Cargando…

An inductive graph neural network model for compound–protein interaction prediction based on a homogeneous graph

Identifying the potential compound–protein interactions (CPIs) plays an essential role in drug development. The computational approaches for CPI prediction can reduce time and costs of experimental methods and have benefited from the continuously improved graph representation learning. However, most...

Descripción completa

Detalles Bibliográficos
Autores principales: Wan, Xiaozhe, Wu, Xiaolong, Wang, Dingyan, Tan, Xiaoqin, Liu, Xiaohong, Fu, Zunyun, Jiang, Hualiang, Zheng, Mingyue, Li, Xutong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9310259/
https://www.ncbi.nlm.nih.gov/pubmed/35275993
http://dx.doi.org/10.1093/bib/bbac073
_version_ 1784753351357890560
author Wan, Xiaozhe
Wu, Xiaolong
Wang, Dingyan
Tan, Xiaoqin
Liu, Xiaohong
Fu, Zunyun
Jiang, Hualiang
Zheng, Mingyue
Li, Xutong
author_facet Wan, Xiaozhe
Wu, Xiaolong
Wang, Dingyan
Tan, Xiaoqin
Liu, Xiaohong
Fu, Zunyun
Jiang, Hualiang
Zheng, Mingyue
Li, Xutong
author_sort Wan, Xiaozhe
collection PubMed
description Identifying the potential compound–protein interactions (CPIs) plays an essential role in drug development. The computational approaches for CPI prediction can reduce time and costs of experimental methods and have benefited from the continuously improved graph representation learning. However, most of the network-based methods use heterogeneous graphs, which is challenging due to their complex structures and heterogeneous attributes. Therefore, in this work, we transformed the compound–protein heterogeneous graph to a homogeneous graph by integrating the ligand-based protein representations and overall similarity associations. We then proposed an Inductive Graph AggrEgator-based framework, named CPI-IGAE, for CPI prediction. CPI-IGAE learns the low-dimensional representations of compounds and proteins from the homogeneous graph in an end-to-end manner. The results show that CPI-IGAE performs better than some state-of-the-art methods. Further ablation study and visualization of embeddings reveal the advantages of the model architecture and its role in feature extraction, and some of the top ranked CPIs by CPI-IGAE have been validated by a review of recent literature. The data and source codes are available at https://github.com/wanxiaozhe/CPI-IGAE.
format Online
Article
Text
id pubmed-9310259
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-93102592022-07-26 An inductive graph neural network model for compound–protein interaction prediction based on a homogeneous graph Wan, Xiaozhe Wu, Xiaolong Wang, Dingyan Tan, Xiaoqin Liu, Xiaohong Fu, Zunyun Jiang, Hualiang Zheng, Mingyue Li, Xutong Brief Bioinform Problem Solving Protocol Identifying the potential compound–protein interactions (CPIs) plays an essential role in drug development. The computational approaches for CPI prediction can reduce time and costs of experimental methods and have benefited from the continuously improved graph representation learning. However, most of the network-based methods use heterogeneous graphs, which is challenging due to their complex structures and heterogeneous attributes. Therefore, in this work, we transformed the compound–protein heterogeneous graph to a homogeneous graph by integrating the ligand-based protein representations and overall similarity associations. We then proposed an Inductive Graph AggrEgator-based framework, named CPI-IGAE, for CPI prediction. CPI-IGAE learns the low-dimensional representations of compounds and proteins from the homogeneous graph in an end-to-end manner. The results show that CPI-IGAE performs better than some state-of-the-art methods. Further ablation study and visualization of embeddings reveal the advantages of the model architecture and its role in feature extraction, and some of the top ranked CPIs by CPI-IGAE have been validated by a review of recent literature. The data and source codes are available at https://github.com/wanxiaozhe/CPI-IGAE. Oxford University Press 2022-03-12 /pmc/articles/PMC9310259/ /pubmed/35275993 http://dx.doi.org/10.1093/bib/bbac073 Text en © The Author(s) 2022. Published by Oxford University Press. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Problem Solving Protocol
Wan, Xiaozhe
Wu, Xiaolong
Wang, Dingyan
Tan, Xiaoqin
Liu, Xiaohong
Fu, Zunyun
Jiang, Hualiang
Zheng, Mingyue
Li, Xutong
An inductive graph neural network model for compound–protein interaction prediction based on a homogeneous graph
title An inductive graph neural network model for compound–protein interaction prediction based on a homogeneous graph
title_full An inductive graph neural network model for compound–protein interaction prediction based on a homogeneous graph
title_fullStr An inductive graph neural network model for compound–protein interaction prediction based on a homogeneous graph
title_full_unstemmed An inductive graph neural network model for compound–protein interaction prediction based on a homogeneous graph
title_short An inductive graph neural network model for compound–protein interaction prediction based on a homogeneous graph
title_sort inductive graph neural network model for compound–protein interaction prediction based on a homogeneous graph
topic Problem Solving Protocol
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9310259/
https://www.ncbi.nlm.nih.gov/pubmed/35275993
http://dx.doi.org/10.1093/bib/bbac073
work_keys_str_mv AT wanxiaozhe aninductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT wuxiaolong aninductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT wangdingyan aninductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT tanxiaoqin aninductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT liuxiaohong aninductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT fuzunyun aninductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT jianghualiang aninductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT zhengmingyue aninductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT lixutong aninductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT wanxiaozhe inductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT wuxiaolong inductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT wangdingyan inductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT tanxiaoqin inductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT liuxiaohong inductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT fuzunyun inductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT jianghualiang inductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT zhengmingyue inductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph
AT lixutong inductivegraphneuralnetworkmodelforcompoundproteininteractionpredictionbasedonahomogeneousgraph