An RNA secondary structure prediction method based on minimum and suboptimal free energy structures

- We have presented a novel method for predicting the conserved secondary structure. Based on features extracted from MFE and SFE structures, a SVM classifier predicted the conserved base pairs.
- We have presented one novel feature of the SVM classifier.
- The sensitivity performance of the method was better than other outstanding comparative methods recommended by CompaRNA.
- The results showed that we found a few patterns of the base pairs behind the data of reference structures.

The function of an RNA-molecule is mainly determined by its tertiary structures. And its secondary structure is an important determinant of its tertiary structure. The comparative methods usually give better results than the single-sequence methods. Based on minimum and suboptimal free energy structures, the paper presents a novel method for predicting conserved secondary structure of a group of related RNAs. In the method, the information from the known RNA structures is used as training data in a SVM (Support Vector Machine) classifier. Our method has been tested on the benchmark dataset given by Puton et al. The results show that the average sensitivity of our method is higher than that of other comparative methods such as CentroidAlifold, MXScrana, RNAalifold, and TurboFold.