Associating brain imaging phenotypes and genetic risk factors via a hypergraph based netNMF method
AbstractAlzheimer’s disease (AD) is a severe neurodegenerative disease for which there is currently no effective treatment. Mild cognitive impairment (MCI) is an early disease that may progress to AD. The effective diagnosis of AD and MCI in the early stage has important clinical significance.Method...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-03-01
|
Series: | Frontiers in Aging Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnagi.2023.1052783/full |
_version_ | 1811161700817174528 |
---|---|
author | Junli Zhuang Jinping Tian Xiaoxing Xiong Taihan Li Zhengwei Chen Rong Chen Jun Chen Xiang Li |
author_facet | Junli Zhuang Jinping Tian Xiaoxing Xiong Taihan Li Zhengwei Chen Rong Chen Jun Chen Xiang Li |
author_sort | Junli Zhuang |
collection | DOAJ |
description | AbstractAlzheimer’s disease (AD) is a severe neurodegenerative disease for which there is currently no effective treatment. Mild cognitive impairment (MCI) is an early disease that may progress to AD. The effective diagnosis of AD and MCI in the early stage has important clinical significance.MethodsTo this end, this paper proposed a hypergraph-based netNMF (HG-netNMF) algorithm for integrating structural magnetic resonance imaging (sMRI) of AD and MCI with corresponding gene expression profiles.ResultsHypergraph regularization assumes that regions of interest (ROIs) and genes were located on a non-linear low-dimensional manifold and can capture the inherent prevalence of two modalities of data and mined high-order correlation features of the two data. Further, this paper used the HG-netNMF algorithm to construct a brain structure connection network and a protein interaction network (PPI) with potential role relationships, mine the risk (ROI) and key genes of both, and conduct a series of bioinformatics analyses.ConclusionFinally, this paper used the risk ROI and key genes of the AD and MCI groups to construct diagnostic models. The AUC of the AD group and MCI group were 0.8 and 0.797, respectively. |
first_indexed | 2024-04-10T06:18:37Z |
format | Article |
id | doaj.art-82ac6c85cef44c10b152875623de7a38 |
institution | Directory Open Access Journal |
issn | 1663-4365 |
language | English |
last_indexed | 2024-04-10T06:18:37Z |
publishDate | 2023-03-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Aging Neuroscience |
spelling | doaj.art-82ac6c85cef44c10b152875623de7a382023-03-02T05:28:43ZengFrontiers Media S.A.Frontiers in Aging Neuroscience1663-43652023-03-011510.3389/fnagi.2023.10527831052783Associating brain imaging phenotypes and genetic risk factors via a hypergraph based netNMF methodJunli Zhuang0Jinping Tian1Xiaoxing Xiong2Taihan Li3Zhengwei Chen4Rong Chen5Jun Chen6Xiang Li7Department of Vascular Surgery, Renmin Hospital of Wuhan University, Wuhan, ChinaFaculty of Medicine, Jianghan University, Wuhan, ChinaCentral Laboratory, Renmin Hospital of Wuhan University, Wuhan, ChinaDepartment of Clinical Laboratory, The First Affiliated Hospital of Shenzhen University, Shenzhen Second People's Hospital, Shenzhen, ChinaDepartment of Radiology, Hubei Provincial Hospital of Traditional Chinese Medicine, Wuhan, ChinaDepartment of Radiology, Hubei Provincial Hospital of Traditional Chinese Medicine, Wuhan, ChinaDepartment of Radiology, Hubei Provincial Hospital of Traditional Chinese Medicine, Wuhan, ChinaSchool of Health, Wuhan University, Wuhan, ChinaAbstractAlzheimer’s disease (AD) is a severe neurodegenerative disease for which there is currently no effective treatment. Mild cognitive impairment (MCI) is an early disease that may progress to AD. The effective diagnosis of AD and MCI in the early stage has important clinical significance.MethodsTo this end, this paper proposed a hypergraph-based netNMF (HG-netNMF) algorithm for integrating structural magnetic resonance imaging (sMRI) of AD and MCI with corresponding gene expression profiles.ResultsHypergraph regularization assumes that regions of interest (ROIs) and genes were located on a non-linear low-dimensional manifold and can capture the inherent prevalence of two modalities of data and mined high-order correlation features of the two data. Further, this paper used the HG-netNMF algorithm to construct a brain structure connection network and a protein interaction network (PPI) with potential role relationships, mine the risk (ROI) and key genes of both, and conduct a series of bioinformatics analyses.ConclusionFinally, this paper used the risk ROI and key genes of the AD and MCI groups to construct diagnostic models. The AUC of the AD group and MCI group were 0.8 and 0.797, respectively.https://www.frontiersin.org/articles/10.3389/fnagi.2023.1052783/fullnon-negative matrix factorizationAlzheimer’s diseasemild cognitive impairmenthypergraph learningbiomarkers |
spellingShingle | Junli Zhuang Jinping Tian Xiaoxing Xiong Taihan Li Zhengwei Chen Rong Chen Jun Chen Xiang Li Associating brain imaging phenotypes and genetic risk factors via a hypergraph based netNMF method Frontiers in Aging Neuroscience non-negative matrix factorization Alzheimer’s disease mild cognitive impairment hypergraph learning biomarkers |
title | Associating brain imaging phenotypes and genetic risk factors via a hypergraph based netNMF method |
title_full | Associating brain imaging phenotypes and genetic risk factors via a hypergraph based netNMF method |
title_fullStr | Associating brain imaging phenotypes and genetic risk factors via a hypergraph based netNMF method |
title_full_unstemmed | Associating brain imaging phenotypes and genetic risk factors via a hypergraph based netNMF method |
title_short | Associating brain imaging phenotypes and genetic risk factors via a hypergraph based netNMF method |
title_sort | associating brain imaging phenotypes and genetic risk factors via a hypergraph based netnmf method |
topic | non-negative matrix factorization Alzheimer’s disease mild cognitive impairment hypergraph learning biomarkers |
url | https://www.frontiersin.org/articles/10.3389/fnagi.2023.1052783/full |
work_keys_str_mv | AT junlizhuang associatingbrainimagingphenotypesandgeneticriskfactorsviaahypergraphbasednetnmfmethod AT jinpingtian associatingbrainimagingphenotypesandgeneticriskfactorsviaahypergraphbasednetnmfmethod AT xiaoxingxiong associatingbrainimagingphenotypesandgeneticriskfactorsviaahypergraphbasednetnmfmethod AT taihanli associatingbrainimagingphenotypesandgeneticriskfactorsviaahypergraphbasednetnmfmethod AT zhengweichen associatingbrainimagingphenotypesandgeneticriskfactorsviaahypergraphbasednetnmfmethod AT rongchen associatingbrainimagingphenotypesandgeneticriskfactorsviaahypergraphbasednetnmfmethod AT junchen associatingbrainimagingphenotypesandgeneticriskfactorsviaahypergraphbasednetnmfmethod AT xiangli associatingbrainimagingphenotypesandgeneticriskfactorsviaahypergraphbasednetnmfmethod |