A Diagnostic Classifier for Gene Expression-Based Identification of Early Lyme Disease

Lyme disease is a tickborne illness that causes an estimated 476,000 infections annually in the United States. New diagnostic tests are urgently needed, as existing antibody-based assays lack sufficient sensitivity and specificity. Using transcriptome profiling by RNA-Seq, targeted RNA sequencing, and machine learning (ML)-based classification of 218 subjects, we identified a 31-gene Lyme disease classifier (LDC) to discriminate early Lyme patients from “non-Lyme” controls infected with influenza, bacteremia, or tuberculosis or uninfected asymptomatic controls. Among the 31 classifier genes, 23 (74.2%) had previously been described in association with clinical investigations of Lyme disease patients or in vitro cell culture and rodent studies of Borrelia burgdorferi infection. Evaluation of the LDC using an independent test set of samples from 63 subjects (16 Lyme seropositive patients, 14 Lyme seronegative patients, and 33 controls) yielded an overall sensitivity of 90.0%, specificity of 100%, and accuracy of 95.2%. The LDC was positive in 85.7% of seronegative patients and persisted for ≥3 weeks in available longitudinal samples from 9 of 12 (75%) patients. These results highlight the potential clinical utility of a gene expression classifier for diagnosis of early Lyme disease. A total of 31 samples were analyzed in this set which include 6 uninfected controls, 6 influenza, 6 bacteremia, and 13 Lyme samples. >>> Submitter declares that raw data will be submitted to dbGaP due to patient privacy concerns.<<<