A diagnostic classifier for gene expression-based identification of early Lyme disease

Abstract

Background Lyme disease is a tick-borne 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. Methods Here we perform transcriptome profiling by RNA sequencing (RNA-Seq), targeted RNA-Seq, and/or machine learning-based classification of 263 peripheral blood mononuclear cell samples from 218 subjects, including 94 early Lyme disease patients, 48 uninfected control subjects, and 57 patients with other infections (influenza, bacteremia, or tuberculosis). Differentially expressed genes among the 25,278 in the reference database are selected based on ≥1.5-fold change, ≤0.05 p value, and ≤0.001 false-discovery rate cutoffs. After gene selection using a k-nearest neighbor algorithm, the comparative performance of ten different classifier models is evaluated using machine learning. Results We identify a 31-gene Lyme disease classifier (LDC) panel that can discriminate between early Lyme patients and controls, with 23 genes (74.2%) that have 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 yields an overall sensitivity of 90.0%, specificity of 100%, and accuracy of 95.2%. The LDC test is positive in 85.7% of seronegative patients and found to persist for ≥3 weeks in 9 of 12 (75%) patients. Conclusions These results highlight the potential clinical utility of a gene expression classifier for diagnosis of early Lyme disease, including in patients negative by conventional serologic testing.

WITHDRAWN: A gene expression-based diagnostic classifier for identification of severe COVID-19 and multisystem inflammatory syndrome in children (MIS-C)

“…We selected the top 300 relevant features selected using differential expression/abundance analysis in DESeq2 14 (Benjamini-Hochberg adjusted p-value < 0.05, ranked by fold change). Using the top 300 relevant features, we trained 13 machine learning classification models 8 and fit a logistic regression to distinguish wbRNA or cfRNA profiles from patients wi MIS-C, COVID-19, and good health (Fig. 1B-C).…”

“…Using the top 300 relevant features, we trained 13 machine learning classification models 8 and fit a logistic regression to distinguish wbRNA or cfRNA profiles from patients with MIS-C, COVID-19, and good health ( Fig. 1B-C ).…”

“…Transcriptome analysis by RNA sequencing (RNA-Seq) has been shown to be useful in the diagnosis of rare genetic diseases 7 and infections such as Lyme disease 8 , influenza 9 , and COVID-19 10 . In a previous study 11 , analysis of plasma cell-free RNA from patients with MIS-C or severe COVID-19 yielded distinct signatures of cell injury and death between these two disease states, including the involvement of unexpected pathways such as endothelial and neuronal Schwann cell signaling.…”

Lyme rashes disease classification using deep feature fusion technique

“…used deep convolutional neural networks trained on erythema migrans image classification with 93% accuracy. Servellita et al 31 . developed a diagnostic classifier with an accuracy of 95.2% for the gene expression‐based detection of early Lyme illness.…”

“…Assessment of the proposed strategy concerning state-of-the-art paradigms.ResNet50 to detect erythema migrans and other perplexing skin disorders; they achieved 95% accuracy in recognizing erythema migrans, but this only holds if the dataset is legitimate. For early Lyme disease identification based on gene expression, Servellita et al31 created a diagnostic classifier with a 95.2% accuracy. Justin et al66 trained a CNN to identify tick bites using a photo dataset collected via a mobile app.…”