Microarray data has evolved into an indispensable tool for scrutinizing gene expression, prompting researchers to strategically utilize a minimal set of pertinent gene expression profiles to refine the accuracy of tumor identification. The imperative task of identifying key differential genes in colon cancers, crucial for distinguishing patients from the normal population, has led to the development of various techniques and algorithms. Swarm and Evolutionary Algorithms (SEA), renowned for their efficiency as global search agents, have emerged as particularly effective in optimizing the selection of a pertinent subset of genes related to colon cancer. This paper introduces an innovative approach that integrates swarm and evolutionary algorithms to tackle the challenge of feature selection in datasets related to colon cancer. A thorough comparative analysis is conducted, highlighting the differences between the proposed method and an alternative feature selection approach based on swarm and evolutionary algorithms. The extensive experimental results convincingly demonstrate the favorability and effectiveness of the proposed model, showcasing superior accuracy and a notable reduction in the number of selected features.