Breast cancer is the most common form of cancer, and afflicted over 2.2 million people in 2020. The sheer volume of patients that are afflicted with breast cancer warrants the need to continue research and discovery efforts to improve treatment options. Triple negative breast cancer (TNBC) affects 10-15% of breast cancer patients. Unlike other forms of breast cancer, TNBC does not have estrogen or progesterone receptors and makes little to none of the HER2 protein. Due to the lack of these biomarkers that are typical treatment targets for other kinds of breast cancers, hormone therapy and drugs that target other breast cancers are generally ineffective against TNBC. This leaves chemotherapy and radiation therapy as the main treatment options. Although chemotherapy and radiation have treatment benefits, the recurrence rate after treatment is around 40%. Furthermore, these treatment options are very detrimental to the body, resulting in a weaker patient and a necessary recovery time between treatments. In this study, we analyzed publicly available RNA-sequencing data to identify the upregulated and downregulated transcriptional mechanism(s) that play a role in TNBC compared to healthy breast tissue. The analysis of the RNAseq data was completed with the Automated Reproducible Modular Workflow for Preprocessing and Differential Analysis of RNA-seq Data (ARMOR), which identified differentially expressed genes. The ARMOR program trims, maps, and quantifies the mRNA sequencing reads to the human transcriptome for each sample. We then applied a Random Forest algorithm, which is an artificial intelligence-based classification method to identify new biomarkers that best differentiate TNBC cells from healthy cells.which may expand the treatment options for TNBC. We identified specific transcriptional biomarkers for TNBC that could be used as therapeutic targets. These novel targets may broaden the efficacy of treatments for patients with TNBC.