Improving Algorithms for Knowledge Discovery in Genetics Databases

Extracting Knowledge from genetics data-base still one of the most exciting challenges in data mining. Most of the widely association studies algorithm used to determine responsible regions for a complex genetic disease. The objective of our study lies in developing a new approach for knowledge discovery in genetics data base. In this work, firstly we propose some improvements to the existent algorithms applied in this context. Secondly we show that our new algorithm (named NCA) improved the results compared to existents algorithms. As a matter of fact we have applied and compared our approach and existent approach to biological facts concerning hereditary complex illness where the literatures in biology identify the responsible variables for those diseases. Finally, we conclude by proposing suggestions for further research.