Related Experiment Video
Updated: Jul 15, 2026
Multiplex Detection of Bacteria in Complex Clinical and Environmental Samples using Oligonucleotide-coupled Fluorescent Microspheres
Published on: October 23, 2011
Using circulating microbial cell-free DNA to identify persistent Treponema pallidum infection in serofast syphilis
Meng Yin Wu1, Lu Chen2, Li Cheng Liu2
1Department of Dermatology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, China.
Abstract:
The question of whether serofast status of syphilis patients indicates an ongoing low-grade Treponema pallidum (T. pallidum) infection remains unanswered. To address this, we developed a machine learning model to identify T. pallidum in cell-free DNA (cfDNA) using next-generation sequencing (NGS). Our findings showed that a TP_rate cut-off of 0.033 demonstrated superior diagnostic performance for syphilis, with a specificity of 92.3% and a sensitivity of 71.4% (AUROC = 0.92). This diagnosis model predicted that 20 out of 92 serofast patients had a persistent low-level infection. Based on these predictions, re-treatment was administered to these patients and its efficacy was evaluated. The results showed a statistically significant decrease in RPR titers in the prediction-positive group compared to the prediction-negative group after re-treatment (p < 0.05). These findings provide evidence for the existence of T. pallidum under serofast status and support the use of intensive treatment for serofast patients at higher risk in clinical practice.
Insights
Serofast syphilis patients may have ongoing low-grade Treponema pallidum infections. A machine learning model identified persistent T. pallidum in cell-free DNA, guiding effective re-treatment and improving outcomes.
Area of Science:
- Infectious Diseases
- Genomics
- Machine Learning
Background:
- Serofast status in syphilis patients, characterized by persistent positive serology despite treatment, raises questions about residual infection.
- Distinguishing between true serofast status and ongoing low-level Treponema pallidum infection is crucial for effective patient management.
Purpose of the Study:
- To develop and validate a machine learning model for detecting Treponema pallidum in cell-free DNA (cfDNA) to identify persistent infections in serofast syphilis patients.
- To evaluate the efficacy of re-treatment guided by the diagnostic model in serofast individuals.
Main Methods:
- Development of a machine learning model utilizing next-generation sequencing (NGS) data to identify T. pallidum DNA in cfDNA.
- Establishment of a TP_rate cut-off (0.033) for optimal diagnostic performance (AUROC = 0.92, specificity = 92.3%, sensitivity = 71.4%).
- Application of the model to predict persistent infection in 92 serofast patients and subsequent evaluation of re-treatment efficacy.
Main Results:
- The machine learning model accurately predicted persistent low-level T. pallidum infection in 20 out of 92 serofast patients.
- Patients predicted to have persistent infection and receiving re-treatment showed a statistically significant decrease in RPR titers compared to those not predicted positive.
- The TP_rate cut-off demonstrated high diagnostic accuracy for identifying T. pallidum in cfDNA.
Conclusions:
- The study provides evidence supporting the existence of persistent, low-grade Treponema pallidum infections in serofast syphilis patients.
- The developed machine learning model shows promise as a diagnostic tool for identifying individuals who may benefit from intensified treatment regimens.
- Findings support the clinical utility of targeted re-treatment for high-risk serofast syphilis patients based on cfDNA analysis.
