Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/64392
Title: Implementació d'una eina de predicció de dianes de miRNA basat en algorismes de Machine Learning
Author: Carrere Molina, Jordi
Tutor: Pla Planas, Albert
Others: Universitat Oberta de Catalunya
Sánchez-Pla, Alex  
Abstract: miRNA are short non-coding RNA, approximately 22 nucleotides long, with regulatory function of gene expression at post-transcriptional level. About 1500 human miRNA are known, that it is estimated to regulate 30 % of human genes. The identification of miRNA targets is essential to understanding its biological function. Prediction of miRNA targets in silico is a key method to save time and resources to subsequently validate them experimentally. Different softwares can do these predictions applying rule based algorithms. In a recent time, some machine learning algorithms have been applied to model the interaction between miRNA and its target, obtaining great accuracy results. Machine Learning is a method able to recognise patterns in large amounts of data and device a model to classify or predict new data. This thesis presents the tool miRNAforest that models the union between miRNAs and their targets by Random Forest algorithm to classify a new possible target of a given miRNA. miRNAforest is able to predict miRNA targets with an accuracy of 85.78%, 86.93% of sensitivity and 84.66% of specificity.
Keywords: microRNA
machine learning
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 24-May-2017
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 
jcarreremTFM0617memoria.pdfMemòria del TFM2,05 MBAdobe PDFThumbnail
View/Open