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
Director: Pla Planas, Albert
Tutor: Sánchez Pla, Alexandre
Others: Universitat Oberta de Catalunya
Keywords: microRNA
machine learning
Issue Date: 24-May-2017
Publisher: Universitat Oberta de Catalunya
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.
Language: Catalan
URI: http://hdl.handle.net/10609/64392
Appears in Collections:Bachelor thesis, research projects, etc.

Share:
Export:
Files in This Item:
File Description SizeFormat 
jcarreremTFM0617memoria.pdfMemòria del TFM2.05 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons