Secondary structural characterization of the nucleic acids from circular dichroism spectra using extreme gradient boosting decision-tree algorithm

Abstract

Nucleic acids exhibit a repertoire of conformational preference depending on the sequence and environment. Circular dichroism (CD) is an important and valuable tool for monitoring such secondary structural conformations of nucleic acids. Nonetheless, the CD spectral diversity associated with these structures poses a challenge in obtaining the quantitative information about the secondary structural content of a given CD spectrum. To this end, the competence of extreme gradient boosting decision-tree algorithm has been exploited here to predict the diverse secondary structures of nucleic acids. A curated library of 610 CD spectra corresponding to 16 different secondary structures of nucleic acids has been developed and used as a training dataset. For a test dataset of 242 CD spectra, the algorithm exhibited the prediction accuracy of 99%. For the sake of accessibility, the entire process is automated and implemented as a webserver, called CD-NuSS (CD to nucleic acids secondary structure) and is freely accessible at https://www.iith.ac.in/cdnuss/.The XGBoost algorithm presented here may also be extended to identify the hybrid nucleic acid topologies in future.

Expedited circular dichroism prediction and engineering in two-dimensional diffractive chiral metamaterials leveraging a powerful model-agnostic data enhancement algorithm

“…In general, the training dataset created by either numerical simulations or experimental measurements is usually required in order to facilitate a predesigned artificial neural network (ANN) or other ML model to learn the underlying rules, followed by the trained model solving a target problem. Despite striking progress achieved in this area, the training process in most photonics-involved works relies heavily on optical response data from target devices [47][48][49][50], whose size is relatively large.…”