Identifi cation of diagnostic markers for tuberculosis by proteomic fi ngerprinting of serum

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