Please use this identifier to cite or link to this item:

http://hdl.handle.net/10609/98407
Title: Modelització de dades òmiques amb autoencoders
Author: Masip Masip, Jordi
Director: Reverter Comes, Ferran
Vegas Lozano, Esteban
Tutor: Sánchez Pla, Alexandre
Ventura Royo, Carles  
Keywords: autoencoder
omics data
deep learning
Issue Date: Jun-2019
Publisher: Universitat Oberta de Catalunya (UOC)
Abstract: The purpose of this work is to replicate and explore the use of a stacked auto-encoder based artificial neural network to model omic data. Omic data analysis has required the development of new analysis tools, given their great dimensionality. Deep learning tools have brought improvements to this analysis challenge. The work of Xie, et al. (1) showed the superiority of a multi-layer perceptron based on stacked autoencoders model (MLP-SAE) to study the relationship between single nucleotide polymorphisms (SNP) and genetic expression (measured using high-throughput sequencing [HTSeq]), when compared with other available methods.
Language: Catalan
URI: http://hdl.handle.net/10609/98407
Appears in Collections:Bachelor thesis, research projects, etc.

Share:
Export:
Files in This Item:
File Description SizeFormat 
jmasipmasTFM0619memòria.pdfMemòria del TFM2.04 MBAdobe PDFView/Open
codi_i_resultats_Memoria_Treball.zip20.56 MBUnknownView/Open

This item is licensed under a Creative Commons License Creative Commons