Prediction of MoRFs Based on n-gram Convolutional Neural Network

Fang Chun; Yoshitaka Moriwaki; Caihong Li; Kentaro Shimizu

doi:10.29007/5k4z

Download PDF Open PDF in browser

Prediction of MoRFs Based on n-gram Convolutional Neural Network

7 pages•Published: March 18, 2019

Fang Chun, Yoshitaka Moriwaki, Caihong Li and Kentaro Shimizu

Abstract

MoRFs usually play as "hub" site in interaction networks of intrinsically disordered proteins. With more and more serious diseases being found to be associated with disordered proteins, identifying MoRFs has become increasingly important. In this study, we introduce a multichannel convolutional neural network (CNN) model for MoRFs prediction. This model is generated by expanding the standard one-dimensional CNN model using multiple parallel CNNs that read the sequence with different n-gram sizes (groups of residues). In addition, we add an averaging step to refine the output result of machine learning model. When compared with other methods on the same dataset, our approach achieved a balanced accuracy of 0.682 and an AUC of 0.723, which is the best performance among the single model-based approaches.

Keyphrases: disordered proteins, MoRFs, n-gram, single model

In: Oliver Eulenstein, Hisham Al-Mubaid and Qin Ding (editors). Proceedings of 11th International Conference on Bioinformatics and Computational Biology, vol 60, pages 113--119

Links:	https://easychair.org/publications/paper/ZSlw
	https://doi.org/10.29007/5k4z

BibTeX entry

@inproceedings{BiCOB2019:Prediction_of_MoRFs_Based,
  author    = {Fang Chun and Yoshitaka Moriwaki and Caihong Li and Kentaro Shimizu},
  title     = {Prediction of MoRFs Based on n-gram Convolutional Neural Network},
  booktitle = {Proceedings of 11th International Conference on Bioinformatics and Computational Biology},
  editor    = {Oliver Eulenstein and Hisham Al-Mubaid and Qin Ding},
  series    = {EPiC Series in Computing},
  volume    = {60},
  pages     = {113--119},
  year      = {2019},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {https://easychair.org/publications/paper/ZSlw},
  doi       = {10.29007/5k4z}}

Download PDF Open PDF in browser