Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/83245
Title: Seqüències amb FI
Author: Sanjuan Vilaplana, Anna
Tutor: Sanchez-Martinez, Melchor  
Others: Marco-Galindo, Maria-Jesús  
Abstract: Peptides are presented as one of the promising therapeutic molecules given the advantages over other molecules: cell penetration, toxicity, mèdium-life, solubility and immunogenicity ... "In silico" prediction of peptides' toxicity, peptide-protein interaction and biological function has a lot of weight in the initial stage of the process of obtaining therapeutic peptides. There is not a standardized method with the optimal algorithm performing these predictions; neither the method of analysis that should be followed. However, Support Vector Machine algorithm (SVM) has been the mostly used and performed algorithm. In turn, to predicting the previous peptide characteristics researchers usually performthe analysis of the sequences based on their amino acid and dipeptide composition. The results of applying Machine Learning (ML) methods will depend, on the parameters that are set to execute these ones, and, on the characteristics and structure that our dataset has. Creating a common, non-redundant database under the same format would improve the progress of this field in the study of "in silico" sequence-based prediction of therapeutic peptides.
Keywords: machine learning
polypeptide sequence
databases
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 5-Jun-2018
Publication license: https://creativecommons.org/licenses/by/4.0/  
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 
annsTFM0618memòria.pdfMemòria del TFM570,05 kBAdobe PDFThumbnail
View/Open
Share:
Export:
View statistics

Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.