Cargando…

Predicting Protein–Protein Interactions via Gated Graph Attention Signed Network

Protein–protein interactions (PPIs) play a key role in signal transduction and pharmacogenomics, and hence, accurate PPI prediction is crucial. Graph structures have received increasing attention owing to their outstanding performance in machine learning. In practice, PPIs can be expressed as a sign...

Descripción completa

Detalles Bibliográficos
Autores principales: Xiang, Zhijie, Gong, Weijia, Li, Zehui, Yang, Xue, Wang, Jihua, Wang, Hong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8228288/
https://www.ncbi.nlm.nih.gov/pubmed/34071437
http://dx.doi.org/10.3390/biom11060799
_version_ 1783712707878322176
author Xiang, Zhijie
Gong, Weijia
Li, Zehui
Yang, Xue
Wang, Jihua
Wang, Hong
author_facet Xiang, Zhijie
Gong, Weijia
Li, Zehui
Yang, Xue
Wang, Jihua
Wang, Hong
author_sort Xiang, Zhijie
collection PubMed
description Protein–protein interactions (PPIs) play a key role in signal transduction and pharmacogenomics, and hence, accurate PPI prediction is crucial. Graph structures have received increasing attention owing to their outstanding performance in machine learning. In practice, PPIs can be expressed as a signed network (i.e., graph structure), wherein the nodes in the network represent proteins, and edges represent the interactions (positive or negative effects) of protein nodes. PPI predictions can be realized by predicting the links of the signed network; therefore, the use of gated graph attention for signed networks (SN-GGAT) is proposed herein. First, the concept of graph attention network (GAT) is applied to signed networks, in which “attention” represents the weight of neighbor nodes, and GAT updates the node features through the weighted aggregation of neighbor nodes. Then, the gating mechanism is defined and combined with the balance theory to obtain the high-order relations of protein nodes to improve the attention effect, making the attention mechanism follow the principle of “low-order high attention, high-order low attention, different signs opposite”. PPIs are subsequently predicted on the Saccharomyces cerevisiae core dataset and the Human dataset. The test results demonstrate that the proposed method exhibits strong competitiveness.
format Online
Article
Text
id pubmed-8228288
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-82282882021-06-26 Predicting Protein–Protein Interactions via Gated Graph Attention Signed Network Xiang, Zhijie Gong, Weijia Li, Zehui Yang, Xue Wang, Jihua Wang, Hong Biomolecules Article Protein–protein interactions (PPIs) play a key role in signal transduction and pharmacogenomics, and hence, accurate PPI prediction is crucial. Graph structures have received increasing attention owing to their outstanding performance in machine learning. In practice, PPIs can be expressed as a signed network (i.e., graph structure), wherein the nodes in the network represent proteins, and edges represent the interactions (positive or negative effects) of protein nodes. PPI predictions can be realized by predicting the links of the signed network; therefore, the use of gated graph attention for signed networks (SN-GGAT) is proposed herein. First, the concept of graph attention network (GAT) is applied to signed networks, in which “attention” represents the weight of neighbor nodes, and GAT updates the node features through the weighted aggregation of neighbor nodes. Then, the gating mechanism is defined and combined with the balance theory to obtain the high-order relations of protein nodes to improve the attention effect, making the attention mechanism follow the principle of “low-order high attention, high-order low attention, different signs opposite”. PPIs are subsequently predicted on the Saccharomyces cerevisiae core dataset and the Human dataset. The test results demonstrate that the proposed method exhibits strong competitiveness. MDPI 2021-05-28 /pmc/articles/PMC8228288/ /pubmed/34071437 http://dx.doi.org/10.3390/biom11060799 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Xiang, Zhijie
Gong, Weijia
Li, Zehui
Yang, Xue
Wang, Jihua
Wang, Hong
Predicting Protein–Protein Interactions via Gated Graph Attention Signed Network
title Predicting Protein–Protein Interactions via Gated Graph Attention Signed Network
title_full Predicting Protein–Protein Interactions via Gated Graph Attention Signed Network
title_fullStr Predicting Protein–Protein Interactions via Gated Graph Attention Signed Network
title_full_unstemmed Predicting Protein–Protein Interactions via Gated Graph Attention Signed Network
title_short Predicting Protein–Protein Interactions via Gated Graph Attention Signed Network
title_sort predicting protein–protein interactions via gated graph attention signed network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8228288/
https://www.ncbi.nlm.nih.gov/pubmed/34071437
http://dx.doi.org/10.3390/biom11060799
work_keys_str_mv AT xiangzhijie predictingproteinproteininteractionsviagatedgraphattentionsignednetwork
AT gongweijia predictingproteinproteininteractionsviagatedgraphattentionsignednetwork
AT lizehui predictingproteinproteininteractionsviagatedgraphattentionsignednetwork
AT yangxue predictingproteinproteininteractionsviagatedgraphattentionsignednetwork
AT wangjihua predictingproteinproteininteractionsviagatedgraphattentionsignednetwork
AT wanghong predictingproteinproteininteractionsviagatedgraphattentionsignednetwork