CNNPSP: Pseudouridine Sites Prediction Based on Deep Learning

  • Yongxian FanEmail author
  • Yongzhen Li
  • Huihua Yang
  • Xiaoyong PanEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11871)


Pseudouridine (ψ) is a kind of RNA modification, which is formed at specific site of RNA sequence due to the catalytic action of Pseudouridine synthase in the process of gene transcription. It is the most prevalent RNA modification found so far, and plays a vital role in normal biological functions. Several computational methods have been proposed to predict Pseudouridine sites, but these methods still do not achieve high accuracy. At present, deep learning has become a popular field of machine learning, and convolutional neural network (CNN) is one widely used algorithm. CNN can automatically dig into the hidden features of data and make accurate predictions, so a new algorithm based on CNN was proposed for extracting the features from RNA sequences with and without ψ sites. And a predictor called CNNPSP was developed to predict ψ sites in RNAs across three species (H. sapiens, S. cerevisiae and M. musculus). Both the rigorous jackknife test and independent test indicated that the new predictor outperformed the existing methods in this task.


Convolutional Neural Network Deep learning Pseudouridine sites 


  1. 1.
    Czerwoniec, A., et al.: MODOMICS: a database of RNA modification pathways. 2008 update. Nucleic Acids Res. 37, D118–D121 (2009)CrossRefGoogle Scholar
  2. 2.
    Carlile, T.M., Rojas-Duran, M.F., Zinshteyn, B., Shin, H., Bartoli, K.M., Gilbert, W.V.: Pseudouridine profiling reveals regulated mRNA pseudouridylation in yeast and human cells. Nature 515, 143 (2014)CrossRefGoogle Scholar
  3. 3.
    Chen, W., Tang, H., Ye, J., Lin, H., Chou, K.-C.: iRNA-PseU: identifying RNA pseudouridine sites. Mol. Ther-Nucleic Acids 5, e332 (2016)Google Scholar
  4. 4.
    Li, Y.-H., Zhang, G., Cui, Q.: PPUS: a web server to predict PUS-specific pseudouridine sites. Bioinformatics 31, 3362–3364 (2015)CrossRefGoogle Scholar
  5. 5.
    Pan, X., Rijnbeek, P., Yan, J., Shen, H.-B.: Prediction of RNA-protein sequence and structure binding preferences using deep convolutional and recurrent neural networks. BMC Genomics. 19, 511 (2018)CrossRefGoogle Scholar
  6. 6.
    Alipanahi, B., Delong, A., Weirauch, M.T., Frey, B.J.: Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat. Biotech. 33, 831 (2015)CrossRefGoogle Scholar
  7. 7.
    Pan, X., Shen, H.-B.: RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach. BMC Bioinf. 18, 136 (2017)CrossRefGoogle Scholar
  8. 8.
    Sun, W.-J., et al.: RMBase: a resource for decoding the landscape of RNA modifications from high-throughput sequencing data. Nucleic Acids Res. 44, D259–D265 (2016)CrossRefGoogle Scholar
  9. 9.
    Speir, M.L., et al.: The UCSC genome browser database: 2016 update. Nucleic Acids Res. 44, D717–D725 (2016)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Computer and Information SecurityGuilin University of Electronic TechnologyGuilinChina
  2. 2.School of Electronic Engineering and AutomationGuilin University of Electronic TechnologyGuilinChina
  3. 3.Institute of Image Processing and Pattern RecognitionShanghai Jiao Tong UniversityShanghaiChina
  4. 4.School of AutomationBeijing University of Posts and TelecommunicationsBeijingChina

Personalised recommendations