systems. However, due to the great variety of potential NVs, including NPs materials and their functionalization, in addition to the plethora of molecules that could transport, this fields presents a great challenge in terms of resources to find NVs with the most optimal physicochemical properties such as particle size and drug loading, where most of efforts rely on trial and error experimentation. In this regard, Artificial intelligence (AI) and metaheuristic algorithms offer efficient of the state-of-the-art modelling and optimization, respectively. This review focuses, through a systematic search, on the use of artificial intelligence and metaheuristic algorithms for nanoparticle synthesis in drug delivery systems. The main findings are: neural networks are better at modelling NVs properties than linear regression algorithms and response surface methodology, there is a very limited number of studies comparing AI or metaheuristic algorithm, and there is no information regarding the appropriateness of calculations of the sample size. Based on these findings, multilayer perceptron artificial neural network and adaptive neuro fuzzy inference system were tested for their modelling performance with a NV dataset; finding the latter the better algorithm. For metaheuristic algorithms, benchmark functions were optimized with cuckoo search, firefly algorithm, genetic algorithm and symbiotic organism search; finding cuckoo search and symbiotic organism search with the best performance. Finally, methods to estimate appropriate sample size for AI algorithms are discussed.