MALDI(+) FT-ICR Mass Spectrometry (MS) Combined with Machine Learning toward Saliva-Based Diagnostic Screening for COVID-19

Abstract

Rapid identification of existing respiratory viruses in biological samples is of utmost importance in strategies to combat pandemics. Inputting MALDI FT-ICR MS (matrix-assisted laser desorption/ionization Fourier-transform ion cyclotron resonance mass spectrometry) data output into machine learning algorithms could hold promise in classifying positive samples for SARS-CoV-2. This study aimed to develop a fast and effective methodology to perform saliva-based screening of patients with suspected COVID-19, using the MALDI FT-ICR MS technique with a support vector machine (SVM). In the method optimization, the best sample preparation was obtained with the digestion of saliva in 10 μL of trypsin for 2 h and the MALDI analysis, which presented a satisfactory resolution for the analysis with 1 M. SVM models were created with data from the analysis of 97 samples that were designated as SARS-CoV-2 positives versus 52 negatives, confirmed by RT-PCR tests. SVM1 and SVM2 models showed the best results. The calibration group obtained 100% accuracy, and the test group 95.6% (SVM1) and 86.7% (SVM2). SVM1 selected 780 variables and has a false negative rate (FNR) of 0%, while SVM2 selected only two variables with a FNR of 3%. The proposed methodology suggests a promising tool to aid screening for COVID-19.

Proteomic Analysis of Salivary Extracellular Vesicles from COVID-19 Patients Reveals a Specific Anti-COVID-19 Response Protein Signature

“…Notable contributions have been made to the understanding of COVID-19 through proteomics [28][29][30][31], and several studies have explored the saliva proteome during SARS-CoV-2 infection [32][33][34]. Nevertheless, to our knowledge, this study marks the first attempt to assess extracellular EVs in saliva from COVID-19 patients, comparing them to their healthy "in-house" close contacts.…”

Recent Developments in Machine Learning for Mass Spectrometry

“…Recent work has also applied ML to classify clinical MS data. Notable examples include colorectal liver metastasis diagnosis using linear regression on Probe-ESI mass spectra, classification of nephrotic syndrome forms from kidney tissue biopsies by using desorption electrospray ionization MS and SVM, COVID screening using SVM with MALDI Fourier-transform ion cyclotron resonance (FT-ICR) mass spectra of saliva, narcotic detection in blood samples using MLPs on LC HRMS data-independent acquisition experiments, and antimicrobial resistance determination by using MALDI-TOF mass spectra with LightGBM and an MLP . In an additional example, Seddiki et al developed a transfer learning method with 1-D CNNs to examine various sample types by using a range of instruments, showcasing successful finetuning of task specific data when data is sparce …”