Identification of diagnostic markers for tuberculosis by proteomic fingerprinting of serum

Abstract

Background: We investigated the potential of proteomic fingerprinting with mass spectrometric serum profiling, coupled with pattern recognition methods, to identify biomarkers that could improve diagnosis of tuberculosis.

Methods: We obtained serum proteomic profiles from patients with active tuberculosis and controls by surface-enhanced laser desorption ionisation time of flight mass spectrometry. A supervised machine-learning approach based on the support vector machine (SVM) was used to obtain a classifier that distinguished between the groups in two independent test sets. We used k-fold cross validation and random sampling of the SVM classifier to assess the classifier further. Relevant mass peaks were selected by correlational analysis and assessed with SVM. We tested the diagnostic potential of candidate biomarkers, identified by peptide mass fingerprinting, by conventional immunoassays and SVM classifiers trained on these data.

Findings: Our SVM classifier discriminated the proteomic profile of patients with active tuberculosis from that of controls with overlapping clinical features. Diagnostic accuracy was 94% (sensitivity 93.5%, specificity 94.9%) for patients with tuberculosis and was unaffected by HIV status. A classifier trained on the 20 most informative peaks achieved diagnostic accuracy of 90%. From these peaks, two peptides (serum amyloid A protein and transthyretin) were identified and quantitated by immunoassay. Because these peptides reflect inflammatory states, we also quantitated neopterin and C reactive protein. Application of an SVM classifier using combinations of these values gave diagnostic accuracies of up to 84% for tuberculosis. Validation on a second, prospectively collected testing set gave similar accuracies using the whole proteomic signature and the 20 selected peaks. Using combinations of the four biomarkers, we achieved diagnostic accuracies of up to 78%.

Interpretation: The potential biomarkers for tuberculosis that we identified through proteomic fingerprinting and pattern recognition have a plausible biological connection with the disease and could be used to develop new diagnostic tests.

Figure 1

Performance and validation of classifiers (A) Classifier performance in ROC space. SVM_1, ADT_2, C4·5_2, C5·0_1, SVM_4, SLP_3, MLP: for names and parameters see table 3. ADT_1=Adaptive decision tree without AdaBoost. NCP_3=Non-conservative projection (normalised, random presentation). C5·0_2=C5·0 tree with winnowing. C4·5_1=C4·5 tree without AdaBoost. CP_2=conservative projection (normalised). NCP_2=non-conservative projection (normalised). Red line indicates convex hull. (B) Gaussian kernel Support Vector Machine performance (ten-fold crossvalidation). Each block of three bars shows the values for accuracy (red), sensitivity (green) and specificity (blue) obtained when the sigma Gaussian-kernel was optimised for each of these criteria. (C) Averaged ROC using ten-fold train crossvalidation with test. 100 randomly selected train and test sets with a train:test ratio [80:20]. Parameters were selected with a ten-fold crossvalidation on the train set and performance obtained in the test. Red line shows averaged ROC curve of classifiers obtained when kernel parameter is selected on accuracy criteria. Similar ROC curves were obtained when selecting on sensitivity and specificity (webfigure 1).

Figure 2

Performance of SVM classifiers based on subsets of peak clusters and combinations of identified biomarkers SAA=serum amyloid A. CRP=C-reactive protein. Gaussian SVMs were trained with the initial train set (table 2) using the specified mass peak clusters or biomarker combination (ten-fold crossvalidation for parameter selection). Classifier performance was then assessed on initial test (table 2). (A) Classification performance of correlated mass clusters. 1=10 positively correlated and 10 negatively correlated; 2=remaining 199. 3=10 positively correlated; 4=remaining 209. 5=10 negatively correlated; 6=remaining 209. Raw values supplied in webtable 1. Red line represents convex hull defined by optimal classifiers (4 and 1). (B) Biomarkers. 1g=transthyretin. 2g=CRP. 3g=neopterin. 4g=SAA. 5g=neopterin-SAA. 6g=CRP-SAA. 7g=CRP-neopterin. 8g=transthyretin-SAA. 9g=transthyretin-neopterin. 10g=transthyretin-CRP. 11g=transthyretin-CRP-neopterin. 12g=transthyretin-CRP-SAA. 13g=transthyretin-neopterin-SAA. 14g=CRP-neopterin-SAA. 15g=transthyretin-CRP-neopterin-SAA. Raw values supplied in webtable 2. Red line represents convex hull defined by optimal classifiers (2g, 6g, 12g, 9g).