Although widely prevalent, Lyme disease is still under-diagnosed and misunderstood . Here we followed 73 acute Lyme disease patients and uninfected controls over a period of a year . At each visit, RNA-sequencing was applied to profile patients' peripheral blood mononuclear cells in addition to extensive clinical phenotyping . Based on the projection of the RNA-seq data into lower dimensions, we observe that the cases are separated from controls, and almost all cases never return to cluster with the controls over time . Enrichment analysis of the differentially expressed genes between clusters identifies up-regulation of immune response genes . This observation is also supported by deconvolution analysis to identify the changes in cell type composition due to Lyme disease infection . Importantly, we developed several machine learning classifiers that attempt to perform various Lyme disease classifications . We show that Lyme patients can be distinguished from the controls as well as from COVID-19 patients, but classification was not successful in distinguishing those patients with early Lyme disease cases that would advance to develop post-treatment persistent symptoms.
Index: Lyme disease, PBMCs, PTLDS, RNA-seq, data mining, machine learning