Application of artificial neural networks in the prediction of product distribution in electrophoretically mediated microanalysis

Abstract

The successful application of artificial neural networks toward the prediction of product distribution in electrophoretically mediated microanalysis is presented. To illustrate this concept, we examined the factors and levels required for optimization of reaction conditions for the conversion of nicotinamide adenine dinucleotide to nicotinamide adenine dinucleotide, reduced form by glucose-6-phosphate dehydrogenase in the conversion of glucose-6-phosphate to 6-phosphogluconate. A full factorial experimental design examining the factors voltage, enzyme concentration, and mixing time of reaction was utilized as input-output data sources for suitable artificial neural networks training for prediction purposes. This approach proved successful in predicting optimal values in a reduced number of experiments. Model validation addressing the extent of reaction and product ratios were subsequently determined experimentally in replicate analyses, with results shown to be in good agreement (<10% discrepancy difference) with predicted data.

Recent developments and applications of EMMA in enzymatic and derivatization reactions

“…Based on a small molecule reaction, Strein's group has shown that careful control of reagent plug length as well as concentration and pH of the BGE can result in a marked improvement in the sensitivity due to the minimization of electrodispersion 30. They also demonstrated, using both experiment and simulation, how sample zone conductivity can affect plug‐plug mixing in small molecule applications of EMMA 31. Two small molecule systems were used: (i) creatinine determination via the Jaffe reaction 32 and (ii) the redox reaction between gallate and 2,6‐dichloroindophenol.…”

Microscale Measurements of Michaelis–Menten Constants of Neuraminidase with Nanogel Capillary Electrophoresis for the Determination of the Sialic Acid Linkage

“…While not as prevalent, the use of EMMA to determine K M is feasible if the enzyme remains in the native state, the enzyme does not adsorb to the capillary surface, and the electrophoretic differences of analyte, enzyme, and product facilitate separation. Significant optimization is required to ensure that the incubation conditions are compatible with the electrophoresis, and exquisite strategies to address this optimization have been described. − These barriers are overcome with the use of phospholipid nanogels, which self-assemble to form a thermally responsive material that is suitable as a replaceable gel to sieve DNA in capillary electrophoresis, , as a viscosity switch to close and open channels in microfluidics, , and as a viscous additive to improve capillary electrophoresis separations of oligosaccharides. − Nanogels are biocompatible materials that immobilize and pattern enzymes in microscale channels.…”

Application of a computational neural network to optimize the fluorescence signal from a receptor–ligand interaction on a microfluidic chip

“…While much of the current research on microfluidic devices has focused on the technology and applications of devices, there has been little focus on statistical methods and computational techniques examining the role experimental parameters have on experimental outcomes in microfluidic devices as well as their role in improving the performance of the devices . Previous work has demonstrated the use of statistical methods and computational techniques in different systems to study the effects that experimental variables have on an output response for optimization .…”