Cargando…

Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks

Biomedical interaction networks have incredible potential to be useful in the prediction of biologically meaningful interactions, identification of network biomarkers of disease, and the discovery of putative drug targets. Recently, graph neural networks have been proposed to effectively learn repre...

Descripción completa

Detalles Bibliográficos
Autores principales: KC, Kishan, Li, Rui, Cui, Feng, Haake, Anne R.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8518029/
https://www.ncbi.nlm.nih.gov/pubmed/33587705
http://dx.doi.org/10.1109/TCBB.2021.3059415
_version_ 1784584135032963072
author KC, Kishan
Li, Rui
Cui, Feng
Haake, Anne R.
author_facet KC, Kishan
Li, Rui
Cui, Feng
Haake, Anne R.
author_sort KC, Kishan
collection PubMed
description Biomedical interaction networks have incredible potential to be useful in the prediction of biologically meaningful interactions, identification of network biomarkers of disease, and the discovery of putative drug targets. Recently, graph neural networks have been proposed to effectively learn representations for biomedical entities and achieved state-of-the-art results in biomedical interaction prediction. These methods only consider information from immediate neighbors but cannot learn a general mixing of features from neighbors at various distances. In this paper, we present a higher-order graph convolutional network (HOGCN) to aggregate information from the higher-order neighborhood for biomedical interaction prediction. Specifically, HOGCN collects feature representations of neighbors at various distances and learns their linear mixing to obtain informative representations of biomedical entities. Experiments on four interaction networks, including protein-protein, drug-drug, drug-target, and gene-disease interactions, show that HOGCN achieves more accurate and calibrated predictions. HOGCN performs well on noisy, sparse interaction networks when feature representations of neighbors at various distances are considered. Moreover, a set of novel interaction predictions are validated by literature-based case studies.
format Online
Article
Text
id pubmed-8518029
institution National Center for Biotechnology Information
language English
publishDate 2022
record_format MEDLINE/PubMed
spelling pubmed-85180292022-04-03 Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks KC, Kishan Li, Rui Cui, Feng Haake, Anne R. IEEE/ACM Trans Comput Biol Bioinform Article Biomedical interaction networks have incredible potential to be useful in the prediction of biologically meaningful interactions, identification of network biomarkers of disease, and the discovery of putative drug targets. Recently, graph neural networks have been proposed to effectively learn representations for biomedical entities and achieved state-of-the-art results in biomedical interaction prediction. These methods only consider information from immediate neighbors but cannot learn a general mixing of features from neighbors at various distances. In this paper, we present a higher-order graph convolutional network (HOGCN) to aggregate information from the higher-order neighborhood for biomedical interaction prediction. Specifically, HOGCN collects feature representations of neighbors at various distances and learns their linear mixing to obtain informative representations of biomedical entities. Experiments on four interaction networks, including protein-protein, drug-drug, drug-target, and gene-disease interactions, show that HOGCN achieves more accurate and calibrated predictions. HOGCN performs well on noisy, sparse interaction networks when feature representations of neighbors at various distances are considered. Moreover, a set of novel interaction predictions are validated by literature-based case studies. 2022 2022-04-01 /pmc/articles/PMC8518029/ /pubmed/33587705 http://dx.doi.org/10.1109/TCBB.2021.3059415 Text en https://creativecommons.org/licenses/by/4.0/This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
spellingShingle Article
KC, Kishan
Li, Rui
Cui, Feng
Haake, Anne R.
Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
title Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
title_full Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
title_fullStr Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
title_full_unstemmed Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
title_short Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
title_sort predicting biomedical interactions with higher-order graph convolutional networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8518029/
https://www.ncbi.nlm.nih.gov/pubmed/33587705
http://dx.doi.org/10.1109/TCBB.2021.3059415
work_keys_str_mv AT kckishan predictingbiomedicalinteractionswithhigherordergraphconvolutionalnetworks
AT lirui predictingbiomedicalinteractionswithhigherordergraphconvolutionalnetworks
AT cuifeng predictingbiomedicalinteractionswithhigherordergraphconvolutionalnetworks
AT haakeanner predictingbiomedicalinteractionswithhigherordergraphconvolutionalnetworks