Multifaceted protein-protein interaction prediction based on Siamese residual RCNN.

Bioinformatics 2019 Jul;35(14):i305-i314

Department of Computer Science, University of California, Los Angeles, Los Angeles, CA, USA.

Motivation: Sequence-based protein-protein interaction (PPI) prediction represents a fundamental computational biology problem. To address this problem, extensive research efforts have been made to extract predefined features from the sequences. Based on these features, statistical algorithms are learned to classify the PPIs. However, such explicit features are usually costly to extract, and typically have limited coverage on the PPI information.

Results: We present an end-to-end framework, PIPR (Protein-Protein Interaction Prediction Based on Siamese Residual RCNN), for PPI predictions using only the protein sequences. PIPR incorporates a deep residual recurrent convolutional neural network in the Siamese architecture, which leverages both robust local features and contextualized information, which are significant for capturing the mutual influence of proteins sequences. PIPR relieves the data pre-processing efforts that are required by other systems, and generalizes well to different application scenarios. Experimental evaluations show that PIPR outperforms various state-of-the-art systems on the binary PPI prediction problem. Moreover, it shows a promising performance on more challenging problems of interaction type prediction and binding affinity estimation, where existing approaches fall short.

Availability And Implementation: The implementation is available at https://github.com/muhaochen/seq_ppi.git.

Supplementary Information: Supplementary data are available at Bioinformatics online.

Download full-text PDF

Source
http://dx.doi.org/10.1093/bioinformatics/btz328DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6681469PMC
July 2019

Publication Analysis

Top Keywords

protein-protein interaction
12
sequences pipr
8
based siamese
8
residual rcnn
8
ppi prediction
8
prediction based
8
siamese residual
8
interaction prediction
8
prediction
5
deep residual
4
type prediction
4
incorporates deep
4
pipr incorporates
4
prediction binding
4
residual recurrent
4
siamese architecture
4
recurrent convolutional
4
problems interaction
4
neural network
4
convolutional neural
4

References

(Supplied by CrossRef)
Controlling the false discovery rate: a practical and powerful approach to multiple testing
Benjamini et al.
J. R. Stat. Soc. Series B (Methodol.) 1995
The protein data bank
Berman et al.
Nucleic Acids Res 2000
Neural article pair modeling for Wikipedia sub-article matching
Chen et al.
ECML-PKDD 2018

Cho et al.
2014

Conneau et al.
2017
UniProt: the universal protein knowledgebase
Consortium et al.
Nucleic Acids Res 2018

Dhingra et al.
2017

Similar Publications