如何评估 RNA 二级结构预测准确性。
How to benchmark RNA secondary structure prediction accuracy.
机构信息
Center for RNA Biology, Department of Biochemistry & Biophysics, and Department of Biostatistics & Computational Biology, University of Rochester Medical Center, 601 Elmwood Avenue, Box 712, Rochester, NY 14642, United States.
出版信息
Methods. 2019 Jun 1;162-163:60-67. doi: 10.1016/j.ymeth.2019.04.003. Epub 2019 Apr 2.
Abstract
RNA secondary structure prediction is widely used. As new methods are developed, these are often benchmarked for accuracy against existing methods. This review discusses good practices for performing these benchmarks, including the choice of benchmarking structures, metrics to quantify accuracy, the importance of allowing flexibility for pairs in the accepted structure, and the importance of statistical testing for significance.
摘要
RNA 二级结构预测应用广泛。随着新方法的不断发展，人们经常将这些方法与现有方法进行准确性基准测试。本文讨论了进行这些基准测试的良好实践，包括基准结构的选择、用于量化准确性的指标、在接受结构中为碱基对留出灵活性的重要性以及统计测试对显著性的重要性。
相似文献
1
How to benchmark RNA secondary structure prediction accuracy.如何评估 RNA 二级结构预测准确性。
Methods. 2019 Jun 1;162-163:60-67. doi: 10.1016/j.ymeth.2019.04.003. Epub 2019 Apr 2.
2
Energy-based RNA consensus secondary structure prediction in multiple sequence alignments.基于能量的多序列比对中RNA共有二级结构预测
Methods Mol Biol. 2014;1097:125-41. doi: 10.1007/978-1-62703-709-9_7.
3
Computational analysis of RNA structures with chemical probing data.利用化学探针数据对RNA结构进行计算分析。
Methods. 2015 Jun;79-80:60-6. doi: 10.1016/j.ymeth.2015.02.003. Epub 2015 Feb 14.
4
iFoldRNA v2: folding RNA with constraints.iFoldRNA v2：带约束条件的RNA折叠
Bioinformatics. 2015 Sep 1;31(17):2891-3. doi: 10.1093/bioinformatics/btv221. Epub 2015 Apr 24.
5
SARNA-Predict: accuracy improvement of RNA secondary structure prediction using permutation-based simulated annealing.SARNA-Predict：基于排列模拟退火的 RNA 二级结构预测准确性改进。
IEEE/ACM Trans Comput Biol Bioinform. 2010 Oct-Dec;7(4):727-40. doi: 10.1109/TCBB.2008.97.
6
SCFGs in RNA secondary structure prediction RNA secondary structure prediction: a hands-on approach.RNA二级结构预测中的SCFGs：RNA二级结构预测：一种实践方法。
Methods Mol Biol. 2014;1097:143-62. doi: 10.1007/978-1-62703-709-9_8.
7
RNA Secondary Structure Prediction with Pseudoknots Using Chemical Reaction Optimization Algorithm.基于化学反应优化算法的含假结RNA二级结构预测
IEEE/ACM Trans Comput Biol Bioinform. 2021 May-Jun;18(3):1195-1207. doi: 10.1109/TCBB.2019.2936570. Epub 2021 Jun 3.
8
The BRaliBase dent-a tale of benchmark design and interpretation.BRaliBase牙的故事——基准设计与解读
Brief Bioinform. 2017 Mar 1;18(2):306-311. doi: 10.1093/bib/bbw022.
9
Sequence Design Using RNAstructure.使用 RNAstructure 进行序列设计。
Methods Mol Biol. 2025;2847:17-31. doi: 10.1007/978-1-0716-4079-1_2.
10
Predicting pseudoknotted structures across two RNA sequences.预测两条 RNA 序列中的假结结构。
Bioinformatics. 2012 Dec 1;28(23):3058-65. doi: 10.1093/bioinformatics/bts575. Epub 2012 Oct 8.
引用本文的文献
1
ECSFinder: optimized prediction of evolutionarily conserved RNA secondary structures from genome sequences.ECSFinder：从基因组序列中对进化保守RNA二级结构进行优化预测。
Nucleic Acids Res. 2025 Aug 11;53(15). doi: 10.1093/nar/gkaf780.
2
AlignmentFold and AlignmentPartition: Improving the align-then-fold approach for RNA secondary structure prediction.比对折叠与比对划分：改进用于RNA二级结构预测的先比对后折叠方法
bioRxiv. 2025 Jul 28:2025.07.23.666478. doi: 10.1101/2025.07.23.666478.
3
RiNALMo: general-purpose RNA language models can generalize well on structure prediction tasks.RiNALMo：通用RNA语言模型在结构预测任务上能很好地泛化。
Nat Commun. 2025 Jul 1;16(1):5671. doi: 10.1038/s41467-025-60872-5.
4
Comprehensive benchmarking of large language models for RNA secondary structure prediction.用于RNA二级结构预测的大语言模型的全面基准测试。
Brief Bioinform. 2025 Mar 4;26(2). doi: 10.1093/bib/bbaf137.
