Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/149665
Title: Exploring genetic patterns in cancer transcriptomes: an unsupervised learning approach
Author: Toledo Iglesias, Eloísa  
Tutor: Rebrij, Romina  
Others: Ventura, Carles  
Abstract: Cancer is a complex and heterogeneous disease that represents a major global public health concern due to its escalating casualty rates and the absence of effective treatments. RNA mutations and modifications have been shown to play a crucial role in the development and progression of tumors. In this context, the molecular study of the cancer biology is of paramount importance, due to its relevance in classifying and comparing multiple cancer types and subtypes, allowing the development of more personalized therapies and increasing the treatment success. However, although RNA-seq technologies, such as Illumina Hiseq sequencing, have revolutionized medical research, they involve the analysis of complex and extensive amounts of data. Unsupervised machine learning techniques can be of unparalleled help in creating novel cancer classifications, surpassing the limitations of traditional techniques. In the present work, different dimensionality reduction approaches, such as PCA and UMAP, and several unsupervised algorithms, including partitioning, density based, hierarchical and model based algorithms, were tested in order to identify types and/or subtypes of cancer according to their gene expression. Several algorithms, namely, k-means, PAM, CLARA and agglomerative hierarchical algorithms using the UMAP technique for dimensional reduction, demonstrated the ability to classify gene expression data with a high degree of accuracy forming well separated clusters. These results confirm the potential of these algorithms to contribute to the fight against cancer.
Keywords: Cancer transcriptome
Unsupervised learning
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 16-Jan-2024
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 
etoledoiFMDP0124report.pdfReport of TFM3,74 MBAdobe PDFThumbnail
View/Open
Share:
Export:
View statistics

This item is licensed under aCreative Commons License Creative Commons