Multidimensional analysis of immune responses identified biomarkers of recent Mycobacterium tuberculosis infection

Abstract

The risk of tuberculosis (TB) disease is higher in individuals with recent Mycobacterium tuberculosis (M.tb) infection compared to individuals with more remote, established infection. We aimed to define blood-based biomarkers to distinguish between recent and remote infection, which would allow targeting of recently infected individuals for preventive TB treatment. We hypothesized that integration of multiple immune measurements would outperform the diagnostic performance of a single biomarker. Analysis was performed on different components of the immune system, including adaptive and innate responses to mycobacteria, measured on recently and remotely M.tb infected adolescents. The datasets were standardized using variance stabilizing scaling and missing values were imputed using a multiple factor analysis-based approach. For data integration, we compared the performance of a Multiple Tuning Parameter Elastic Net (MTP-EN) to a standard EN model, which was built to the individual adaptive and innate datasets. Biomarkers with non-zero coefficients from the optimal single data EN models were then isolated to build logistic regression models. A decision tree and random forest model were used for statistical confirmation. We found no difference in the predictive performances of the optimal MTP-EN model and the EN model [average area under the receiver operating curve (AUROC) = 0.93]. EN models built to the integrated dataset and the adaptive dataset yielded identically high AUROC values (average AUROC = 0.91), while the innate data EN model performed poorly (average AUROC = 0.62). Results also indicated that integration of adaptive and innate biomarkers did not outperform the adaptive biomarkers alone (Likelihood Ratio Test χ2 = 6.09, p = 0.808). From a total of 193 variables, the level of HLA-DR on ESAT6/CFP10-specific Th1 cytokine-expressing CD4 cells was the strongest biomarker for recent M.tb infection. The discriminatory ability of this variable was confirmed in both tree-based models. A single biomarker measuring M.tb-specific T cell activation yielded excellent diagnostic potential to distinguish between recent and remote M.tb infection.

Fig 1. Workflow showing data pre-processing steps (A) and regression modeling (B).

PID: participant ID; AUC: area under the curve; LR: logistic regression; CB: candidate biomarkers; CV: cross validation; LRT: likelihood ratio test.

Fig 2. Candidate biomarkers of recent M.tb infection identified by the adaptive and innate EN models.

Boxplots comparing the raw values of recent (red) and persistent (blue) QFT+ individuals for the three candidate biomarkers with non-zero coefficients in the adaptive EN model (A) and the 10 biomarkers with non-zero coefficients in the innate EN model (B). Wilcoxon tests were used to compare the two groups and the resulting p-values are shown.

Fig 3. Tree-based modeling results.

(A) Results from the simple classification tree built to the entire integrated dataset. Boxplots comparing vast scaled values of recent (red) and persistent (blue) QFT+ individuals were plotted for the two most stratifying features identified by the decision tree. The split values are superimposed onto the plots at (B) -0.098 for proportions of E6C10-specific Th1 cells expressing HLA-DR, and (C) -0.12 for frequencies of Esp-specific IL2+CD107-CD154-IFN-γ-TNF+ CD4+ T cells. (D) Variable importance plot of the final RF model showing the top 10 variables that resulted in the largest average decrease in the Gini Index.