Cargando…

Gated Graph Attention Network for Cancer Prediction

With its increasing incidence, cancer has become one of the main causes of worldwide mortality. In this work, we mainly propose a novel attention-based neural network model named Gated Graph ATtention network (GGAT) for cancer prediction, where a gating mechanism (GM) is introduced to work with the...

Descripción completa

Detalles Bibliográficos
Autores principales: Qiu, Linling, Li, Han, Wang, Meihong, Wang, Xiaoli
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7998488/
https://www.ncbi.nlm.nih.gov/pubmed/33801894
http://dx.doi.org/10.3390/s21061938
_version_ 1783670563846225920
author Qiu, Linling
Li, Han
Wang, Meihong
Wang, Xiaoli
author_facet Qiu, Linling
Li, Han
Wang, Meihong
Wang, Xiaoli
author_sort Qiu, Linling
collection PubMed
description With its increasing incidence, cancer has become one of the main causes of worldwide mortality. In this work, we mainly propose a novel attention-based neural network model named Gated Graph ATtention network (GGAT) for cancer prediction, where a gating mechanism (GM) is introduced to work with the attention mechanism (AM), to break through the previous work’s limitation of 1-hop neighbourhood reasoning. In this way, our GGAT is capable of fully mining the potential correlation between related samples, helping for improving the cancer prediction accuracy. Additionally, to simplify the datasets, we propose a hybrid feature selection algorithm to strictly select gene features, which significantly reduces training time without affecting prediction accuracy. To the best of our knowledge, our proposed GGAT achieves the state-of-the-art results in cancer prediction task on LIHC, LUAD, KIRC compared to other traditional machine learning methods and neural network models, and improves the accuracy by 1% to 2% on Cora dataset, compared to the state-of-the-art graph neural network methods.
format Online
Article
Text
id pubmed-7998488
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-79984882021-03-28 Gated Graph Attention Network for Cancer Prediction Qiu, Linling Li, Han Wang, Meihong Wang, Xiaoli Sensors (Basel) Article With its increasing incidence, cancer has become one of the main causes of worldwide mortality. In this work, we mainly propose a novel attention-based neural network model named Gated Graph ATtention network (GGAT) for cancer prediction, where a gating mechanism (GM) is introduced to work with the attention mechanism (AM), to break through the previous work’s limitation of 1-hop neighbourhood reasoning. In this way, our GGAT is capable of fully mining the potential correlation between related samples, helping for improving the cancer prediction accuracy. Additionally, to simplify the datasets, we propose a hybrid feature selection algorithm to strictly select gene features, which significantly reduces training time without affecting prediction accuracy. To the best of our knowledge, our proposed GGAT achieves the state-of-the-art results in cancer prediction task on LIHC, LUAD, KIRC compared to other traditional machine learning methods and neural network models, and improves the accuracy by 1% to 2% on Cora dataset, compared to the state-of-the-art graph neural network methods. MDPI 2021-03-10 /pmc/articles/PMC7998488/ /pubmed/33801894 http://dx.doi.org/10.3390/s21061938 Text en © 2021 by the authors. 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 (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Qiu, Linling
Li, Han
Wang, Meihong
Wang, Xiaoli
Gated Graph Attention Network for Cancer Prediction
title Gated Graph Attention Network for Cancer Prediction
title_full Gated Graph Attention Network for Cancer Prediction
title_fullStr Gated Graph Attention Network for Cancer Prediction
title_full_unstemmed Gated Graph Attention Network for Cancer Prediction
title_short Gated Graph Attention Network for Cancer Prediction
title_sort gated graph attention network for cancer prediction
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7998488/
https://www.ncbi.nlm.nih.gov/pubmed/33801894
http://dx.doi.org/10.3390/s21061938
work_keys_str_mv AT qiulinling gatedgraphattentionnetworkforcancerprediction
AT lihan gatedgraphattentionnetworkforcancerprediction
AT wangmeihong gatedgraphattentionnetworkforcancerprediction
AT wangxiaoli gatedgraphattentionnetworkforcancerprediction