Genetic Algorithm-Based Design for Metal-Enhanced Fluorescent Nanostructures

Abstract

In this paper, we present our optimization tool for fluorophore-conjugated metal nanostructures for the purpose of designing novel contrast agents for multimodal bioimaging. Contrast agents are of great importance to biological imaging. They usually include nanoelements causing a reduction in the need for harmful materials and improvement in the quality of the captured images. Thus, smart design tools that are based on evolutionary algorithms and machine learning definitely provide a technological leap in the fluorescence bioimaging world. This article proposes the usage of properly designed metallic structures that change their fluorescence properties when the dye molecules and the plasmonic nanoparticles interact. The nanostructures design and evaluation processes are based upon genetic algorithms, and they result in an optimal separation distance, orientation angles, and aspect ratio of the metal nanostructure.