Histoplasmosis is the largest endemic fungal infection in North America caused by H. Capsulatum. It affects 250,000 people every year in the U.S.A with a mortality rate of 5% to 8%. Currently there are no drugs that are specially manufactured to treat Histoplasmosis. Determining the factors that influence protein production in the yeast form of H. Capsulatum is the key to finding methods to regulate the gene inside the fungi and invent powerful drugs to treat Histoplasmosis. However, what sequence elements in 5’ UTR​ ​determine TE in Histoplasma is not well understood. I explored the 5’ UTR region of 4981 genes common to 4 strains of Histoplasma to identify a correlation between the different sequence elements in the 5’ UTR of mRNA and TE. Subsequently, using these sequence elements I developed computational models to predict TE. The results demonstrate that the CG/ATG ratio has the best correlation to TE. Also, computational models using Random Forest outperformed other machine learning algorithms to best predict TE. My research was the first to investigate 5’ UTR of mRNA and discover that CG to ATG ratio significantly affects TE in H. Capsulatum. This research was also the first to develop 4 computational models to predict TE of Histoplasma. These discoveries are a key step towards future research on developing powerful drugs for the treatment of Histoplasmosis.