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
A comparative analysis of multi-omics data for biomarker identification and pathway analysis in cancer research
University of Skövde, School of Bioscience.
2024 (English)Independent thesis Advanced level (degree of Master (One Year)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

The integration of multi-omics data across multiple cancer types, including Breast Invasive Carcinoma (BRCA), Lung Adenocarcinoma (LUAD) and Cervical Squamous Cell Carcinoma and Endocervical Adenocarcinoma (CESC) enriches with a better understanding of cancer biology. Three different types of data (mRNA, miRNA, and RPPA) for each cancer were integrated with the DIABLO and NOLAS methods. The study aimed to evaluate and compare the performance of both methods and study their strengths and limitations. The DIABLO model showed high specificity across datasets, having strong discrimination ability, though it had low sensitivity, which indicated difficulties of the model in the identification of tumor cases. Conversely, the NOLAS model showed a high robustness in handling data with noise and batch effects, which implied that the NOLAS model had better abilities for class separation. Both models had maintained moderate accuracy while making predictions for test data, and were effective in identifying potential biomarkers and relevant pathways. The DIABLO model selected a limited number of highly informative features, while the NOLAS model extracted a wide range of biological variations. Pathway analysis revealed the engagement of pathways related to the identified biomarkers by both models in cancer progression, such as "microRNAs in cancer" and "hedgehog signaling" for lung cancer and "epidermis development" for cervical cancer. The study showed both strengths and limitations of both models and suggested the need to improve the feature selection process and to solve issues with class imbalance to improve the prediction performance of both models. The research focused on improving multi-omics integration methods to contribute to cancer research and develop strategies for personalized medicine.

Place, publisher, year, edition, pages
2024. , p. 71
National Category
Bioinformatics (Computational Biology)
Identifiers
URN: urn:nbn:se:his:diva-24873OAI: oai:DiVA.org:his-24873DiVA, id: diva2:1933320
Subject / course
Bioinformatics
Educational program
Bioinformatics - Master’s Programme
Supervisors
Examiners
Available from: 2025-02-03 Created: 2025-01-31 Last updated: 2025-09-29Bibliographically approved

Open Access in DiVA

fulltext(3513 kB)219 downloads
File information
File name FULLTEXT01.pdfFile size 3513 kBChecksum SHA-512
48cbe3c49b68e759c97e901927a9f5aca2eb63ed15f8ca42c40e210144bfb2c0bb8e581897c4d97bd6c29b0151d3627a0f8a87ce9d2753df2b94c8997dbadae3
Type fulltextMimetype application/pdf

By organisation
School of Bioscience
Bioinformatics (Computational Biology)

Search outside of DiVA

GoogleGoogle Scholar
Total: 219 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 337 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