Microbe-disease associations prediction by graph regularized non-negative matrix factorization with L 2 , 1 $$ {L}_{2,1} $$ norm regularization terms

Microbes are involved in a wide range of biological processes and are closely associated with disease. Inferring potential disease-associated microbes as the biomarkers or drug targets may help prevent, diagnose and treat complex human diseases. However, biological experiments are time-consuming and...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of cellular and molecular medicine Jg. 28; H. 17; S. e18553
Hauptverfasser: Chen, Ziwei, Zhang, Liangzhe, Li, Jingyi, Chen, Hang
Format: Journal Article
Sprache:Englisch
Veröffentlicht: England 01.09.2024
Schlagworte:
ISSN:1582-4934, 1582-4934
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Microbes are involved in a wide range of biological processes and are closely associated with disease. Inferring potential disease-associated microbes as the biomarkers or drug targets may help prevent, diagnose and treat complex human diseases. However, biological experiments are time-consuming and expensive. In this study, we introduced a new method called iPALM-GLMF, which modelled microbe-disease association prediction as a problem of non-negative matrix factorization with graph dual regularization terms and norm regularization terms. The graph dual regularization terms were used to capture potential features in the microbe and disease space, and the norm regularization terms were used to ensure the sparsity of the feature matrices obtained from the non-negative matrix factorization and to improve the interpretability. To solve the model, iPALM-GLMF used a non-negative double singular value decomposition to initialize the matrix factorization and adopted an inertial Proximal Alternating Linear Minimization iterative process to obtain the final matrix factorization results. As a result, iPALM-GLMF performed better than other existing methods in leave-one-out cross-validation and fivefold cross-validation. In addition, case studies of different diseases demonstrated that iPALM-GLMF could effectively predict potential microbial-disease associations. iPALM-GLMF is publicly available at https://github.com/LiangzheZhang/iPALM-GLMF.
AbstractList Microbes are involved in a wide range of biological processes and are closely associated with disease. Inferring potential disease-associated microbes as the biomarkers or drug targets may help prevent, diagnose and treat complex human diseases. However, biological experiments are time-consuming and expensive. In this study, we introduced a new method called iPALM-GLMF, which modelled microbe-disease association prediction as a problem of non-negative matrix factorization with graph dual regularization terms and norm regularization terms. The graph dual regularization terms were used to capture potential features in the microbe and disease space, and the norm regularization terms were used to ensure the sparsity of the feature matrices obtained from the non-negative matrix factorization and to improve the interpretability. To solve the model, iPALM-GLMF used a non-negative double singular value decomposition to initialize the matrix factorization and adopted an inertial Proximal Alternating Linear Minimization iterative process to obtain the final matrix factorization results. As a result, iPALM-GLMF performed better than other existing methods in leave-one-out cross-validation and fivefold cross-validation. In addition, case studies of different diseases demonstrated that iPALM-GLMF could effectively predict potential microbial-disease associations. iPALM-GLMF is publicly available at https://github.com/LiangzheZhang/iPALM-GLMF.
