Servellita Venice, Bouquet Jerome, Rebman Alison, Yang Ting, Samayoa Erik, Miller Steve, Stone Mars, Lanteri Marion, Busch Michael, Tang Patrick, Morshed Muhammad, Soloski Mark J, Aucott John, Chiu Charles Y
Department of Laboratory Medicine, University of California, San Francisco, CA USA.
Lyme Disease Research Center, Division of Rheumatology, Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD USA.
Commun Med (Lond). 2022 Jul 22;2:92. doi: 10.1038/s43856-022-00127-2. eCollection 2022.
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.
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 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.
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 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.
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.
莱姆病是一种由蜱传播的疾病，在美国每年估计导致47.6万例感染。由于现有的基于抗体的检测方法缺乏足够的敏感性和特异性，因此迫切需要新的诊断测试。
我们通过RNA测序（RNA-Seq）、靶向RNA-Seq和/或基于机器学习的分类方法，对来自218名受试者的263份外周血单核细胞样本进行转录组分析，其中包括94例早期莱姆病患者、48例未感染的对照受试者和57例其他感染（流感、菌血症或结核病）患者。根据参考数据库中25278个基因中≥1.5倍变化、≤0.05的P值和≤0.001的错误发现率临界值，选择差异表达基因。在使用k近邻算法进行基因选择后，使用机器学习评估十种不同分类器模型的比较性能。
我们确定了一个由31个基因组成的莱姆病分类器（LDC）面板，该面板可以区分早期莱姆病患者和对照，其中23个基因（74.2%）先前已在莱姆病患者的临床研究或感染的体外细胞培养和啮齿动物研究中被描述。使用来自63名受试者的独立测试样本集对LDC进行评估，总体敏感性为90.0%，特异性为100%，准确性为95.2%。LDC检测在85.7%的血清阴性患者中呈阳性，并且在12名患者中的9名（75%）中发现持续≥3周。
这些结果突出了基因表达分类器在诊断早期莱姆病方面的潜在临床应用价值，包括在传统血清学检测为阴性的患者中。
