Construction of Protein-Protein Interactions Model by Deep Neural Networks

DOI

10.2991/bbbs-18.2018.47How to use a DOI?

Keywords

Deep neural networks, Protein-protein interaction, Construction.

Abstract

In order to improve the effectiveness of the network prediction result of protein-protein interaction, the network prediction model of protein-protein interaction based on deep neural network has been proposed. Here, we present here a novel DPPI model with deep neural network and conjoint triad (CT) descriptors to predict protein-protein interactions only using the information of protein sequences. The best DPPI model achieved an accuracy of 97.65%, recall of 98.96% and area under the curve (AUC) of 98.51% with 10-fold cross-validation, respectively, which means that the model of predicting the interaction of protein-protein by deep neural network algorithm is accurate and effective.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yuanmiao Gui
AU  - Rujing Wang
AU  - Yuanyuan Wei
AU  - Xue Wang
PY  - 2018/04
DA  - 2018/04
TI  - Construction of Protein-Protein Interactions Model by Deep Neural Networks
BT  - Proceedings of the 2018 International Workshop on Bioinformatics, Biochemistry, Biomedical Sciences (BBBS 2018)
PB  - Atlantis Press
SP  - 221
EP  - 229
SN  - 2468-5747
UR  - https://doi.org/10.2991/bbbs-18.2018.47
DO  - 10.2991/bbbs-18.2018.47
ID  - Gui2018/04
ER  -