Neural Network Modeling in Dithiothreitol Reduction and Ion Treatment of Recombinant Human Insulin Obtained from the Circular Dichroism (CD) Spectral Information

Abstract

In this study, induced changes in the secondary structure of the human insulin were carried out by addition of various reagents causing modification in the disulfide bond such as dithiothreitol (DTT) three dimensional structure of insulin. CD spectra were taken accordingly and the spectra recorded. There are methods to predict and estimate spectral changes of a peptide molecule, however there is no method to process CD spectral data and correlate them with that of inducing factor. Artificial intelligence backpropagation algorithm, as a strong model building tool was used here for prediction and data mining. Therefore, artificial neural network (ANN) methodology was used to build a model to study the effect of selected biochemical factors in the downstream process of a recombinant peptide.