Within the study of pathological conditions from the analysis of high-throughput data, the usual approach consists in using supervised classification algorithms. Such approach frequently fails due to the initial bias of class definition uncertainty. We used an unsupervised approach to arrange samples according to the progression state of a disease by using a tool, Sample Progression Discovery, developed by Peng Qiu et al. After evaluating its functionality and how to handle its critical aspects, we applied it to two pathologies: chronic lymphocytic leukemia and Waldenström’s macroglobulinemia. The progressions found show good correspondence with clinical parameters under some constraints on the input
Extraction of dynamic patterns from static rna expression data: an application to hematological neoplasms
Bianchi, Giulia
2012/2013
Abstract
Within the study of pathological conditions from the analysis of high-throughput data, the usual approach consists in using supervised classification algorithms. Such approach frequently fails due to the initial bias of class definition uncertainty. We used an unsupervised approach to arrange samples according to the progression state of a disease by using a tool, Sample Progression Discovery, developed by Peng Qiu et al. After evaluating its functionality and how to handle its critical aspects, we applied it to two pathologies: chronic lymphocytic leukemia and Waldenström’s macroglobulinemia. The progressions found show good correspondence with clinical parameters under some constraints on the inputFile | Dimensione | Formato | |
---|---|---|---|
Tesi.pdf
accesso aperto
Dimensione
992.57 kB
Formato
Adobe PDF
|
992.57 kB | Adobe PDF | Visualizza/Apri |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/16487