Attention-based multi-label neural networks for integrated prediction and interpretation of twelve widely occurring RNA modifications

被引:85
作者
Song, Zitao [1 ]
Huang, Daiyun [2 ,3 ]
Song, Bowen [1 ,4 ]
Chen, Kunqi [5 ]
Song, Yiyou [2 ]
Liu, Gang [1 ]
Su, Jionglong [6 ]
de Magalhaes, Joao Pedro [7 ]
Rigden, Daniel J. [4 ]
Meng, Jia [2 ,4 ,8 ]
机构
[1] Xian Jiaotong Liverpool Univ, Dept Math Sci, Suzhou, Peoples R China
[2] Xian Jiaotong Liverpool Univ, Dept Biol Sci, Suzhou, Peoples R China
[3] Univ Liverpool, Dept Comp Sci, Liverpool, Merseyside, England
[4] Univ Liverpool, Inst Syst Mol & Integrat Biol, Liverpool, Merseyside, England
[5] Fujian Med Univ, Sch Basic Med Sci, Lab Minist Educ Gastrointestinal Canc, Fuzhou, Peoples R China
[6] Xian Jiaotong Liverpool Univ, XJTLU Entrepreneur Coll Taicang, Sch AI & Adv Comp, Suzhou, Peoples R China
[7] Univ Liverpool, Inst Ageing & Chron Dis, Liverpool, Merseyside, England
[8] Xian Jiaotong Liverpool Univ, AI Univ Res Ctr, Suzhou, Peoples R China
基金
中国国家自然科学基金;
关键词
WEB SERVER; SITES; PSEUDOURIDINE; NUCLEOTIDE; DATABASE; TISSUES;
D O I
10.1038/s41467-021-24313-3
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Recent studies suggest that epi-transcriptome regulation via post-transcriptional RNA modifications is vital for all RNA types. Precise identification of RNA modification sites is essential for understanding the functions and regulatory mechanisms of RNAs. Here, we present MultiRM, a method for the integrated prediction and interpretation of post-transcriptional RNA modifications from RNA sequences. Built upon an attention-based multi-label deep learning framework, MultiRM not only simultaneously predicts the putative sites of twelve widely occurring transcriptome modifications (m(6)A, m(1)A, m(5)C, m(5)U, m(6)Am, m(7)G, Psi, I, Am, Cm, Gm, and Um), but also returns the key sequence contents that contribute most to the positive predictions. Importantly, our model revealed a strong association among different types of RNA modifications from the perspective of their associated sequence contexts. Our work provides a solution for detecting multiple RNA modifications, enabling an integrated analysis of these RNA modifications, and gaining a better understanding of sequence-based RNA modification mechanisms. RNA modifications appear to play a role in determining RNA structure and function. Here, the authors develop a deep learning model that predicts the location of 12 RNA modifications using primary sequence, and show that several modifications are associated, which suggests dependencies between them.
引用
收藏
页数:11
相关论文
共 70 条
[1]  
[Anonymous], P 5 INT C LEARN REPR
[2]  
[Anonymous], 2019, P IEEE C COMP VIS PA
[3]  
[Anonymous], 2017, INT C MACH LEARN
[4]   Acetylation of Cytidine in mRNA Promotes Translation Efficiency [J].
Arango, Daniel ;
Sturgill, David ;
Alhusaini, Najwa ;
Dillman, Allissa A. ;
Sweet, Thomas J. ;
Hanson, Gavin ;
Hosogane, Masaki ;
Sinclair, Wilson R. ;
Nanan, Kyster K. ;
Mandler, Mariana D. ;
Fox, Stephen D. ;
Zengeya, Thomas T. ;
Andresson, Thorkell ;
Meier, Jordan L. ;
Coller, Jeffery ;
Oberdoerffer, Shalini .
CELL, 2018, 175 (07) :1872-+
[5]   Base-resolution models of transcription-factor binding reveal soft motif syntax [J].
Avsec, Ziga ;
Weilert, Melanie ;
Shrikumar, Avanti ;
Krueger, Sabrina ;
Alexandari, Amr ;
Dalal, Khyati ;
Fropf, Robin ;
McAnany, Charles ;
Gagneur, Julien ;
Kundaje, Anshul ;
Zeitlinger, Julia .
NATURE GENETICS, 2021, 53 (03) :354-+
[6]  
Bahdanau D., 2015, 3 INT C LEARN REP IC
[7]  
Bailey T. L., BIOINFORMATICS
[8]   DREME: motif discovery in transcription factor ChIP-seq data [J].
Bailey, Timothy L. .
BIOINFORMATICS, 2011, 27 (12) :1653-1659
[9]   MODOMICS: a database of RNA modification pathways. 2017 update [J].
Boccaletto, Pietro ;
Machnicka, Magdalena A. ;
Purta, Elzbieta ;
Piatkowski, Pawe ;
Baginski, Blazej ;
Wirecki, Tomasz K. ;
de Crecy-Lagard, Valerie ;
Ross, Robert ;
Limbach, Patrick A. ;
Kotter, Annika ;
Helm, Mark ;
Bujnicki, Janusz M. .
NUCLEIC ACIDS RESEARCH, 2018, 46 (D1) :D303-D307
[10]   FICC-Seq: a method for enzyme-specified profiling of methyl-5-uridine in cellular RNA [J].
Carter, Jean-Michel ;
Emmett, Warren ;
Mozos, Igor R. D. L. ;
Kotter, Annika ;
Helm, Mark ;
Ule, Jernej ;
Hussain, Shobbir .
NUCLEIC ACIDS RESEARCH, 2019, 47 (19) :E113-+