Advanced search
1 file | 628.50 KB

TISRover : ConvNets learn biologically relevant features for effective translation initiation site prediction

Jasper Zuallaert (UGent) , Mijung Kim, Arne Soete (UGent) , Yvan Saeys (UGent) and Wesley De Neve (UGent)
Author
Organization
Abstract
Being a key component in gene regulation, translation initiation is a well-studied topic. However, recent findings have shown translation initiation to be more complex than initially thought, urging for more effective prediction methods. In this paper, we present TISRover, a multi-layered convolutional neural network architecture for translation initiation site prediction. We achieve state-of-the-art results, outperforming a previous deep learning approach by 4% to 23% in terms of auPRC, and other approaches by at least 68% in terms of error rate. Furthermore, we present a methodology to analyse the decision-making process of our network models, revealing various biologically relevant features for translation initiation site prediction that are automatically learnt from scratch, without any prior knowledge. The most notable features found are the Kozak consensus sequence, the reading frame characteristics, the influence of stop and start codons in the sequence, and the presence of donor splice site patterns.
Keywords
convolutional neural networks, deep learning, genomics, model interpretation, model visualisation, translation initiation site prediction, SEQUENCES, BINDING

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 628.50 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Zuallaert, Jasper, Mijung Kim, Arne Soete, Yvan Saeys, and Wesley De Neve. 2018. “TISRover : ConvNets Learn Biologically Relevant Features for Effective Translation Initiation Site Prediction.” International Journal of Data Mining and Bioinformatics 20 (3): 267–284.
APA
Zuallaert, Jasper, Kim, M., Soete, A., Saeys, Y., & De Neve, W. (2018). TISRover : ConvNets learn biologically relevant features for effective translation initiation site prediction. INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS, 20(3), 267–284.
Vancouver
1.
Zuallaert J, Kim M, Soete A, Saeys Y, De Neve W. TISRover : ConvNets learn biologically relevant features for effective translation initiation site prediction. INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS. 2018;20(3):267–84.
MLA
Zuallaert, Jasper, Mijung Kim, Arne Soete, et al. “TISRover : ConvNets Learn Biologically Relevant Features for Effective Translation Initiation Site Prediction.” INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS 20.3 (2018): 267–284. Print.
@article{8575499,
  abstract     = {Being a key component in gene regulation, translation initiation is a well-studied topic. However, recent findings have shown translation initiation to be more complex than initially thought, urging for more effective prediction methods. In this paper, we present TISRover, a multi-layered convolutional neural network architecture for translation initiation site prediction. We achieve state-of-the-art results, outperforming a previous deep learning approach by 4\% to 23\% in terms of auPRC, and other approaches by at least 68\% in terms of error rate. Furthermore, we present a methodology to analyse the decision-making process of our network models, revealing various biologically relevant features for translation initiation site prediction that are automatically learnt from scratch, without any prior knowledge. The most notable features found are the Kozak consensus sequence, the reading frame characteristics, the influence of stop and start codons in the sequence, and the presence of donor splice site patterns.},
  author       = {Zuallaert, Jasper and Kim, Mijung and Soete, Arne and Saeys, Yvan and De Neve, Wesley},
  issn         = {1748-5673},
  journal      = {INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS},
  language     = {eng},
  number       = {3},
  pages        = {267--284},
  title        = {TISRover : ConvNets learn biologically relevant features for effective translation initiation site prediction},
  url          = {http://dx.doi.org/10.1504/IJDMB.2018.094781},
  volume       = {20},
  year         = {2018},
}

Altmetric
View in Altmetric
Web of Science
Times cited: