M 3 HOGAT: A Multi-View Multi-Modal Multi-Scale High-Order Graph Attention Network for Microbe-Disease Association Prediction

Numerous scientific studies have found a link between diverse microorganisms in the human body and complex human diseases. Because traditional experimental approaches are time-consuming and expensive, using computational methods to identify microbes correlated with diseases is critical. In this pape...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE journal of biomedical and health informatics Ročník 28; číslo 10; s. 6259 - 6267
Hlavní autoři: Wang, Shuang, Liu, Jin-Xing, Li, Feng, Wang, Juan, Gao, Ying-Lian
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States 01.10.2024
Témata:
ISSN:2168-2194, 2168-2208
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Numerous scientific studies have found a link between diverse microorganisms in the human body and complex human diseases. Because traditional experimental approaches are time-consuming and expensive, using computational methods to identify microbes correlated with diseases is critical. In this paper, a new microbe-disease association prediction model is proposed that combines a multi-view multi-modal network and a multi-scale feature fusion mechanism, called M HOGAT. Firstly, a microbe-disease association network and multiple similarity views are constructed based on multi-source information. Then, consider that neighbor information from disparate orders might be more adept at learning node representations. Consequently, the higher-order graph attention network (HOGAT) is devised to aggregate neighbor information from disparate orders to extract microbe and disease features from different networks and views. Given that the embedding features of microbe and disease from different views possess varying importance, a multi-scale feature fusion mechanism is employed to learn their interaction information, thereby generating the final feature of microbes and diseases. Finally, an inner product decoder is used to reconstruct the microbe-disease association matrix. Compared with five state-of-the-art methods on the HMDAD and Disbiome datasets, the results of 5-fold cross-validations show that M HOGAT achieves the best performance. Furthermore, case studies on asthma and obesity confirm the effectiveness of M HOGAT in identifying potential disease-related microbes.
AbstractList Numerous scientific studies have found a link between diverse microorganisms in the human body and complex human diseases. Because traditional experimental approaches are time-consuming and expensive, using computational methods to identify microbes correlated with diseases is critical. In this paper, a new microbe-disease association prediction model is proposed that combines a multi-view multi-modal network and a multi-scale feature fusion mechanism, called M HOGAT. Firstly, a microbe-disease association network and multiple similarity views are constructed based on multi-source information. Then, consider that neighbor information from disparate orders might be more adept at learning node representations. Consequently, the higher-order graph attention network (HOGAT) is devised to aggregate neighbor information from disparate orders to extract microbe and disease features from different networks and views. Given that the embedding features of microbe and disease from different views possess varying importance, a multi-scale feature fusion mechanism is employed to learn their interaction information, thereby generating the final feature of microbes and diseases. Finally, an inner product decoder is used to reconstruct the microbe-disease association matrix. Compared with five state-of-the-art methods on the HMDAD and Disbiome datasets, the results of 5-fold cross-validations show that M HOGAT achieves the best performance. Furthermore, case studies on asthma and obesity confirm the effectiveness of M HOGAT in identifying potential disease-related microbes.
