• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

RNAelem：一种用于发现RNA结合蛋白所结合RNA中的序列-结构基序的算法。

RNAelem: an algorithm for discovering sequence-structure motifs in RNA bound by RNA-binding proteins.

作者信息

Miyake Hiroshi, Kawaguchi Risa Karakida, Kiryu Hisanori

机构信息

Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, University of Tokyo, Chiba 277-8561, Japan.

Department of Life Science Frontiers, Center for iPS Cell Research and Application (CiRA), Kyoto University, Sakyo-ku 606-8507, Japan.

出版信息

Bioinform Adv. 2024 Sep 28;4(1):vbae144. doi: 10.1093/bioadv/vbae144. eCollection 2024.

DOI:10.1093/bioadv/vbae144
PMID:39399375
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11471262/
Abstract

MOTIVATION

RNA-binding proteins (RBPs) play a crucial role in the post-transcriptional regulation of RNA. Given their importance, analyzing the specific RNA patterns recognized by RBPs has become a significant research focus in bioinformatics. Deep Neural Networks have enhanced the accuracy of prediction for RBP-binding sites, yet understanding the structural basis of RBP-binding specificity from these models is challenging due to their limited interpretability. To address this, we developed RNAelem, which combines profile context-free grammar and the Turner energy model for RNA secondary structure to predict sequence-structure motifs in RBP-binding regions.

RESULTS

RNAelem exhibited superior detection accuracy compared to existing tools for RNA sequences with structural motifs. Upon applying RNAelem to the eCLIP database, we were not only able to reproduce many known primary sequence motifs in the absence of secondary structures, but also discovered many secondary structural motifs that contained sequence-nonspecific insertion regions. Furthermore, the high interpretability of RNAelem yielded insightful findings such as long-range base-pairing interactions in the binding region of the U2AF protein.

AVAILABILITY AND IMPLEMENTATION

The code is available at https://github.com/iyak/RNAelem.

摘要

动机

RNA结合蛋白（RBPs）在RNA的转录后调控中起着至关重要的作用。鉴于其重要性，分析RBPs识别的特定RNA模式已成为生物信息学中的一个重要研究重点。深度神经网络提高了RBP结合位点预测的准确性，但由于其可解释性有限，从这些模型中理解RBP结合特异性的结构基础具有挑战性。为了解决这个问题，我们开发了RNAelem，它结合了轮廓上下文无关语法和RNA二级结构的特纳能量模型，以预测RBP结合区域中的序列-结构基序。

结果

与现有的用于具有结构基序的RNA序列的工具相比，RNAelem表现出更高的检测准确性。将RNAelem应用于eCLIP数据库时，我们不仅能够在不存在二级结构的情况下重现许多已知的一级序列基序，还发现了许多包含序列非特异性插入区域的二级结构基序。此外，RNAelem的高可解释性产生了有深刻见解的发现，例如U2AF蛋白结合区域中的长程碱基配对相互作用。

可用性和实现方式

代码可在https://github.com/iyak/RNAelem获取。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/9b35dddbcf00/vbae144f8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/ae483206dceb/vbae144f1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/193abab61398/vbae144f2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/703d478cbe9a/vbae144f3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/bc8276e598af/vbae144f4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/292c83797e55/vbae144f5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/5abe751ba504/vbae144f6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/4d22a91c2b33/vbae144f7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/9b35dddbcf00/vbae144f8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/ae483206dceb/vbae144f1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/193abab61398/vbae144f2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/703d478cbe9a/vbae144f3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/bc8276e598af/vbae144f4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/292c83797e55/vbae144f5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/5abe751ba504/vbae144f6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/4d22a91c2b33/vbae144f7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9bfd/11471262/9b35dddbcf00/vbae144f8.jpg

