DMfold: A Novel Method to Predict RNA Secondary Structure With Pseudoknots Based on Deep Learning and Improved Base Pair Maximization Principle

• Published in: Frontiers in genetics 2019-03, Vol.10, p.143
• Main Authors: Wang, Linyu, Liu, Yuanning, Zhong, Xiaodan, Liu, Haiming, Lu, Chao, Li, Cong, Zhang, Hao
• Format: Article
• Language: English
• Subjects: deep learning; Genetics; multi-sequence method; pseudoknot; RNA; secondary structure prediction; single-sequence method
• ISSN: 1664-8021; 1664-8021
• DOI: 10.3389/fgene.2019.00143

While predicting the secondary structure of RNA is vital for researching its function, determining RNA secondary structure is challenging, especially for that with pseudoknots. Typically, several excellent computational methods can be utilized to predict the secondary structure (with or without pseudoknots), but they have their own merits and demerits. These methods can be classified into two categories: the multi-sequence method and the single-sequence method. The main advantage of the multi-sequence method lies in its use of the auxiliary sequences to assist in predicting the secondary structure, but it can only successfully predict in the presence of multiple highly homologous sequences. The single-sequence method is associated with the major merit of easy operation (only need the target sequence to predict secondary structure), but its folding parameters are the common features of diversity RNA, which cannot describe the unique characteristics of RNA, thus potentially resulting in the low prediction accuracy in some RNA. In this paper, "DMfold," a method based on the Deep Learning and Improved Base Pair Maximization Principle, is proposed to predict the secondary structure with pseudoknots, which fully absorbs the advantages and avoids some disadvantages of those two methods. Notably, DMfold could predict the secondary structure of RNA by learning similar RNA in the known structures, which uses the similar RNA sequences instead of the highly homogeneous sequences in the multi-sequence method, thereby reducing the requirement for auxiliary sequences. In DMfold, it only needs to input the target sequence to predict the secondary structure. Its folding parameters are fully extracted automatically by deep learning, which could avoid the lack of folding parameters in the single-sequence method. Experiments show that our method is not only simple to operate, but also improves the prediction accuracy compared to multiple excellent prediction methods. A repository containing our code can be found at https://github.com/linyuwangPHD/RNA-Secondary-Structure-Database.