National and Kapodistrian University of Athens
Computational methods for the identification of statistically significant genes: applications to gene expression data of various human diseases
Abstract
dc:descriptionIn this dissertation, we address the problem of gene selection from ranked gene lists. We propose a new hybrid feature selection method (mAP-KL) that combines successfully multiple hypothesis testing and affinity propagation clustering algorithm along with the Krzanowski & Lai cluster quality index, to select a small yet informative subset of genes. We subject our method across a variety of validation tests on simulated microarray data as well as on real microarray data. The overall evaluation results suggest that mAP-KL generates concise yet biologically relevant and informative n-gene expression signatures, which can serve as a valuable discrimination tool for diagnostic and prognostic purposes, by identifying potential disease biomarkers in a broad range of diseases. Finally, to provide the research community with the capability to apply mAP-KL in any given gene expression dataset, we have implemented this methodology to a Bioconductor/R-package accompanied with extra functionalities.
Degree
thesis:*- Grantor dc:publisher
- National and Kapodistrian University of Athens
- Year dc:date
- 2015
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Sakellariou, Argiris
- Σακελλαρίου, Αργύρης
Subjects
dc:subject × 14- Μικροσυστοιχίες
- Δεδομένα γονιδιακής έκφρασης
- Ανάλυση σημαντικότητας
- Υβριδική μέθοδος επιλογής χαρακτηριστικών
- Βιοδείκτες
- Microarrays
- Gene expression data
- Significance analysis
- Hybrid feature selection
- Biomarkers
- Φυσικές Επιστήμες
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Natural Sciences
- Computer and Information Sciences
Rights
- Language dc:language
- eng
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/44047