Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/109506
Title: Herramienta para analizar matrices de expresión génicas con machine learning
Author: Rodríguez Pérez, Domingo Javier
Tutor: Fernandez Hilario, Alberto  
Others: Adsuar Gómez, Antonio Jesús
Abstract: In the field of biomedical applications, it is as important to obtain high precision as to make the generated models explainable to clinical staff. For this reason, it is essential to apply intelligent techniques that are able to learn effectively in these scenarios. This time it is about creating software in R to provide a simple way to construct an explanatory analysis of the causality between gene expression and patient conditions. The software created is highly automated, facilitating data entry to study different expression matrices, with a linear flow, with a reading of data through the GEO code, a preprocessing in which a hypothesis contrast is facilitated, a normalization to make the comparable data between them and a gene filtration that reduces the computational calculation of the subsequent training of machine learning models which entails different gene selection techniques to, through the validation of the model, detect the relationship between gene expression and the patient's condition and share the results of the genes really involved in the response I test this tool with one of the most current issues in terms of clinical diagnosis, the detection of cancer through the gene expression of platelets. The data were obtained from the experiment with code GSE89843. AUC above 90% are obtained with only 10 genes, which is a great advance in this field. The AUC can be interpreted as the probability of classifying them correctly. Due to its low cost due to the reduced number of genes and its low invasiveness, it can be carried out as a preventive test and reduce its mortality rate.
Keywords: RNA-seq
feature selectión
liquid biopsy
random forest
Document type: info:eu-repo/semantics/masterThesis
Issue Date: Jan-2020
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 
jrodriguezperez012TFM0120memoria.pdfMemoria del TFM644,26 kBAdobe PDFThumbnail
View/Open