View in EDS

NCAE: data-driven representations using a deep network-coherent DNA methylation autoencoder identify robust disease and risk factor signatures

Saved in:
Bibliographic Details
Title: NCAE: data-driven representations using a deep network-coherent DNA methylation autoencoder identify robust disease and risk factor signatures
Authors: Martinez-Enguita, David, Dwivedi, Sanjiv K., Jörnsten, Rebecka, 1971, Gustafsson, Mika
Source: Briefings in Bioinformatics. 24(5)
Subject Terms: DNA methylation, deep learning, autoencoders, biomarkers, systems medicine, transfer learning
Description: Precision medicine relies on the identification of robust disease and risk factor signatures from omics data. However, current knowledge-driven approaches may overlook novel or unexpected phenomena due to the inherent biases in biological knowledge. In this study, we present a data-driven signature discovery workflow for DNA methylation analysis utilizing network-coherent autoencoders (NCAEs) with biologically relevant latent embeddings. First, we explored the architecture space of autoencoders trained on a large-scale pan-tissue compendium (n = 75 272) of human epigenome-wide association studies. We observed the emergence of co-localized patterns in the deep autoencoder latent space representations that corresponded to biological network modules. We determined the NCAE configuration with the strongest co-localization and centrality signals in the human protein interactome. Leveraging the NCAE embeddings, we then trained interpretable deep neural networks for risk factor (aging, smoking) and disease (systemic lupus erythematosus) prediction and classification tasks. Remarkably, our NCAE embedding-based models outperformed existing predictors, revealing novel DNA methylation signatures enriched in gene sets and pathways associated with the studied condition in each case. Our data-driven biomarker discovery workflow provides a generally applicable pipeline to capture relevant risk factor and disease information. By surpassing the limitations of knowledge-driven methods, our approach enhances the understanding of complex epigenetic processes, facilitating the development of more effective diagnostic and therapeutic strategies.
File Description: electronic
Access URL: https://research.chalmers.se/publication/537413
https://research.chalmers.se/publication/537413/file/537413_Fulltext.pdf
Database: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://research.chalmers.se/publication/537413#
    Name: EDS - SwePub (s4221598)
    Category: fullText
    Text: View record in SwePub
  – Url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=search&db=pmc&term=1467-5463[TA]+AND+[PG]+AND+2023[PDAT]
    Name: FREE - PubMed Central (ISSN based link)
    Category: fullText
    Text: Full Text
    Icon: https://imageserver.ebscohost.com/NetImages/iconPdf.gif
    MouseOverText: Check this PubMed for the article full text.
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edsswe&genre=article&issn=14675463&ISBN=&volume=24&issue=5&date=20230101&spage=&pages=&title=Briefings in Bioinformatics&atitle=NCAE%3A%20data-driven%20representations%20using%20a%20deep%20network-coherent%20DNA%20methylation%20autoencoder%20identify%20robust%20disease%20and%20risk%20factor%20signatures&aulast=Martinez-Enguita%2C%20David&id=DOI:10.1093/bib/bbad293
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Martinez-Enguita%20D
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsswe
DbLabel: SwePub
An: edsswe.oai.research.chalmers.se.b08e55e7.e74b.4341.a2f8.c092aea1f10c
RelevancyScore: 984
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 983.779541015625
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: NCAE: data-driven representations using a deep network-coherent DNA methylation autoencoder identify robust disease and risk factor signatures
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Martinez-Enguita%2C+David%22">Martinez-Enguita, David</searchLink><br /><searchLink fieldCode="AR" term="%22Dwivedi%2C+Sanjiv+K%2E%22">Dwivedi, Sanjiv K.</searchLink><br /><searchLink fieldCode="AR" term="%22Jörnsten%2C+Rebecka%22">Jörnsten, Rebecka</searchLink>, 1971<br /><searchLink fieldCode="AR" term="%22Gustafsson%2C+Mika%22">Gustafsson, Mika</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>Briefings in Bioinformatics</i>. 24(5)
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22DNA+methylation%22">DNA methylation</searchLink><br /><searchLink fieldCode="DE" term="%22deep+learning%22">deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22autoencoders%22">autoencoders</searchLink><br /><searchLink fieldCode="DE" term="%22biomarkers%22">biomarkers</searchLink><br /><searchLink fieldCode="DE" term="%22systems+medicine%22">systems medicine</searchLink><br /><searchLink fieldCode="DE" term="%22transfer+learning%22">transfer learning</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Precision medicine relies on the identification of robust disease and risk factor signatures from omics data. However, current knowledge-driven approaches may overlook novel or unexpected phenomena due to the inherent biases in biological knowledge. In this study, we present a data-driven signature discovery workflow for DNA methylation analysis utilizing network-coherent autoencoders (NCAEs) with biologically relevant latent embeddings. First, we explored the architecture space of autoencoders trained on a large-scale pan-tissue compendium (n = 75 272) of human epigenome-wide association studies. We observed the emergence of co-localized patterns in the deep autoencoder latent space representations that corresponded to biological network modules. We determined the NCAE configuration with the strongest co-localization and centrality signals in the human protein interactome. Leveraging the NCAE embeddings, we then trained interpretable deep neural networks for risk factor (aging, smoking) and disease (systemic lupus erythematosus) prediction and classification tasks. Remarkably, our NCAE embedding-based models outperformed existing predictors, revealing novel DNA methylation signatures enriched in gene sets and pathways associated with the studied condition in each case. Our data-driven biomarker discovery workflow provides a generally applicable pipeline to capture relevant risk factor and disease information. By surpassing the limitations of knowledge-driven methods, our approach enhances the understanding of complex epigenetic processes, facilitating the development of more effective diagnostic and therapeutic strategies.
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/537413" linkWindow="_blank">https://research.chalmers.se/publication/537413</link><br /><link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/537413/file/537413_Fulltext.pdf" linkWindow="_blank">https://research.chalmers.se/publication/537413/file/537413_Fulltext.pdf</link>
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.research.chalmers.se.b08e55e7.e74b.4341.a2f8.c092aea1f10c
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1093/bib/bbad293
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: DNA methylation
        Type: general
      – SubjectFull: deep learning
        Type: general
      – SubjectFull: autoencoders
        Type: general
      – SubjectFull: biomarkers
        Type: general
      – SubjectFull: systems medicine
        Type: general
      – SubjectFull: transfer learning
        Type: general
    Titles:
      – TitleFull: NCAE: data-driven representations using a deep network-coherent DNA methylation autoencoder identify robust disease and risk factor signatures
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Martinez-Enguita, David
      – PersonEntity:
          Name:
            NameFull: Dwivedi, Sanjiv K.
      – PersonEntity:
          Name:
            NameFull: Jörnsten, Rebecka
      – PersonEntity:
          Name:
            NameFull: Gustafsson, Mika
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-print
              Value: 14675463
            – Type: issn-print
              Value: 14774054
            – Type: issn-locals
              Value: SWEPUB_FREE
            – Type: issn-locals
              Value: CTH_SWEPUB
          Numbering:
            – Type: volume
              Value: 24
            – Type: issue
              Value: 5
          Titles:
            – TitleFull: Briefings in Bioinformatics
              Type: main
ResultId 1