Διιδρυματικό ΠΜΣ Τεχνολογίες Πληροφορικής στην Ιατρική και τη Βιολογία
Library of the School of Science

2015-09-14

2015

Σακελλαρίου Αργύρης

Σέργιος Θεοδωρίδης, Δημήτριος Μαρούλης, Εμμανουήλ Σαγκριώτης

Computational Methods for the Identification of Statistically Significant Genes: Applications to Gene Expression Data of Various Human Diseases

English

Υπολογιστικές Μέθοδοι για τον Προσδιορισμό Στατιστικώς Σημαντικών Γονιδίων: Εφαρμογές σε δεδομένα γονιδιακής έκφρασης από διάφορες ανθρώπινες νόσους

In 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.

microarrays, gene expression data, significance analysis, hybrid feature selection, biomarkers

Yes

27-34

Yes

120

146

https://pergamos.lib.uoa.gr/uoa/dl/object/1309580/file.pdf

https://pergamos.lib.uoa.gr/uoa/dl/object/1309580