PMID- 38233745
OWN - NLM
STAT- MEDLINE
DCOM- 20240119
LR  - 20240202
IS  - 1471-2105 (Electronic)
IS  - 1471-2105 (Linking)
VI  - 25
IP  - 1
DP  - 2024 Jan 17
TI  - MSCAN: multi-scale self- and cross-attention network for RNA methylation site 
      prediction.
PG  - 32
LID - 10.1186/s12859-024-05649-1 [doi]
LID - 32
AB  - BACKGROUND: Epi-transcriptome regulation through post-transcriptional RNA 
      modifications is essential for all RNA types. Precise recognition of RNA 
      modifications is critical for understanding their functions and regulatory 
      mechanisms. However, wet experimental methods are often costly and 
      time-consuming, limiting their wide range of applications. Therefore, recent 
      research has focused on developing computational methods, particularly deep 
      learning (DL). Bidirectional long short-term memory (BiLSTM), convolutional 
      neural network (CNN), and the transformer have demonstrated achievements in 
      modification site prediction. However, BiLSTM cannot achieve parallel 
      computation, leading to a long training time, CNN cannot learn the dependencies 
      of the long distance of the sequence, and the Transformer lacks information 
      interaction with sequences at different scales. This insight underscores the 
      necessity for continued research and development in natural language processing 
      (NLP) and DL to devise an enhanced prediction framework that can effectively 
      address the challenges presented. RESULTS: This study presents a multi-scale 
      self- and cross-attention network (MSCAN) to identify the RNA methylation site 
      using an NLP and DL way. Experiment results on twelve RNA modification sites 
      (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) reveal that 
      the area under the receiver operating characteristic of MSCAN obtains 
      respectively 98.34%, 85.41%, 97.29%, 96.74%, 99.04%, 79.94%, 76.22%, 65.69%, 
      92.92%, 92.03%, 95.77%, 89.66%, which is better than the state-of-the-art 
      prediction model. This indicates that the model has strong generalization 
      capabilities. Furthermore, MSCAN reveals a strong association among different 
      types of RNA modifications from an experimental perspective. A user-friendly web 
      server for predicting twelve widely occurring human RNA modification sites 
      (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) is 
      available at http://47.242.23.141/MSCAN/index.php . CONCLUSIONS: A predictor 
      framework has been developed through binary classification to predict RNA 
      methylation sites.
CI  - (c) 2024. The Author(s).
FAU - Wang, Honglei
AU  - Wang H
AD  - School of Information and Control Engineering, China University of Mining and 
      Technology, Xuzhou, 221116, China.
AD  - School of Information Engineering, Xuzhou College of Industrial Technology, 
      Xuzhou, 221400, China.
FAU - Huang, Tao
AU  - Huang T
AD  - School of Information and Control Engineering, China University of Mining and 
      Technology, Xuzhou, 221116, China.
FAU - Wang, Dong
AU  - Wang D
AD  - School of Computer Science and Technology, China University of Mining and 
      Technology, Xuzhou, 221116, China.
FAU - Zeng, Wenliang
AU  - Zeng W
AD  - School of Information and Control Engineering, China University of Mining and 
      Technology, Xuzhou, 221116, China.
FAU - Sun, Yanjing
AU  - Sun Y
AD  - School of Information and Control Engineering, China University of Mining and 
      Technology, Xuzhou, 221116, China. yjsun@cumt.edu.cn.
FAU - Zhang, Lin
AU  - Zhang L
AD  - School of Information and Control Engineering, China University of Mining and 
      Technology, Xuzhou, 221116, China. lin.zhang@cumt.edu.cn.
LA  - eng
GR  - 31871337/the National Natural Science Foundation of China/
GR  - 31871337/the National Natural Science Foundation of China/
GR  - 61971422/National Natural Science Foundation of China/
GR  - 61971422/National Natural Science Foundation of China/
GR  - 61971422/National Natural Science Foundation of China/
GR  - 61971422/National Natural Science Foundation of China/
GR  - BRA2020328/the "333 Project" of Jiangsu/
GR  - BRA2020328/the "333 Project" of Jiangsu/
GR  - BRA2020328/the "333 Project" of Jiangsu/
GR  - BRA2020328/the "333 Project" of Jiangsu/
PT  - Journal Article
DEP - 20240117
PL  - England
TA  - BMC Bioinformatics
JT  - BMC bioinformatics
JID - 100965194
RN  - 63231-63-0 (RNA)
SB  - IM
MH  - Humans
MH  - *RNA/genetics
MH  - *RNA Methylation
MH  - Neural Networks, Computer
MH  - Methylation
MH  - RNA Processing, Post-Transcriptional
PMC - PMC10795237
OTO - NOTNLM
OT  - Cross-attention
OT  - Multi-scale
OT  - Predictor
OT  - RNA methylation
OT  - Self-attention
OT  - Transformer
COIS- The authors declare that they have no competing interests.
EDAT- 2024/01/18 00:42
MHDA- 2024/01/19 06:43
PMCR- 2024/01/17
CRDT- 2024/01/17 23:32
PHST- 2023/04/24 00:00 [received]
PHST- 2024/01/11 00:00 [accepted]
PHST- 2024/01/19 06:43 [medline]
PHST- 2024/01/18 00:42 [pubmed]
PHST- 2024/01/17 23:32 [entrez]
PHST- 2024/01/17 00:00 [pmc-release]
AID - 10.1186/s12859-024-05649-1 [pii]
AID - 5649 [pii]
AID - 10.1186/s12859-024-05649-1 [doi]
PST - epublish
SO  - BMC Bioinformatics. 2024 Jan 17;25(1):32. doi: 10.1186/s12859-024-05649-1.