利用k近邻分类器网络从序列比对中预测RNA二级结构。
RNA secondary structure prediction from sequence alignments using a network of k-nearest neighbor classifiers.
作者信息
Bindewald Eckart, Shapiro Bruce A
机构信息
Basic Research Program, SAIC-Frederick, Inc, National Cancer Institute-Frederick, MD 21702, USA.
出版信息
RNA. 2006 Mar;12(3):342-52. doi: 10.1261/rna.2164906.
Abstract
We present a machine learning method (a hierarchical network of k-nearest neighbor classifiers) that uses an RNA sequence alignment in order to predict a consensus RNA secondary structure. The input to the network is the mutual information, the fraction of complementary nucleotides, and a novel consensus RNAfold secondary structure prediction of a pair of alignment columns and its nearest neighbors. Given this input, the network computes a prediction as to whether a particular pair of alignment columns corresponds to a base pair. By using a comprehensive test set of 49 RFAM alignments, the program KNetFold achieves an average Matthews correlation coefficient of 0.81. This is a significant improvement compared with the secondary structure prediction methods PFOLD and RNAalifold. By using the example of archaeal RNase P, we show that the program can also predict pseudoknot interactions.
摘要
我们提出了一种机器学习方法（k近邻分类器的层次网络），该方法使用RNA序列比对来预测共有RNA二级结构。网络的输入是互信息、互补核苷酸的比例，以及一对比对列及其最近邻的新型共有RNAfold二级结构预测。基于这些输入，网络计算关于特定比对列对是否对应碱基对的预测。通过使用包含49个RFAM比对的综合测试集，程序KNetFold实现了平均马修斯相关系数为0.81。与二级结构预测方法PFOLD和RNAalifold相比，这是一个显著的改进。通过古细菌RNase P的例子，我们表明该程序还可以预测假结相互作用。
相似文献
1
RNA secondary structure prediction from sequence alignments using a network of k-nearest neighbor classifiers.利用k近邻分类器网络从序列比对中预测RNA二级结构。
RNA. 2006 Mar;12(3):342-52. doi: 10.1261/rna.2164906.
2
[RNA secondary structure prediction based on support vector machine classification].基于支持向量机分类的RNA二级结构预测
Sheng Wu Gong Cheng Xue Bao. 2008 Jul;24(7):1140-8.
3
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.
4
RNAalifold: improved consensus structure prediction for RNA alignments.RNAalifold：改进的RNA比对共有结构预测
BMC Bioinformatics. 2008 Nov 11;9:474. doi: 10.1186/1471-2105-9-474.
5
Evaluation of the suitability of free-energy minimization using nearest-neighbor energy parameters for RNA secondary structure prediction.使用最近邻能量参数的自由能最小化对RNA二级结构预测适用性的评估。
BMC Bioinformatics. 2004 Aug 5;5:105. doi: 10.1186/1471-2105-5-105.
6
StatAlign 2.0: combining statistical alignment with RNA secondary structure prediction.StatAlign 2.0：将统计比对与 RNA 二级结构预测相结合。
Bioinformatics. 2013 Mar 1;29(5):654-5. doi: 10.1093/bioinformatics/btt025. Epub 2013 Jan 17.
7
Predicting RNA structure using mutual information.利用互信息预测RNA结构。
Appl Bioinformatics. 2005;4(1):53-9. doi: 10.2165/00822942-200504010-00006.
8
Pair stochastic tree adjoining grammars for aligning and predicting pseudoknot RNA structures.用于比对和预测假结RNA结构的成对随机树邻接文法
Proc IEEE Comput Syst Bioinform Conf. 2004:290-9.
9
Novel representation of RNA secondary structure used to improve prediction algorithms.用于改进预测算法的RNA二级结构新表示法。
Genet Mol Res. 2011 Sep 9;10(3):1986-98. doi: 10.4238/vol10-3gmr1181.
10
Transfer RNA processing in archaea: unusual pathways and enzymes.古菌中的转运RNA加工：异常途径与酶
FEBS Lett. 2010 Jan 21;584(2):303-9. doi: 10.1016/j.febslet.2009.10.067.
引用本文的文献
1
Transformers in RNA structure prediction: A review.RNA结构预测中的Transformer：综述
Comput Struct Biotechnol J. 2025 Mar 17;27:1187-1203. doi: 10.1016/j.csbj.2025.03.021. eCollection 2025.
2
RNA-targeted small-molecule drug discoveries: a machine-learning perspective.基于机器学习的靶向 RNA 小分子药物研发
RNA Biol. 2023 Jan;20(1):384-397. doi: 10.1080/15476286.2023.2223498.
3
Design and Prediction of Aptamers Assisted by In Silico Methods.计算机辅助方法辅助的适配体设计与预测
Biomedicines. 2023 Jan 26;11(2):356. doi: 10.3390/biomedicines11020356.
