Extracting Gradual Rules to reveal regulation between genes
Background: The gene regulation represents a very complex mechanism produced in the cell in order to increase or decrease the gene expression. This regulation of genes forms a Gene regulatory Network GRN composed of a collection of genes and products of genes in interaction. The high throughput technologies that generate a huge volume of gene expression data are useful for analyzing the GRN. The biologists are interested in the relevant genetic knowledge hidden in these data sources. Although, the knowledge extracted by the different data mining approaches of the literature are insufficient for inferring the GRN topology or do not give a good representation of the real genetic regulation in the cell. Objective: In this work, we are interested in the extraction of genetic interactions from the high throughput technologies, such as the microarrays or DNA chips. Methods: In this paper, in order to extract expressive and explicit knowledge about the interactions between genes, we use the method of gradual patterns and rules extraction applied on numerical data that extracts the frequent co-variations between gene expression values. Furthermore, we choose to integrate experimental biological data and biological knowledge in the process of knowledge extraction of genetic interactions. Results: The validation results on real gene expression data of the model plant Arabidopsis and human lung cancer shows the performance of this approach. Conclusion: The extracted gradual rules express the genetic interactions composed a GRN, these rules help to understand complex systems and cellular functions.