This paper describes the use of chemometrics and hybrid neural networks on microfluidic platforms to optimize the fluorescence output in two chemical systems. In the first, the binding of 5-carboxyfluorescein-D-Ala-D-Ala-D-Ala (5-FAM-(D-Ala)3 (1 ) to the antibiotic teicoplanin from Actinoplanes teichomyceticus electrostatically attached to a microfluidic channel originally modified with 3-aminopropyltriethoxysilane was examined. In the second, the enzyme diaphorase was covalently attached to magnetic micro-beads and used to convert non-fluorescent resazurin, in the presence of nicotinamide adenine dinucleotide phosphate, to fluorescent resorufin. By changing various parameters for each experiment, the neural network methodology can be applied to optimize fluorescence. This approach proved successful in predicting optimal values in a reduced number of experiments.

Implementation of hybrid neural network methodology in optimizing fluorescence in receptor-ligand binding interactions and enzyme-catalyzed reactions on microchips

243rd National Meeting (2012)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.