Author Li, Feng
Wang, Shuang
Gao, Ying-Lian
Wang, Juan
Liu, Jin-Xing
Author_xml – sequence: 1
  givenname: Shuang
  orcidid: 0009-0000-6861-9764
  surname: Wang
  fullname: Wang, Shuang
  organization: School of Computer Science, Qufu Normal University, Rizhao, Shandong, China
– sequence: 2
  givenname: Jin-Xing
  orcidid: 0000-0001-6104-2149
  surname: Liu
  fullname: Liu, Jin-Xing
  organization: School of Health and Life Sciences, University of Health and Rehabilitation Sciences, Qingdao, Shandong, China
– sequence: 3
  givenname: Feng
  orcidid: 0000-0002-5556-3789
  surname: Li
  fullname: Li, Feng
  organization: School of Computer Science, Qufu Normal University, Rizhao, Shandong, China
– sequence: 4
  givenname: Juan
  orcidid: 0000-0003-3934-0435
  surname: Wang
  fullname: Wang, Juan
  organization: School of Computer Science, Qufu Normal University, Rizhao, Shandong, China
– sequence: 5
  givenname: Ying-Lian
  orcidid: 0000-0003-0483-5622
  surname: Gao
  fullname: Gao, Ying-Lian
  organization: Qufu Normal University Library, Qufu Normal University, Rizhao, Shandong, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/39012741$$D View this record in MEDLINE/PubMed
BookMark eNp1kE1OwzAQhS1URKH0AGyQL5DisaP8sAsFmqKGIlHYWo7tUEPaVHaqigV3J2nTDRKzmafRe6OZ7wL11tVaI3QFZARA4punu3Q6ooT6I-bTGGh0gs4pBJFHKYl6Rw2x30dD5z5JU1EzioMz1GcxARr6cI5-MsxwOp8ki1uc4Gxb1sZ7N3rXyaxSouz0qxSlxqn5WHpzq7TFEys2S5zUtV7XplrjZ13vKvuFi8rizEhb5dq7N04Lp3HiXCWN2PterFZGtvISnRaidHrY9QF6e3xYjFNvNp9Mx8nMkwAMPKqIDGTAYuUDDVhECl_4WoYxVTQvpAIRspCRMNe-IiyiucjDnGoaKFDNz4wN0PVh72abr7TiG2tWwn7zI4fGEB4MzdXOWV1waer9tbUVpuRAeAudt9B5C5130Jsk_Ekel_-f-QVp6oJE
CitedBy_id crossref_primary_10_3389_fphar_2025_1578140
Cites_doi 10.1109/TCBB.2020.3018138
10.1109/TCBB.2019.2907626
10.1109/CVPR.2018.00109
10.1109/TCBB.2020.2986459
10.1183/09031936.00087906
10.1093/bib/bbaa436
10.1007/s12275-018-8032-4
10.1039/C9FO02554E
10.1056/NEJMoa021423
10.4167/jbv.2013.43.4.270
10.4168/aair.2010.2.3.199
10.1093/bioinformatics/btw715
10.3855/jidc.6035
10.1093/bib/bbae167
10.1186/s12866-018-1257-x
10.1109/JBHI.2022.3229473
10.1093/database/baaa050
10.1093/bib/bbz057
10.1109/TCYB.2020.3026652
10.1093/bib/bbad255
10.1109/TCBB.2022.3228617
10.1007/s00253-013-5346-3
10.3390/ijms20153648
10.3389/fgene.2021.754425
10.1093/bib/bbac159
10.1056/nejmoa1614362
10.1109/JBHI.2021.3130110
10.1016/j.csbj.2022.12.053
10.1093/bib/bbw005
10.3390/cells8091012
10.1038/nrc3610
10.1186/s12967-021-02732-6
10.1109/TCBB.2021.3082183
10.1109/JBHI.2023.3272154
10.1093/bib/bbaa146
10.1093/bib/bbaa157
10.1016/j.jaci.2014.11.011
10.1109/TCBB.2018.2883041
10.1111/j.1398-9995.2004.00526.x
10.1186/s12866-018-1197-5
10.1371/journal.pcbi.1005366
10.1093/bioinformatics/btl467
10.1111/jvim.12455
ContentType Journal Article
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
DOI 10.1109/JBHI.2024.3429128
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
DatabaseTitleList MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2168-2208
EndPage 6267
ExternalDocumentID 39012741
10_1109_JBHI_2024_3429128
Genre Research Support, Non-U.S. Gov't
Journal Article
GroupedDBID 0R~
4.4
6IF
6IH
6IK
97E
AAJGR
AASAJ
AAWTH
AAYXX
ABQJQ
ABVLG
ACIWK
ACPRK
AENEX
AFRAH
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CITATION
EBS
EJD
HZ~
IFIPE
IPLJI
JAVBF
M43
O9-
OCL
PQQKQ
RIA
RIE
RNS
AARMG
ABAZT
CGR
CUY
CVF
ECM
EIF
NPM
RIG
ID FETCH-LOGICAL-c1131-2d0c6c639d4126380f4a4ec792d2bfcd1a737307be4d0382bab7b2e26d1d81633
ISSN 2168-2194
IngestDate Mon Jul 21 06:01:01 EDT 2025
Sat Nov 29 04:18:38 EST 2025
