Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/9CE41ADE-C233-4C3B-865E-EEFCFF858D76 | ||
| Year | 2016 | ||
| Type of Item | Conference Full Paper | ||
| License |
|
||
| Bibliographic Citation | V. Leska, E. S. Bei, E. Petrakis and M. Zervakis, "Gene expression data analysis for classification of bipolar disorders," in 14th Mediterranean Conference on Medical and Biological Engineering and Computing, 2016, pp. 494-500. doi: 10.1007/978-3-319-32703-7_96 https://doi.org/10.1007/978-3-319-32703-7_97 | ||
| Appears in Collections |
In recent years DNA microarray technology has become a widely used tool for gene expression profile analysis. This technology can be useful for the early diagnosis of complex diseases such as bipolar disorder, providing useful information for its genetic background. The ability to classify bipolar disorders may have a major impact on our understanding of disease pathophysiology, as well as it may be essential for guiding the appropriate treatment strategy and determining prognosis for successful targeted therapy. In this preliminary meta-data-study, we propose an analytic framework for biomarker identification aiming at prediction of bipolar disorder, by considering peripheral gene expression differences between bipolar patients and healthy controls. The aim of this paper is to extract a significant genomic signature for which biological knowledge may already exists and discover novel genomic information that can motivate further analysis. We study two classification algorithms based on support and relevance vector machines. The observed results indicate that the latter approach performs better in the specific biological environment.
Copyright © DIAS 2013
