Qualitative Reasoning on Systematic Gene Perturbation Experiments
Observations of systematic gene perturbation experiments have been proven the most informative for the identification of regulatory relations between genes. For this purpose, we present a novel Qualitative Reasoning approach, based on a qualitative abstraction of DNA-microarray data and on a set of IF-THEN inference rules. Our algorithm exhibits an extremely low rate of false positives, competitive with the state-of-the-art, on both noise-free and noisy simulated data. This, together with the polynomial running time, makes our algorithm an useful tool for systematic gene perturbation experiments, able to identify a subset of the oriented regulatory relations with high reliability and to provide valuable insights on the amount of information conveyed by a set of experiments.
Unable to display preview. Download preview PDF.
- 4.Hunter, L.: Life and its molecules: A brief introduction. AI Magazine - Special issue on AI and Bioinformatics 25(1), 9–22 (2004)Google Scholar
- 6.Molla, M., Waddell, M., Page, D., Shavlik, J.: Using machine learning to design and interpret gene-expression microarrays. AI Magazine - Special issue on AI and Bioinformatics 25(1), 23–44 (2004)Google Scholar