Microbes are involved in a wide range of biological processes and are closely associated with disease. Inferring potential disease-associated microbes as the biomarkers or drug targets may help prevent, diagnose and treat complex human diseases. However, biological experiments are time-consuming and expensive. In this study, we introduced a new method called iPALM-GLMF, which modelled microbe-disease association prediction as a problem of non-negative matrix factorization with graph dual regularization terms and L 2 , 1 $$ {L}_{2,1} $$ norm regularization terms. The graph dual regularization terms were used to capture potential features in the microbe and disease space, and the L 2 , 1 $$ {L}_{2,1} $$ norm regularization terms were used to ensure the sparsity of the feature matrices obtained from the non-negative matrix factorization and to improve the interpretability. To solve the model, iPALM-GLMF used a non-negative double singular value decomposition to initialize the matrix factorization and adopted an inertial Proximal Alternating Linear Minimization iterative process to obtain the final matrix factorization results. As a result, iPALM-GLMF performed better than other existing methods in leave-one-out cross-validation and fivefold cross-validation. In addition, case studies of different diseases demonstrated that iPALM-GLMF could effectively predict potential microbial-disease associations. iPALM-GLMF is publicly available at https://github.com/LiangzheZhang/iPALM-GLMF.Microbes are involved in a wide range of biological processes and are closely associated with disease. Inferring potential disease-associated microbes as the biomarkers or drug targets may help prevent, diagnose and treat complex human diseases. However, biological experiments are time-consuming and expensive. In this study, we introduced a new method called iPALM-GLMF, which modelled microbe-disease association prediction as a problem of non-negative matrix factorization with graph dual regularization terms and L 2 , 1 $$ {L}_{2,1} $$ norm regularization terms. The graph dual regularization terms were used to capture potential features in the microbe and disease space, and the L 2 , 1 $$ {L}_{2,1} $$ norm regularization terms were used to ensure the sparsity of the feature matrices obtained from the non-negative matrix factorization and to improve the interpretability. To solve the model, iPALM-GLMF used a non-negative double singular value decomposition to initialize the matrix factorization and adopted an inertial Proximal Alternating Linear Minimization iterative process to obtain the final matrix factorization results. As a result, iPALM-GLMF performed better than other existing methods in leave-one-out cross-validation and fivefold cross-validation. In addition, case studies of different diseases demonstrated that iPALM-GLMF could effectively predict potential microbial-disease associations. iPALM-GLMF is publicly available at https://github.com/LiangzheZhang/iPALM-GLMF.
Author Chen, Hang
Li, Jingyi
Chen, Ziwei
Zhang, Liangzhe
Author_xml – sequence: 1
  givenname: Ziwei
  surname: Chen
  fullname: Chen, Ziwei
  organization: School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China
– sequence: 2
  givenname: Liangzhe
  orcidid: 0009-0005-6618-7765
  surname: Zhang
  fullname: Zhang, Liangzhe
  organization: School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China
– sequence: 3
  givenname: Jingyi
  surname: Li
  fullname: Li, Jingyi
  organization: School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China
– sequence: 4
  givenname: Hang
  surname: Chen
  fullname: Chen, Hang
  organization: School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/39239860$$D View this record in MEDLINE/PubMed
BookMark eNpNkMtOwzAQRS1URB-w4QOQF12waEoc5-EsUcVLCmLTfWQ7k9ZVHQc7AUrVz-B_SWkRjEaaO5o7R6MZol5lKkDokvhT0sXNSmo9JSyK6AkakIgFXpjSsPdP99HQuZXv05jQ9Az1aRrQlMX-AH09K2mNAK9QDrgDzJ0zUvFGmcrh2kKh5F5jscELy-sltrBo19yqTyhwd4hXwaJzvwHWvLHqA5dcNqYb_yDwu2qWOMMBnmCCx2O8zXb5NpiQ3b6pjNV_vMNCA1a7c3Ra8rWDi2Mdofn93Xz26GUvD0-z28yro9j3SFAkhYwTIUiUBBBxQUrww31GAS_DiBEGYRxDyGRZpsAFZSItRAJSlkzGdISuD9jamtcWXJNr5SSs17wC07qcEp8ENPEp66xXR2srNBR5bZXmdpP_fpJ-AzPqeP8
ContentType Journal Article
Copyright 2024 The Author(s). Journal of Cellular and Molecular Medicine published by Foundation for Cellular and Molecular Medicine and John Wiley & Sons Ltd.
Copyright_xml – notice: 2024 The Author(s). Journal of Cellular and Molecular Medicine published by Foundation for Cellular and Molecular Medicine and John Wiley & Sons Ltd.
