A new hybrid approach for feature selection and predicting of protein interaction network in lung cancer

Abstract

Different computational and evolutionary methods have been employed in the last decade for selecting important molecular features from biological data. Extracting information from microarray data is extremely important and complex task due to the high dimensionality of its datasets. Feature selection is a very important aspect of the analysis that helps in identifying the important genes that can be used in a further biological analysis. This paper proposes a new hybridization between the Flower Pollination and Differential Evolution algorithms for optimizing feature selection parameters and to find out the most important subset of features over gene expression profiles of lung cancer. The results showed that the hybrid approach has a better capability in searching for the best solutions compared to applying each algorithm independently. SLC5A1 gene was identified as a biomarker gene of lung cancer. By constructing the protein-protein interaction network for the extracted genes, a direct interaction has been detected between the SLC5A1 and EGFR genes, where the latter is known to have an important role in the mutation process of lung cells.