Tue Nov 18 22:38:04 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 10
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c1131-2d0c6c639d4126380f4a4ec792d2bfcd1a737307be4d0382bab7b2e26d1d81633
ORCID 0000-0003-0483-5622
0000-0003-3934-0435
0000-0002-5556-3789
0009-0000-6861-9764
0000-0001-6104-2149
PMID 39012741
PageCount 9
ParticipantIDs pubmed_primary_39012741
crossref_citationtrail_10_1109_JBHI_2024_3429128
crossref_primary_10_1109_JBHI_2024_3429128
PublicationCentury 2000
PublicationDate 2024-10-00
PublicationDateYYYYMMDD 2024-10-01
PublicationDate_xml – month: 10
  year: 2024
  text: 2024-10-00
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle IEEE journal of biomedical and health informatics
PublicationTitleAlternate IEEE J Biomed Health Inform
PublicationYear 2024
References ref13
ref35
ref12
ref34
ref15
ref37
ref14
ref36
ref31
ref30
ref11
ref33
ref10
ref32
ref2
ref1
ref39
ref16
ref38
ref19
ref18
Velikovi (ref17)
ref24
ref23
ref45
ref26
ref25
ref20
ref42
ref41
ref22
ref44
ref21
ref43
ref28
ref27
ref8
ref7
ref9
ref4
ref3
ref6
ref5
ref40
Abu-El-Haija (ref29)
References_xml – ident: ref14
  doi: 10.1109/TCBB.2020.3018138
– ident: ref33
  doi: 10.1109/TCBB.2019.2907626
– ident: ref31
  doi: 10.1109/CVPR.2018.00109
– ident: ref16
  doi: 10.1109/TCBB.2020.2986459
– ident: ref4
  doi: 10.1183/09031936.00087906
– ident: ref2
  doi: 10.1093/bib/bbaa436
– ident: ref3
  doi: 10.1007/s12275-018-8032-4
– ident: ref7
  doi: 10.1039/C9FO02554E
– ident: ref42
  doi: 10.1056/NEJMoa021423
– ident: ref39
  doi: 10.4167/jbv.2013.43.4.270
– ident: ref40
  doi: 10.4168/aair.2010.2.3.199
– ident: ref9
  doi: 10.1093/bioinformatics/btw715
– ident: ref45
  doi: 10.3855/jidc.6035
– ident: ref30
  doi: 10.1093/bib/bbae167
– ident: ref41
  doi: 10.1186/s12866-018-1257-x
– ident: ref11
  doi: 10.1109/JBHI.2022.3229473
– ident: ref1
  doi: 10.1093/database/baaa050
– ident: ref25
  doi: 10.1093/bib/bbz057
– ident: ref10
  doi: 10.1109/TCYB.2020.3026652
– ident: ref15
  doi: 10.1093/bib/bbad255
– start-page: 21
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref29
  article-title: Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing
– ident: ref32
  doi: 10.1109/TCBB.2022.3228617
– ident: ref6
  doi: 10.1007/s00253-013-5346-3
– volume-title: Proc. 6th Int. Conf. Learn. Representations
  ident: ref17
  article-title: Graph attention networks
– ident: ref18
  doi: 10.3390/ijms20153648
– ident: ref13
  doi: 10.3389/fgene.2021.754425
– ident: ref28
  doi: 10.1093/bib/bbac159
– ident: ref43
  doi: 10.1056/nejmoa1614362
– ident: ref21
  doi: 10.1109/JBHI.2021.3130110
– ident: ref27
  doi: 10.1016/j.csbj.2022.12.053
– ident: ref22
  doi: 10.1093/bib/bbw005
– ident: ref19
  doi: 10.3390/cells8091012
– ident: ref5
  doi: 10.1038/nrc3610
– ident: ref34
  doi: 10.1186/s12967-021-02732-6
– ident: ref12
  doi: 10.1109/TCBB.2021.3082183
– ident: ref20
  doi: 10.1109/JBHI.2023.3272154
– ident: ref36
  doi: 10.1093/bib/bbaa146
– ident: ref8
  doi: 10.1093/bib/bbaa157
– ident: ref38
  doi: 10.1016/j.jaci.2014.11.011
– ident: ref35
  doi: 10.1109/TCBB.2018.2883041
– ident: ref37
  doi: 10.1111/j.1398-9995.2004.00526.x
– ident: ref23
  doi: 10.1186/s12866-018-1197-5
– ident: ref26
  doi: 10.1371/journal.pcbi.1005366
– ident: ref24
  doi: 10.1093/bioinformatics/btl467
– ident: ref44
  doi: 10.1111/jvim.12455
SSID ssj0000816896
Score 2.4182897
Snippet Numerous scientific studies have found a link between diverse microorganisms in the human body and complex human diseases. Because traditional experimental...
