Pseudomonas aeruginosa is an opportunistic pathogen that chronically infects the lungs of patients with cystic fibrosis. We know that these bacteria evolve within the lung environment, and have an idea of some of the changes that occur. I performed a genome-wide association study in P. aeruginosa using a variety of analysis methods and several datasets of gene and SNP presence/absence. I determined that the machine learning algorithms random forest and support vector machines performed well on gene presence/absence and core SNP datasets, respectively, when compared with current methods (PLINK and treeWAS). Genes and SNPs already associated with adaptation to the CF lung environment, such as mucA, gyrA, and mex genes, were found with these methods. Some hypothetical and probable proteins were also recovered, and are good candidates for future research.