中国物理B ›› 2025, Vol. 34 ›› Issue (8): 88710-088710.doi: 10.1088/1674-1056/adea9c

所属专题： SPECIAL TOPIC — A celebration of the 90th Anniversary of the Birth of Bolin Hao

• • 上一篇    下一篇

A comprehensive evaluation of RNA secondary structures prediction methods

Xinlong Chen(陈昕龙)1, En Lou(娄恩)1, Zouchenyu Zhou(周邹辰毓)1, Ya-Lan Tan(谭雅岚)2,‡, and Zhi-Jie Tan(谭志杰)1,†   

  1. 1 Department of Physics and Key Laboratory of Artificial Micro & Nano-structures of Ministry of Education, School of Physics and Technology, Wuhan University, Wuhan 430072, China;
    2 School of Bioengineering and Health & Research Center of Nonlinear Science, Wuhan Textile University, Wuhan 430200, China
  • 收稿日期:2025-06-11 修回日期:2025-06-26 接受日期:2025-07-02 出版日期:2025-07-17 发布日期:2025-07-21
  • 通讯作者: Zhi-Jie Tan, Ya-Lan Tan E-mail:zjtan@whu.edu.cn;yltan@wtu.edu.cn
  • 基金资助:
    We are grateful to Profs Shi-Jie Chen (University of Missouri) and Jian Zhang (Nanjing University) for valuable discussions. This work was supported by grants from the National Science Foundation of China (Grant Nos. 12375038 and 12075171 to ZJT, and 12205223 to YLT).

A comprehensive evaluation of RNA secondary structures prediction methods

Xinlong Chen(陈昕龙)1, En Lou(娄恩)1, Zouchenyu Zhou(周邹辰毓)1, Ya-Lan Tan(谭雅岚)2,‡, and Zhi-Jie Tan(谭志杰)1,†   

  1. 1 Department of Physics and Key Laboratory of Artificial Micro & Nano-structures of Ministry of Education, School of Physics and Technology, Wuhan University, Wuhan 430072, China;
    2 School of Bioengineering and Health & Research Center of Nonlinear Science, Wuhan Textile University, Wuhan 430200, China
  • Received:2025-06-11 Revised:2025-06-26 Accepted:2025-07-02 Online:2025-07-17 Published:2025-07-21
  • Contact: Zhi-Jie Tan, Ya-Lan Tan E-mail:zjtan@whu.edu.cn;yltan@wtu.edu.cn
  • Supported by:
    We are grateful to Profs Shi-Jie Chen (University of Missouri) and Jian Zhang (Nanjing University) for valuable discussions. This work was supported by grants from the National Science Foundation of China (Grant Nos. 12375038 and 12075171 to ZJT, and 12205223 to YLT).

RichHTML

0

PDF (PC)

88

赞

补充材料

1

摘要： RNAs have important biological functions and the functions of RNAs are generally coupled to their structures, especially their secondary structures. In this work, we have made a comprehensive evaluation of the performances of existing top RNA secondary structure prediction methods, including five deep-learning (DL) based methods and five minimum free energy (MFE) based methods. First, we made a brief overview of these RNA secondary structure prediction methods. Afterwards, we built two rigorous test datasets consisting of RNAs with non-redundant sequences and comprehensively examined the performances of the RNA secondary structure prediction methods through classifying the RNAs into different length ranges and different types. Our examination shows that the DL-based methods generally perform better than the MFE-based methods for RNAs with long lengths and complex structures, while the MFE-based methods can achieve good performance for small RNAs and some specialized MFE-based methods can achieve good prediction accuracy for pseudoknots. Finally, we provided some insights and perspectives in modeling RNA secondary structures.

关键词: RNA secondary structure prediction, computational methods, comprehensive evaluation, traditional methods, deep-learning-based methods

Abstract: RNAs have important biological functions and the functions of RNAs are generally coupled to their structures, especially their secondary structures. In this work, we have made a comprehensive evaluation of the performances of existing top RNA secondary structure prediction methods, including five deep-learning (DL) based methods and five minimum free energy (MFE) based methods. First, we made a brief overview of these RNA secondary structure prediction methods. Afterwards, we built two rigorous test datasets consisting of RNAs with non-redundant sequences and comprehensively examined the performances of the RNA secondary structure prediction methods through classifying the RNAs into different length ranges and different types. Our examination shows that the DL-based methods generally perform better than the MFE-based methods for RNAs with long lengths and complex structures, while the MFE-based methods can achieve good performance for small RNAs and some specialized MFE-based methods can achieve good prediction accuracy for pseudoknots. Finally, we provided some insights and perspectives in modeling RNA secondary structures.

Key words: RNA secondary structure prediction, computational methods, comprehensive evaluation, traditional methods, deep-learning-based methods

中图分类号:  (Biological information)

  • 87.10.Vg
87.15.bg (Tertiary structure) 87.14.gn (RNA)