You can view the full text of this article for free using the link below.

Title: Secondary structure prediction of RNA using convolutional neural networks

Authors: Bisera Chauleva; Atanas Hristov; Ustijana Rechkoska Shikoska; Ljubinka Gjergjeska Sandjakoska

Addresses: Department of Computer Science and Engineering, University for Information Science and Technology 'St. Paul the Apostole' Ohrid, North Macedonia ' Department of Computer Systems, Complex and Networks, University for Information Science and Technology 'St. Paul the Apostole' Ohrid, North Macedonia ' Department of Electrical Engineering and Computer Science, University for Information Science and Technology 'St. Paul the Apostole' Ohrid, North Macedonia ' Department of Machine Learning, University for Information Science and Technology 'St. Paul the Apostole' Ohrid, North Macedonia

Abstract: One of the most popular bioinformatics and genetics topics is the secondary structure prediction of RNA since it is the first step in developing new therapeutic and pharmacological methods. The crucial point in these branches is the development time and accuracy. The work presented in this paper will look upon the state-of-the-art techniques that are currently used for prediction. The deep learning method is evaluated to speed up and to increase accuracy level. Furthermore, modern convolutional neural networks known as residual network, as a secondary structure prediction of RNA, are considered as a more accurate and efficient approach. Finally, a comparison of evaluating results with existing methods is performed, which will prove the successfulness of the proposed algorithm, taken into consideration the benchmark evaluation.

Keywords: ribonucleic acid; RNA; secondary structure prediction; bioinformatics; artificial intelligence; deep learning; convolutional neural networks; PyTorch; classification; residual networks; ResNet; artificial neural networks.

DOI: 10.1504/IJSPR.2021.10041211

International Journal of Student Project Reporting, 2022 Vol.1 No.1, pp.43 - 67

Received: 13 Dec 2020
Accepted: 24 Apr 2021

Published online: 23 Mar 2022 *

Full-text access for editors Access for subscribers Free access Comment on this article