Predict protein-protein interactions from protein primary sequences: using wavelet transform combined with stacking algorithm
- Published
- Accepted
- Subject Areas
- Bioinformatics, Biotechnology, Computational Biology
- Keywords
- Pseudo amino acid composition, Protein sequence, Wavelet transfrom, Protein-protein interaction, Stacked generalization
- Copyright
- © 2017 Xu et al.
- Licence
- This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Preprints) and either DOI or URL of the article must be cited.
- Cite this article
- 2017. Predict protein-protein interactions from protein primary sequences: using wavelet transform combined with stacking algorithm. PeerJ Preprints 5:e2964v1 https://doi.org/10.7287/peerj.preprints.2964v1
Abstract
Most biological processes within a cell are carried out by protein-protein interaction (PPI) networks, or so called interactomics. Therefore, identification of PPIs is crucial to elucidating protein functions and further understanding of various cellular biological processes. Currently, a series of high-throughput experimental technologies for detect PPIs have been presented. However, the time-consuming and labor-driven characteristics of these methods forced people to turn to virtual technology for PPIs prediction. Herein, we developed a new predictor which uses stacking algorithm with information extraction by wavelet transform. When applied on the Saccharomyces cerevisiae PPI dataset, the proposed method got a prediction accuracy of 83.35% with sensitivity of 92.95% at the specificity of 65.41%. An independent data set of 2726 Helicobacter pylori PPIs was also used to evaluate this prediction model, and the prediction accuracy is 80.39%, which is better than that of most existing methods.
Author Comment
This is a submission to PeerJ for review.