Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/98846
Title: Elaboración de modelos predictivos con datos multimodales
Author: Gonzalo Sanz, Ricardo  
Tutor: Sánchez-Pla, Alex  
Abstract: Traditionally, the analysis of the omic data has been carried out individually, drawing conclusions only using the single omics analyzed. Lately, it has been seen that the information provided by the different omics if used together, provides much more information than analyzing them separately. The method of integrating different omic data is not well established. The main objective of this work is to define a workflow for the integration of omic data. A data set that contains four types of data: analysis of gene expression, analysis of miRNA expression, analysis of cell populations and an extensive collection of clinical variables has been used in this work. In a first instance, each data set has been analyzed separately and the most significant variables in each case have been selected to be included in the subsequent integration workflow. DIABLO method implemented in the Bioconductor R package called mixOmics has been used. Among the results obtained, it is observed that the clinical variables selected are the ones that best separate the two experimental conditions present in the samples, followed by the miRNAs. A group of variables has been also identified from the different omics studied that are highly correlated with each other. Several networks have been created that relate these variables to each other. The created model classifies the samples of the test data set quite well.
Keywords: omic data analysis
omic data integration
personalized medicine
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 17-Jun-2019
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 
rgonzalosaTFM0619memoria.pdfMemoria del TFM1,97 MBAdobe PDFThumbnail
View/Open