相似文献

1
RNAelem: an algorithm for discovering sequence-structure motifs in RNA bound by RNA-binding proteins.RNAelem：一种用于发现RNA结合蛋白所结合RNA中的序列-结构基序的算法。
Bioinform Adv. 2024 Sep 28;4(1):vbae144. doi: 10.1093/bioadv/vbae144. eCollection 2024.
2
Prediction of RNA-protein sequence and structure binding preferences using deep convolutional and recurrent neural networks.使用深度卷积和递归神经网络预测 RNA-蛋白质序列和结构的结合偏好。
BMC Genomics. 2018 Jul 3;19(1):511. doi: 10.1186/s12864-018-4889-1.
3
Deep neural networks for inferring binding sites of RNA-binding proteins by using distributed representations of RNA primary sequence and secondary structure.利用 RNA 一级序列和二级结构的分布式表示来推断 RNA 结合蛋白结合位点的深度神经网络。
BMC Genomics. 2020 Dec 17;21(Suppl 13):866. doi: 10.1186/s12864-020-07239-w.
4
Predicting RNA-protein binding sites and motifs through combining local and global deep convolutional neural networks.通过结合局部和全局深度卷积神经网络预测 RNA 与蛋白质的结合位点和基序。
Bioinformatics. 2018 Oct 15;34(20):3427-3436. doi: 10.1093/bioinformatics/bty364.
5
A deep learning framework for modeling structural features of RNA-binding protein targets.一种用于对RNA结合蛋白靶点的结构特征进行建模的深度学习框架。
Nucleic Acids Res. 2016 Feb 29;44(4):e32. doi: 10.1093/nar/gkv1025. Epub 2015 Oct 13.
6
Prediction of binding property of RNA-binding proteins using multi-sized filters and multi-modal deep convolutional neural network.基于多尺寸滤波器和多模态深度卷积神经网络的 RNA 结合蛋白结合特性预测。
PLoS One. 2019 Apr 26;14(4):e0216257. doi: 10.1371/journal.pone.0216257. eCollection 2019.
7
RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach.基于新型混合深度学习跨域知识整合方法的RNA-蛋白质结合基序挖掘
BMC Bioinformatics. 2017 Feb 28;18(1):136. doi: 10.1186/s12859-017-1561-8.
8
circRNA-binding protein site prediction based on multi-view deep learning, subspace learning and multi-view classifier.基于多视图深度学习、子空间学习和多视图分类器的 circRNA 结合蛋白位点预测。
Brief Bioinform. 2022 Jan 17;23(1). doi: 10.1093/bib/bbab394.
9
Prediction of the RBP binding sites on lncRNAs using the high-order nucleotide encoding convolutional neural network.使用高阶核苷酸编码卷积神经网络预测长链非编码RNA上的RBP结合位点
Anal Biochem. 2019 Oct 15;583:113364. doi: 10.1016/j.ab.2019.113364. Epub 2019 Jul 16.
10
Deep neural networks for interpreting RNA-binding protein target preferences.用于解释 RNA 结合蛋白靶标偏好的深度神经网络。
Genome Res. 2020 Feb;30(2):214-226. doi: 10.1101/gr.247494.118. Epub 2020 Jan 28.

本文引用的文献

1
Structural basis for human mitochondrial tRNA maturation.人类线粒体 tRNA 成熟的结构基础。
Nat Commun. 2024 Jun 1;15(1):4683. doi: 10.1038/s41467-024-49132-0.
2
Prediction of RNA-protein interactions using a nucleotide language model.使用核苷酸语言模型预测RNA-蛋白质相互作用。
Bioinform Adv. 2022 Apr 7;2(1):vbac023. doi: 10.1093/bioadv/vbac023. eCollection 2022.
3
Aberrant interaction of FUS with the U1 snRNA provides a molecular mechanism of FUS induced amyotrophic lateral sclerosis.FUS 与 U1 snRNA 的异常相互作用为 FUS 诱导的肌萎缩侧索硬化症提供了一种分子机制。
Nat Commun. 2020 Dec 11;11(1):6341. doi: 10.1038/s41467-020-20191-3.
4
A large-scale binding and functional map of human RNA-binding proteins.人类 RNA 结合蛋白的大规模结合和功能图谱。
Nature. 2020 Jul;583(7818):711-719. doi: 10.1038/s41586-020-2077-3. Epub 2020 Jul 29.
5
Modern deep learning in bioinformatics.生物信息学中的现代深度学习
J Mol Cell Biol. 2020 Oct 30;12(11):823-827. doi: 10.1093/jmcb/mjaa030.
6
How RNA-Binding Proteins Interact with RNA: Molecules and Mechanisms.RNA 结合蛋白与 RNA 的相互作用：分子与机制。
Mol Cell. 2020 Apr 2;78(1):9-29. doi: 10.1016/j.molcel.2020.03.011.
7
Staufen1 reads out structure and sequence features in ARF1 dsRNA for target recognition.Staufen1 读取 ARF1 dsRNA 的结构和序列特征以进行靶标识别。
Nucleic Acids Res. 2020 Feb 28;48(4):2091-2106. doi: 10.1093/nar/gkz1163.
8
The mechanism of RNA duplex recognition and unwinding by DEAD-box helicase DDX3X.DEAD-box 解旋酶 DDX3X 识别和解开 RNA 双链的机制。
Nat Commun. 2019 Jul 12;10(1):3085. doi: 10.1038/s41467-019-11083-2.
9
The Solution Structure of FUS Bound to RNA Reveals a Bipartite Mode of RNA Recognition with Both Sequence and Shape Specificity.FUS 与 RNA 结合的溶液结构揭示了一种具有序列和形状特异性的 RNA 识别的二分模式。
Mol Cell. 2019 Feb 7;73(3):490-504.e6. doi: 10.1016/j.molcel.2018.11.012. Epub 2018 Dec 20.
10
HuR biological function involves RRM3-mediated dimerization and RNA binding by all three RRMs.HuR 的生物学功能涉及 RRM3 介导的二聚化和所有三个 RRMs 的 RNA 结合。
Nucleic Acids Res. 2019 Jan 25;47(2):1011-1029. doi: 10.1093/nar/gky1138.