This part is an extension to the workflow analysis with unsupervised machine learning to find target genes in the samples from GSE318371 that have EBV or Epstein-Barr Viral infection and Natural Killer T-cell Lymphoma or NKTC aggressive Lymphoma. We do the PCA, the K-Nearest Neighbor, and UMap. Later we will do TSNE since available in Seurat, and also add this data with gene name as a data frame to link to the clusters of known EBV targeted genes to see how they change within the pathology of NKTCL vs healthy, add these genes minus EBV target genes already known to the database of our known pathology gene targets in predicting pathology of EBV, EBV associated diseases like Mononucleosis, Multiple Sclerosis, Hodgkin Disease, Burkett's Lymphoma, and nasopharyngeal carcinoma, as well as not EBV associated pathologies of fibromyalgia and Lyme disease. More to come.

This is my reproducible pitch for the Developing Data Products course.