4
Review of machine learning methods for RNA secondary structure prediction.机器学习方法在 RNA 二级结构预测中的研究进展综述。
PLoS Comput Biol. 2021 Aug 26;17(8):e1009291. doi: 10.1371/journal.pcbi.1009291. eCollection 2021 Aug.
5
PlncRNA-HDeep: plant long noncoding RNA prediction using hybrid deep learning based on two encoding styles.PlncRNA-HDeep：基于两种编码方式的混合深度学习进行植物长链非编码RNA预测
BMC Bioinformatics. 2021 May 12;22(Suppl 3):242. doi: 10.1186/s12859-020-03870-2.
6
Artificial Intelligence in Aptamer-Target Binding Prediction.适体-靶点结合预测中的人工智能
Int J Mol Sci. 2021 Mar 30;22(7):3605. doi: 10.3390/ijms22073605.
7
Detecting genetic interactions using parallel evolution in experimental populations.利用实验群体中的并行进化检测遗传相互作用。
Philos Trans R Soc Lond B Biol Sci. 2019 Jul 22;374(1777):20180237. doi: 10.1098/rstb.2018.0237. Epub 2019 Jun 3.
8
Genetic variants in mRNA untranslated regions.mRNA 非翻译区的遗传变异。
Wiley Interdiscip Rev RNA. 2018 Jul;9(4):e1474. doi: 10.1002/wrna.1474. Epub 2018 Mar 26.
9
Physics-based RNA structure prediction.基于物理学的RNA结构预测。
Biophys Rep. 2015;1:2-13. doi: 10.1007/s41048-015-0001-4. Epub 2015 Jul 9.
10
DECIPHER: harnessing local sequence context to improve protein multiple sequence alignment.DECIPHER：利用局部序列上下文来改进蛋白质多序列比对。
BMC Bioinformatics. 2015 Oct 6;16:322. doi: 10.1186/s12859-015-0749-z.
本文引用的文献
1
Rfam: annotating non-coding RNAs in complete genomes.Rfam：对完整基因组中的非编码RNA进行注释。
Nucleic Acids Res. 2005 Jan 1;33(Database issue):D121-4. doi: 10.1093/nar/gki081.
2
A comprehensive comparison of comparative RNA structure prediction approaches.比较RNA结构预测方法的全面比较。
BMC Bioinformatics. 2004 Sep 30;5:140. doi: 10.1186/1471-2105-5-140.
3
BayesFold: rational 2 degrees folds that combine thermodynamic, covariation, and chemical data for aligned RNA sequences.贝叶斯折叠：结合热力学、共变和化学数据用于比对RNA序列的合理二级结构折叠。
RNA. 2004 Sep;10(9):1323-36. doi: 10.1261/rna.5168504.
4
Design, implementation and evaluation of a practical pseudoknot folding algorithm based on thermodynamics.基于热力学的实用假结折叠算法的设计、实现与评估。
BMC Bioinformatics. 2004 Aug 4;5:104. doi: 10.1186/1471-2105-5-104.
5
ILM: a web server for predicting RNA secondary structures with pseudoknots.ILM：一个用于预测带假结的RNA二级结构的网络服务器。
Nucleic Acids Res. 2004 Jul 1;32(Web Server issue):W146-9. doi: 10.1093/nar/gkh444.
6
Incorporating chemical modification constraints into a dynamic programming algorithm for prediction of RNA secondary structure.将化学修饰约束纳入用于预测RNA二级结构的动态规划算法中。
Proc Natl Acad Sci U S A. 2004 May 11;101(19):7287-92. doi: 10.1073/pnas.0401799101. Epub 2004 May 3.
7
An iterated loop matching approach to the prediction of RNA secondary structures with pseudoknots.一种用于预测含假结的RNA二级结构的迭代循环匹配方法。
Bioinformatics. 2004 Jan 1;20(1):58-66. doi: 10.1093/bioinformatics/btg373.
8
Pfold: RNA secondary structure prediction using stochastic context-free grammars.Pfold：使用随机上下文无关文法进行RNA二级结构预测。
Nucleic Acids Res. 2003 Jul 1;31(13):3423-8. doi: 10.1093/nar/gkg614.
9
Mfold web server for nucleic acid folding and hybridization prediction.用于核酸折叠和杂交预测的Mfold网络服务器。
Nucleic Acids Res. 2003 Jul 1;31(13):3406-15. doi: 10.1093/nar/gkg595.
10
Rfam: an RNA family database.Rfam：一个RNA家族数据库。
Nucleic Acids Res. 2003 Jan 1;31(1):439-41. doi: 10.1093/nar/gkg006.
Zotero 插件