Mining Gene Expression Profiles and Gene Regulatory Networks: Identification of Phenotype-Specific Molecular Mechanisms

  • Authors:
  • Alexandros Kanterakis;Dimitris Kafetzopoulos;Vassilis Moustakis;George Potamias

  • Affiliations:
  • Institute of Computer Science, Foundation for Research & Technology --- Hellas (FORTH), Heraklion, Greece 71110;Institute of Molecular Biology & Biotechnology, Foundation for Research & Technology --- Hellas (FORTH), Heraklion, Greece 71110;Institute of Computer Science, Foundation for Research & Technology --- Hellas (FORTH), Heraklion, Greece 71110 and Department of Production Engineering and Management, Technical University of Cre ...;Institute of Computer Science, Foundation for Research & Technology --- Hellas (FORTH), Heraklion, Greece 71110

  • Venue:
  • SETN '08 Proceedings of the 5th Hellenic conference on Artificial Intelligence: Theories, Models and Applications
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

The complex regulatory mechanisms of genes and their transcription are the major gene regulatory steps in the cell. Gene Regulatory Networks (GRNs) and DNA Microarrays (MAs) present two of the most prominent and heavily researched concepts in contemporary molecular biology and bioinformatics. The challenge in contemporary biomedical informatics research lies in systems biology - the linking of various pillars of heterogeneous data so they can be used in synergy for life science research. Faced with this challenge we devised and present an integrated methodology that `amalgamates' knowledge and data from both GRNs and MA gene expression sources. The methodology, is able to identify phenotype-specific GRN functional paths, and aims to uncover potential gene-regulatory `fingerprints' and molecular mechanisms that govern the genomic profiles of diseases. Initial implementation and experimental results on a real-world breast-cancer study demonstrate the suitability and reliability of the approach.