As a waterborne pathogen of increasing concern, techniques for cost-effective and rapid characterization of Legionella are vital. This study examines the development of a Matrix Assisted Laser Desorption/Ionization-Time of Flight Mass Spectrometry (MALDI-TOF-MS) analysis methodology for this microbe. First, optimal sample preparation methods for the analysis of environmental Legionella isolates via MALDI-TOF-MS were determined. These methods were then implemented to perform strain-level characterization of environmental Legionella isolates from central Arizona. Results demonstrate that a MALDI-TOF-MS method involving BCYE agar-based culturing and protein extraction-based sample preparation yield high-quality mass spectra. Twenty-eight environmental Legionella isolates originating from two separate drinking water distribution systems were analyzed. Multiple species were detected, and strain-level characterization was achieved, with 12 unique strains distinguished. In addition, isolates of L. pneumophila, the most common species observed in the study, were correctly assigned to specific sampling sites. These results demonstrate the potential for this technique to be applied for sub-species characterization of Legionella with significant benefits over established methodologies.

A rapid classification method was developed for the malignant and benign thyroid nodules with ultrasound guided-fine needle aspiration biopsy (FNAB) samples. With probe electrospray ionization mass spectrometry, the mass-scan data of FNAB samples were used as datasets for machine learning. The patients were marked as malignant (98 patients), benign (110 patients) or undetermined (42 patients) by experienced doctors in terms of ultrasound, the B-Raf (BRAF) gene, and cytopathology inspections. Pairwise coupling was performed on 163 ions to generate 3630 ion ratios as new features for classifier training. With the new features, the performance of the multilayer perception (MLP) classifier is much better than that with the 163 ions as features directly. After training, the accuracy of the MLP classifier is as high as 92.0%. The accuracy of the single-blind test is 82.4%, which proved the good generalization ability of the MLP classifier. The overall concordance is 73.0% between prediction and six-month follow-up for patients in the undetermined group. Especially, the classifier showed high accuracy for the undetermined patients with suspicious for papillary carcinoma diagnosis (90.9%). In summary, the machine learning method based on FNAB samples has potential for real clinical applications.