Saved in:
| Main Authors: | , |
|---|---|
| Format: | Recurso digital |
| Language: | English |
| Published: |
Zenodo
2019
|
| Online Access: | https://doi.org/10.5281/zenodo.17164057 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>RNA molecules play an important role in cell function especially including pseudoknots. Their functions are directly related to their secondary and tertiary structures. In past decades, there developed several methods to predict RNA secondary structure with pseudoknots, and the most popular one is using minimum free energy. The RNA pseudoknotted structure prediction is a nondeterministic polynomial-time hard (NP-hard) problem. We have proposed an approach based on a metaheuristic algorithm named Chemical Reaction Optimization (CRO) to solve the RNA pseudoknotted structure prediction problem. To solve the problem, CRO first finds all possible candidate stems. From these candidate stems, CRO generates an initial population. We have redesigned the reaction operators of CRO algorithm and used them on the generated population to find the structure with the minimum free energy. Four energy models have been applied to calculate the minimum free energy. Besides the basic reaction operators of CRO, an additional operator called Repair function has been developed here. Repair function has a great influence on our algorithm in increasing accuracy. It helps to increase the true positive base pairs while decreasing the false positive and false negative base pairs. To evaluate the performance, we have used five datasets containing RNA pseudoknotted sequences taken from RNA STRAND and Pseudobase++ database. Our algorithm has been compared with some existing algorithms such as Knotty, IPknot, Simulated Annealing (SA), and TT2NE. Experimental results present that our CRO based model is a better prediction method in terms of accuracy and speed compared to several competitive prediction methods.</p>