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1111/jcmm.18553
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Biology
EISSN 1582-4934
ExternalDocumentID 39239860
Genre Journal Article
GroupedDBID ---
0R~
1OC
24P
29K
31~
36B
4.4
53G
5GY
5VS
7X7
8-0
8-1
88E
88I
8AO
8FE
8FH
8FI
8FJ
8R4
8R5
AAMMB
AAZKR
ABJNI
ABUWG
ACCMX
ACGFS
ACGOD
ACXQS
ADBBV
ADKYN
ADPDF
ADRAZ
ADZMN
AEFGJ
AENEX
AFBPY
AFKRA
AFZJQ
AGXDD
AHMBA
AIDQK
AIDYY
ALAGY
ALIPV
ALMA_UNASSIGNED_HOLDINGS
ALUQN
AOIJS
AVUZU
AZQEC
BAWUL
BBNVY
BCNDV
BENPR
BHPHI
BPHCQ
BVXVI
CAG
CCPQU
CGR
COF
CS3
CUY
CVF
D-9
D-I
DIK
DU5
DWQXO
E3Z
EBD
EBS
ECM
EIF
EJD
EMB
EMOBN
F5P
FYUFA
GNUQQ
GODZA
GROUPED_DOAJ
HCIFZ
HMCUK
HYE
HZ~
IAO
IHR
ITC
KQ8
LH4
LK8
LW6
M1P
M2P
M48
M7P
NPM
O9-
OIG
OK1
OVD
OVEED
PHGZM
PHGZT
PIMPY
PJZUB
PPXIY
PQGLB
PQQKQ
PROAC
PSQYO
Q2X
RNS
ROL
RPM
SV3
TEORI
UKHRP
7X8
AFFHD
WIN
ID FETCH-LOGICAL-p560-12d7dc67bb1572e5ab1fe04e04e52af45818e466e48cff9eab38b9db7eccf8c63
ISSN 1582-4934
IngestDate Sun Nov 09 11:52:55 EST 2025
Mon Jul 21 06:00:43 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 17
Keywords graph dual regularization
microbe–disease association
inertial proximal alternating linearized minimization
norm regularization
non‐negative matrix factorization
Language English
License 2024 The Author(s). Journal of Cellular and Molecular Medicine published by Foundation for Cellular and Molecular Medicine and John Wiley & Sons Ltd.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-p560-12d7dc67bb1572e5ab1fe04e04e52af45818e466e48cff9eab38b9db7eccf8c63
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0009-0005-6618-7765
PMID 39239860
PQID 3101237038
PQPubID 23479
ParticipantIDs proquest_miscellaneous_3101237038
pubmed_primary_39239860
PublicationCentury 2000
PublicationDate 2024-Sep
20240901
PublicationDateYYYYMMDD 2024-09-01
PublicationDate_xml – month: 09
  year: 2024
  text: 2024-Sep
PublicationDecade 2020
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle Journal of cellular and molecular medicine
PublicationTitleAlternate J Cell Mol Med
PublicationYear 2024
SSID ssj0036139
Score 2.426933
Snippet Microbes are involved in a wide range of biological processes and are closely associated with disease. Inferring potential disease-associated microbes as the...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage e18553
SubjectTerms Algorithms
Computational Biology - methods
Humans
Microbiota
Title Microbe-disease associations prediction by graph regularized non-negative matrix factorization with L 2 , 1 $$ {L}_{2,1} $$ norm regularization terms
URI https://www.ncbi.nlm.nih.gov/pubmed/39239860
https://www.proquest.com/docview/3101237038
Volume 28
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1582-4934
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0036139
  issn: 1582-4934
  databaseCode: DOA
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVPQU
  databaseName: Biological Science Database
  customDbUrl:
  eissn: 1582-4934
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0036139
  issn: 1582-4934
  databaseCode: M7P
  dateStart: 20000701
