Application of supervised Kohonen map and counter propagation neural network for classification of nucleic acid structures based on their circular dichroism spectra

•We applied the supervised Kohonen network for classification of nucleic acid structures.•The classification was fulfilled based on CD spectra of different DNA structures with high similarity.•It is shown that the spectral similarities between the weights of each group and their CD spectra lead to accurate prediction of unknown samples.•The weight analysis was used for accurate prediction of unknown samples.•Prediction of mixture samples was done well by applying the introduced weight analysis method.

One of the most popular instrumental methods to detect the DNA structure is circular dichroism. Specific experimental conditions are required to form different structures of DNA. However, there is the possibility of different structures establishing in the similar circumstance. So, methods development to improve the classification and prediction of structures using their spectra information are needed. To this end, we applied unsupervised (PCA) and supervised (PLS-DA, SKN, and CPNN) approaches to classify CD spectra dataset of different DNA sequences (random coil (ss-DNA), duplex, hairpin, reversed and normal triplex, parallel and antiparallel G-quadruplex, and i-motif). The main part of this work concentrates on the application of artificial neural networks and weight analysis to obtain more classification and prediction accuracy. For this purpose, the trained network was run 10 times, and the average weights were taken. Also, weight analysis was done for the prediction of mixture samples include different structures. The results prove that new method of weights analysis based on SKN and CPNN is useful for classification of complicated data such as different types of DNA structures.

Graphical abstractFigure optionsDownload full-size imageDownload as PowerPoint slide