SourceID pubmed
crossref
SourceType Index Database
Enrichment Source
StartPage 6259
SubjectTerms Algorithms
Computational Biology - methods
Humans
Title M 3 HOGAT: A Multi-View Multi-Modal Multi-Scale High-Order Graph Attention Network for Microbe-Disease Association Prediction
URI https://www.ncbi.nlm.nih.gov/pubmed/39012741
Volume 28
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 2168-2208
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816896
  issn: 2168-2194
  databaseCode: RIE
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Jb9QwFLaGghCXirW0LPKBE1GGxM7ECbdh61CRKRJDmVuU2I6IVKVVyVS98Df5PTwv43jKInrgYllW8pTJ943fe85bEHpWk0x1PWpCmcOQ5IyElZjQMFWn-rwSqdDFdI4-sPk8Wy7zj6PRj3UuzPkx67rs4iI__a9QwxqArVJnrwC3EwoLMAfQYQTYYfwn4IuABrPD_enCJJ3rDNvwSOWnmGlxIlQ-rp5_AoSkjvUID1UNzmBf1a8Opn1voyDnJkpcByMWKnavluEb803HR1ZFcoiWO5Cttas8Sb82hcn1d_UJTA5mYGu39l7c_Zf1KfbXVWVVqwoaaleadG0XLlt_WVvgclhZ336wsty3xxokcQFydvcjcQq4xqYD8lh6ayTK_O2bZD5NI28zVq6dp9jBdWO_Vxq65urBq9n7sXqSMQUdHVuxGwW6LylOF86oHakoL5WIUokorYhr6Dphkzw3eYXu7E83O9Gt49yvtB_cQcqLXx5kw2TacH60EbS4jbat94KnhnV30Eh2d9HNwsZn3EPfC0yxJt9LPMUD9bBHPexRDw_Uw5p62FEPW-phIAe-RD3sUQ8P1LuPPr97u3g9C22Dj5DHMY1DIiKecrCRRRITUARRk1SJ5CwngtQNF3HFKGggVstERDQjdVWzmkiSiljAK6T0AdrqTjr5EOE0AbsWdAunUiQNuD0TPklkzbOGsJjxahdF63dYclv9XjVhOS7_CN4ueu5uOTWlX_528Y4Bxl2qDhNVbai9q4h5hG4Nf4bHaKs_W8kn6AY_79tvZ081i34CRgCm-Q
linkProvider IEEE
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=M+3+HOGAT%3A+A+Multi-View+Multi-Modal+Multi-Scale+High-Order+Graph+Attention+Network+for+Microbe-Disease+Association+Prediction&rft.jtitle=IEEE+journal+of+biomedical+and+health+informatics&rft.au=Wang%2C+Shuang&rft.au=Liu%2C+Jin-Xing&rft.au=Li%2C+Feng&rft.au=Wang%2C+Juan&rft.date=2024-10-01&rft.issn=2168-2194&rft.eissn=2168-2208&rft.volume=28&rft.issue=10&rft.spage=6259&rft.epage=6267&rft_id=info:doi/10.1109%2FJBHI.2024.3429128&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JBHI_2024_3429128
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2168-2194&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2168-2194&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2168-2194&client=summon