Högskolan i Skövde

his.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Integrating autoencoder embeddings with deep learning for epigenomic insights into BMI prediction and exploring obesity-related biomarkers
University of Skövde, School of Bioscience.
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 30 credits / 45 HE creditsStudent thesis
Abstract [en]

Obesity, a complex multifactorial condition, poses significant global health challenges, necessitating precise prediction and management strategies. This study explores the integration of DNA methylation data into Body Mass Index (BMI) prediction models using advanced computational techniques. The primary aim is to enhance the precision of BMI predictions while uncovering novel insights into the epigenetic factors associated with obesity-related health risks. Through the utilization of a Deep Feedforward Neural Network (DFNN) model and backward feature selection method, DNA methylation patterns strongly associated with BMI are identified. The DFNN model exhibits moderate performance in BMI prediction, with R-squared values ranging from 0.36 to 0.77 across training, validation, and test datasets. Backward feature selection further refines the predictive accuracy, revealing an average R-squared value of 0.41 and highlighting the effectiveness of this approach in identifying relevant DNA methylation patterns. Fisher’s exact test uncovers significant associations between gene sets, elucidating potential regulatory relationships in obesity-related pathways. Gene ontology enrichment analysis underscores the involvement of lipid metabolism and cholesterol regulation in obesity pathogenesis. Ethical considerations regarding participant confidentiality and data privacy are meticulously addressed, ensuring adherence to ethical standards throughout the research process. In conclusion, this study underscores the promise of integrating DNA methylation data into BMI prediction models, offering novel avenues for personalized medicine and advancing our understanding of obesity-related health outcomes.

Place, publisher, year, edition, pages
2024. , p. 28
National Category
Bioinformatics and Computational Biology
Identifiers
URN: urn:nbn:se:his:diva-24349OAI: oai:DiVA.org:his-24349DiVA, id: diva2:1883608
External cooperation
Linköpings universitet
Subject / course
Systems Biology
Educational program
Systems Biology with specialization in Bioinformatics - Master's Programme
Supervisors
Examiners
Available from: 2024-07-11 Created: 2024-07-11 Last updated: 2025-02-07Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
School of Bioscience
Bioinformatics and Computational Biology

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 88 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf