Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/109166
Title: Predicción de la interacción de proteínas relacionadas con el Alzheimer a partir de su estructura primaria
Author: Pérez López, Carlos
Tutor: Sanchez-Martinez, Melchor  
Others: Canovas Izquierdo, Javier Luis  
Abstract: Alzheimer's disease (AD) is a neurodegenerative disease that affects a large number of people at this time. Nowadays, numerous therapies are being used to treat it. However, studies on the development of new medications turn out to be expensive processes; therefore, machine learning techniques are being used to reduce costs. In this thesis, machine learning models will be trained to try to predict whether two proteins interact or not. In order to do this, protein data involved in the AD process are collected, and it is then studied which proteins interact with them (PPIs). Data are also collected from the Intact and Negatome repositories on proteins that have experimental evidence showing that they don't have interactions (nPPIs); while random proteins from Uniprot are paired and assumed to be nPPIs. Drawing from these databases, the primary structures of the proteins are obtained and characteristics are generated in the form of quantitative data using the methodologies of Amino Acid Composition (AAC), Dipeptide Composition (DPC), Composition / Transition / Distribution (CTD) and Composition of pseudo-amino acids (PAAC). To develop the models, based on these characteristics, the algorithms Support Vector Machine (SVM) and Random Forest (RF) are used. Ultimately, it is shown that the model generated by SVM, using AAC and using the Uniprot database as a source of nPPIs, is the one with the greatest prediction and robustness.
Keywords: random forest
protein interaction
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 8-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 
cperezlopezTFM0120memoria.pdfMemoria del TFM619,82 kBAdobe PDFThumbnail
View/Open