5
IPANEMAP Suite: a pipeline for probing-informed RNA structure modeling.IPANEMAP套件：一种用于探测信息RNA结构建模的流程。
NAR Genom Bioinform. 2025 Mar 25;7(1):lqaf028. doi: 10.1093/nargab/lqaf028. eCollection 2025 Mar.
6
Analyzing aptamer structure and interactions: in silico modelling and instrumental methods.分析适配体结构与相互作用：计算机模拟建模及仪器方法
Biophys Rev. 2024 Nov 20;16(6):685-700. doi: 10.1007/s12551-024-01252-z. eCollection 2024 Dec.
7
Robust RNA secondary structure prediction with a mixture of deep learning and physics-based experts.结合深度学习和基于物理的专家方法进行稳健的RNA二级结构预测。
Biol Methods Protoc. 2025 Jan 6;10(1):bpae097. doi: 10.1093/biomethods/bpae097. eCollection 2025.
8
DecoyFinder: Identification of Contaminants in Sets of Homologous RNA Sequences.诱饵序列查找器：同源RNA序列集中污染物的鉴定
bioRxiv. 2024 Oct 15:2024.10.12.618037. doi: 10.1101/2024.10.12.618037.
9
Intronic RNA secondary structural information captured for the human pre-mRNA.为人类前体信使核糖核酸捕获的内含子RNA二级结构信息。
NAR Genom Bioinform. 2024 Oct 24;6(4):lqae143. doi: 10.1093/nargab/lqae143. eCollection 2024 Sep.
10
Discovery and Quantification of Long-Range RNA Base Pairs in Coronavirus Genomes with SEARCH-MaP and SEISMIC-RNA.利用SEARCH-MaP和SEISMIC-RNA发现并定量冠状病毒基因组中的长程RNA碱基对
Res Sq. 2024 Aug 7:rs.3.rs-4814547. doi: 10.21203/rs.3.rs-4814547/v1.
本文引用的文献
1
Kinetics coming into focus: single-molecule microscopy of riboswitch dynamics.动力学成为焦点：核酶动力学的单分子荧光显微镜研究。
RNA Biol. 2019 Sep;16(9):1077-1085. doi: 10.1080/15476286.2018.1536594. Epub 2018 Oct 29.
2
Rfam 13.0: shifting to a genome-centric resource for non-coding RNA families.RFAM 13.0：转向以基因组为中心的非编码 RNA 家族资源
Nucleic Acids Res. 2018 Jan 4;46(D1):D335-D342. doi: 10.1093/nar/gkx1038.
3
Base pair probability estimates improve the prediction accuracy of RNA non-canonical base pairs.碱基对概率估计提高了RNA非规范碱基对的预测准确性。
PLoS Comput Biol. 2017 Nov 6;13(11):e1005827. doi: 10.1371/journal.pcbi.1005827. eCollection 2017 Nov.
4
TurboFold II: RNA structural alignment and secondary structure prediction informed by multiple homologs.TurboFold II：基于多个同源物的RNA结构比对与二级结构预测
Nucleic Acids Res. 2017 Nov 16;45(20):11570-11581. doi: 10.1093/nar/gkx815.
5
Modeling RNA Secondary Structure with Sequence Comparison and Experimental Mapping Data.利用序列比较和实验图谱数据构建RNA二级结构模型。
Biophys J. 2017 Jul 25;113(2):330-338. doi: 10.1016/j.bpj.2017.06.039. Epub 2017 Jul 20.
6
Ensemble cryo-EM elucidates the mechanism of translation fidelity.冷冻电镜技术揭示翻译保真机制。
Nature. 2017 Jun 1;546(7656):113-117. doi: 10.1038/nature22397. Epub 2017 May 24.
7
The ribosome's energy landscape: Recent insights from computation.核糖体的能量景观：计算领域的最新见解
Biophys Rev. 2015 Sep;7(3):301-310. doi: 10.1007/s12551-014-0155-1. Epub 2015 Jan 18.
8
A sensitivity analysis of RNA folding nearest neighbor parameters identifies a subset of free energy parameters with the greatest impact on RNA secondary structure prediction.RNA折叠最近邻参数的敏感性分析确定了对RNA二级结构预测影响最大的自由能参数子集。
Nucleic Acids Res. 2017 Jun 2;45(10):6168-6176. doi: 10.1093/nar/gkx170.
9
Recurring RNA structural motifs underlie the mechanics of L1 stalk movement.重复的 RNA 结构基元是 L1 茎部运动的力学基础。
Nat Commun. 2017 Feb 8;8:14285. doi: 10.1038/ncomms14285.
10
Exact calculation of loop formation probability identifies folding motifs in RNA secondary structures.环状结构形成概率的精确计算可识别RNA二级结构中的折叠基序。
RNA. 2016 Dec;22(12):1808-1818. doi: 10.1261/rna.053694.115. Epub 2016 Oct 19.
Zotero 插件