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/biologicalscijournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1582-4934
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0036139
  issn: 1582-4934
  databaseCode: BENPR
  dateStart: 20000701
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Health & Medical Collection
  customDbUrl:
  eissn: 1582-4934
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0036139
  issn: 1582-4934
  databaseCode: 7X7
  dateStart: 20000701
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 1582-4934
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0036139
  issn: 1582-4934
  databaseCode: PIMPY
  dateStart: 20000701
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Science Database
  customDbUrl:
  eissn: 1582-4934
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0036139
  issn: 1582-4934
  databaseCode: M2P
  dateStart: 20000701
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/sciencejournals
  providerName: ProQuest
– providerCode: PRVWIB
  databaseName: Wiley Online Library Free Content
  customDbUrl:
  eissn: 1582-4934
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0036139
  issn: 1582-4934
  databaseCode: WIN
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
– providerCode: PRVWIB
  databaseName: Wiley Online Library Open Access
  customDbUrl:
  eissn: 1582-4934
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0036139
  issn: 1582-4934
  databaseCode: 24P
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9owFLZY2aa-TLuvuyBPok80E3Euth_XrlM3BYQmHtheIjs4XaSRImg7aNWfsV-1P7XjS4CCkLaHSdEhxMFB-T4dHx8fn4NQUwwZzfSaIeFMeDD_ij0hIuEJkge0LSPJ2tIUm6DdLhsMeK9W-13thbn8QcuSzWZ8_F-hhmsAtt46-w9wLzqFC3AOoIME2EH-FfAdHWInleeWXlpiCcBUpwQYFrY6ONidJlt1a2LK0U-KKx0JcFZ6pTq12cBHOn3_zJXkcfs1reM2aZGWBscHGcLR2qeHyT79kMIngQYfzqumEqzi5TNsJ3o8mG6xi_VSgomN1S79UVW9dyMI4MhtK_lW_FTFhvs7AdafXn1f3J2YoIXPME7Pi_UeToQbvZ3zg4SL6C4Yu5zChhlCyJ1D1Gl0wlaZS1f0swLzxCYn3jZ0ZKPRu42bAOHxyPAFzMmAM1sCYS1Rd9V0B9UJjbhWsXSwmP0HYDdxlx_XhJItHrSL7lc_3T7NMeZO_yF64PDA7y2_HqGaKh-je7Zy6fwJ-rXGMrzKMrxkGZZzbFiGV1iGV1mGLcvwLZZhzTKcYIIPsI-bTXyd3KTX5MC_0V80o_BtRmHDqKeo__G4f3TiuQof3hgsbc8nQzrMYiqlH1GiIiH9XLVDfURE5GEE1qQK41iFLMtzroQMmOQ6IXiW5SyLg2doB_6xeoGwVDQSw5BkMIUIc6U4oTozZAz98zDKoz30tnqzKShQTWVRqrOLaRroDHeglwK2h57bV56ObaaXtMLl5daWV2h3ycvXaOd8cqHeoLvZ5XkxnTQMA4xkDVQ_PO72vjSM1wdkh_S0pCDrvU-d3tc_chafwA
linkProvider ProQuest
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=Microbe-disease+associations+prediction+by+graph+regularized+non-negative+matrix+factorization+with+L+2+%2C+1+%24%24+%7BL%7D_%7B2%2C1%7D+%24%24+norm+regularization+terms&rft.jtitle=Journal+of+cellular+and+molecular+medicine&rft.au=Chen%2C+Ziwei&rft.au=Zhang%2C+Liangzhe&rft.au=Li%2C+Jingyi&rft.au=Chen%2C+Hang&rft.date=2024-09-01&rft.eissn=1582-4934&rft.volume=28&rft.issue=17&rft.spage=e18553&rft_id=info:doi/10.1111%2Fjcmm.18553&rft_id=info%3Apmid%2F39239860&rft.externalDocID=39239860
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1582-4934&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1582-4934&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1582-4934&client=summon