Please use this identifier to cite or link to this item:
http://hdl.handle.net/10609/82085
Title: | Anotación de nuevos microRNAs en el genoma porcino mediante una aproximación basada en Machine Learning |
Author: | Mármol Sánchez, Emilio |
Tutor: | Pla Planas, Albert |
Others: | Universitat Oberta de Catalunya Morán Moreno, Jose Antonio |
Abstract: | Computational discovery of microRNAs (miRNAs) poses a big research challenge nowadays, especially considering non-model species that lack accurate and reliable miRNA annotation. Through the application of a Machine Learning approach by using algorithms like Support Vector Machine (SVM) and Random Forest (RF) and making use of a homology-based comparison with miRNA annotation un humans, we developed a pipeline for identifying and annotating new pre-miRNA candidates in the porcine genome. We generated a set of positive and negative data, filtered considering size and structural folding, and then calculated a series of structural features for each considered sequence that where subsequently used for training a Machine Learning-based SVM classifier. We extracted a set of candidate sequences in the porcine genome that showed to be homologous from human miRNA annotation and classified them by using the previously trained SVM model. These candidate pre-miRNAs sequences were then filtered according to a neighbouring feasibility analysis. Our approach allowed us to identify 26 putative non-annotated pre miRNA sequences in the porcine genome. Among them, we highlighted the putative candidate ssc-miR-483, homologous of human hsa-miR-483 and located at intron 2 of IGF2 gene. This miRNA has been associated to the regulation of cellular proliferation and adipocyte differentiation, modulating lipid integration and storage in response to food intake. These results could enhance our understanding of energy and lipid metabolism regulation in the porcine species. |
Keywords: | machine learning microRNA support vector machine |
Document type: | info:eu-repo/semantics/masterThesis |
Issue Date: | Jun-2018 |
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 | Size | Format | |
---|---|---|---|---|
1.Pig_positive_set.fa | 47,96 kB | Unknown | View/Open | |
2.Pig_negative_set.fa | 38,66 kB | Unknown | View/Open | |
3.Human_positive_set.fa | 179,14 kB | Unknown | View/Open | |
4.Human_negative_set.fa | 265,92 kB | Unknown | View/Open | |
5.Pseudo-miRNAs_set.fa | 815,6 kB | Unknown | View/Open | |
9.miRNAs_Predicted.txt | 18,97 kB | Text | View/Open | |
10.Novel_miRNAs_Predicted.txt | 1,09 kB | Text | View/Open | |
emarmolsTFM0618memoria.pdf | Memoria del TFM | 1,17 MB | Adobe PDF | View/Open |
Share:
This item is licensed under a Creative Commons License