MRM-BERT: a novel deep neural network predictor of multiple RNA modifications by fusing BERT representation and sequence features.

IF 3.6 3区 生物学 Q2 BIOCHEMISTRY & MOLECULAR BIOLOGY
RNA Biology Pub Date : 2024-01-01 Epub Date: 2024-02-15 DOI:10.1080/15476286.2024.2315384
Linshu Wang, Yuan Zhou
{"title":"MRM-BERT: a novel deep neural network predictor of multiple RNA modifications by fusing BERT representation and sequence features.","authors":"Linshu Wang, Yuan Zhou","doi":"10.1080/15476286.2024.2315384","DOIUrl":null,"url":null,"abstract":"<p><p>RNA modifications play crucial roles in various biological processes and diseases. Accurate prediction of RNA modification sites is essential for understanding their functions. In this study, we propose a hybrid approach that fuses a pre-trained sequence representation with various sequence features to predict multiple types of RNA modifications in one combined prediction framework. We developed MRM-BERT, a deep learning method that combined the pre-trained DNABERT deep sequence representation module and the convolutional neural network (CNN) exploiting four traditional sequence feature encodings to improve the prediction performance. MRM-BERT was evaluated on multiple datasets of 12 commonly occurring RNA modifications, including m<sup>6</sup>A, m<sup>5</sup>C, m<sup>1</sup>A and so on. The results demonstrate that our hybrid model outperforms other models in terms of area under receiver operating characteristic curve (AUC) for all 12 types of RNA modifications. MRM-BERT is available as an online tool (http://117.122.208.21:8501) or source code (https://github.com/abhhba999/MRM-BERT), which allows users to predict RNA modification sites and visualize the results. Overall, our study provides an effective and efficient approach to predict multiple RNA modifications, contributing to the understanding of RNA biology and the development of therapeutic strategies.</p>","PeriodicalId":21351,"journal":{"name":"RNA Biology","volume":null,"pages":null},"PeriodicalIF":3.6000,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10877979/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"RNA Biology","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1080/15476286.2024.2315384","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/2/15 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

RNA modifications play crucial roles in various biological processes and diseases. Accurate prediction of RNA modification sites is essential for understanding their functions. In this study, we propose a hybrid approach that fuses a pre-trained sequence representation with various sequence features to predict multiple types of RNA modifications in one combined prediction framework. We developed MRM-BERT, a deep learning method that combined the pre-trained DNABERT deep sequence representation module and the convolutional neural network (CNN) exploiting four traditional sequence feature encodings to improve the prediction performance. MRM-BERT was evaluated on multiple datasets of 12 commonly occurring RNA modifications, including m6A, m5C, m1A and so on. The results demonstrate that our hybrid model outperforms other models in terms of area under receiver operating characteristic curve (AUC) for all 12 types of RNA modifications. MRM-BERT is available as an online tool (http://117.122.208.21:8501) or source code (https://github.com/abhhba999/MRM-BERT), which allows users to predict RNA modification sites and visualize the results. Overall, our study provides an effective and efficient approach to predict multiple RNA modifications, contributing to the understanding of RNA biology and the development of therapeutic strategies.

MRM-BERT:通过融合 BERT 表示法和序列特征预测多种 RNA 修饰的新型深度神经网络。
RNA 修饰在各种生物过程和疾病中发挥着至关重要的作用。准确预测 RNA 修饰位点对了解其功能至关重要。在本研究中,我们提出了一种混合方法,将预先训练的序列表示与各种序列特征相结合,在一个组合预测框架中预测多种类型的 RNA 修饰。我们开发的 MRM-BERT 是一种深度学习方法,它结合了预先训练的 DNABERT 深度序列表示模块和利用四种传统序列特征编码的卷积神经网络(CNN),以提高预测性能。MRM-BERT 在 12 种常见 RNA 修饰(包括 m6A、m5C、m1A 等)的多个数据集上进行了评估。结果表明,就接收者操作特征曲线下面积(AUC)而言,我们的混合模型在所有 12 种 RNA 修饰上都优于其他模型。MRM-BERT以在线工具(http://117.122.208.21:8501)或源代码(https://github.com/abhhba999/MRM-BERT)的形式提供,允许用户预测RNA修饰位点并可视化结果。总之,我们的研究为预测多种 RNA 修饰提供了一种有效且高效的方法,有助于理解 RNA 生物学和开发治疗策略。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
RNA Biology
RNA Biology 生物-生化与分子生物学
CiteScore
8.60
自引率
0.00%
发文量
82
审稿时长
1 months
期刊介绍: RNA has played a central role in all cellular processes since the beginning of life: decoding the genome, regulating gene expression, mediating molecular interactions, catalyzing chemical reactions. RNA Biology, as a leading journal in the field, provides a platform for presenting and discussing cutting-edge RNA research. RNA Biology brings together a multidisciplinary community of scientists working in the areas of: Transcription and splicing Post-transcriptional regulation of gene expression Non-coding RNAs RNA localization Translation and catalysis by RNA Structural biology Bioinformatics RNA in disease and therapy
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信