Different unsupervised learning methods have been applied to single cell RNA sequencing datasets, aiming to unveil similarities and correlations between cells and groups of cells. In this thesis, it will be presented a novel theoretical framework based on information entropy to select most informative genes. In order to achieve this goal it was necessary to study data clustering methods that not only could output a meaningful partition of the high-dimension space of the cell dataset, but also that have well-defined clustering parameters. In addition, it focus on methods that perform under low run time complexity and a good scalability profile. As result, it was found a group of marker genes that preserves the clustering structure they are embedded, which biological relevance still under investigation.

Clustering strategy for selection of relevant genes in single cell transcriptomics(2020 Feb 14).

Clustering strategy for selection of relevant genes in single cell transcriptomics

-
2020-02-14

Abstract

Different unsupervised learning methods have been applied to single cell RNA sequencing datasets, aiming to unveil similarities and correlations between cells and groups of cells. In this thesis, it will be presented a novel theoretical framework based on information entropy to select most informative genes. In order to achieve this goal it was necessary to study data clustering methods that not only could output a meaningful partition of the high-dimension space of the cell dataset, but also that have well-defined clustering parameters. In addition, it focus on methods that perform under low run time complexity and a good scalability profile. As result, it was found a group of marker genes that preserves the clustering structure they are embedded, which biological relevance still under investigation.
14-feb-2020
SILVA, Florentino Gomes de Oliveira
Marsili, Matteo
Rodriguez Garcia, Alejandro
SARTORI, Alberto
File in questo prodotto:
File Dimensione Formato  
Silva.pdf

accesso aperto

Tipologia: Tesi
Licenza: Non specificato
Dimensione 3.76 MB
Formato Adobe PDF
3.76 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11767/116047
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact