Abstract
dc:descriptionDuring the last decades the major advances in informatics and biology have attracted the interest of all humanity. The growth of World Wide Web and the Human Genome Project reflect the extent of the development of these two scientific areas. Moreover, the rapid technological development has resulted in an increased rate of biological data accumulation, necessitating the collaboration between scientists of biology and informatics. This collaboration has lead to the emergence of bioinformatics, a new interdisciplinary research area, which is the intersection of biology and informatics. The aim of bioinformatics is the development and use of tools for managing and analyzing the vast amounts of biological data. Another research area has been grown along with bioinformatics, in order to deal with large-volume data management efficiently and effectively. Knowledge discovery in databases provides a set of tools to analyze new data types in order to extract various types of knowledge efficiently and effectively. These tools combine powerful techniques from different areas, such as statistics, artificial intelligence, pattern recognition and database technology. This fusion of technologies aims to overcome the obstacles and constraints posed by the traditional data analysis methods. The scope of this thesis includes knowledge discovery from biological data and is strongly related to the research areas of knowledge discovery in data bases and bioinformatics. This thesis targets to the invention of new knowledge discovery methods and the modification or extension of existing ones, as well as the application of these methods for biological data analysis. In the framework of this thesis a new knowledge discovery problem, which deals with the discovery of mutually exclusive items, is defined. An algorithm for mining mutually exclusive items from transactional data is provided and is applied on gene expression data. Moreover, an approach for the effective classification of gene expression data and phenotype prediction is proposed. Furthermore, a number of biological sequence analysis approaches are proposed. In particular, two interesting and distinct sequence analysis problems are studied, namely translation initiation site prediction and cleavage-polyadenylation site prediction.
Degree
thesis:*- Grantor dc:publisher
- Aristotle University Of Thessaloniki (AUTH)
- Year dc:date
- 2011
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Tzanis, George
- Τζανής, Γεώργιος
Subjects
dc:subject × 20- Ανακάλυψη γνώσης
- Βιοπληροφορική
- Κανόνες συσχέτισης
- Πρόβλεψη
- Γονιδιακή έκφραση
- Σημείο έναρξης της μετάφρασης
- Σημείο αποκοπής και πολυαδενυλίωσης
- Μηχανική μάθηση
- Knowledge discovery
- Bioinformatics
- Association rules
- Prediction
- Gene expression
- Translation initiation site
- Cleavage and polyadenylation site
- Machine learning
- Φυσικές Επιστήμες
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Natural Sciences
- Computer and Information Sciences
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/25012