Exploratory Study on Application of MALDI-TOF-MS to Detect SARS-CoV-2 Infection in Human Saliva

SARS-CoV-2 has caused a large outbreak since its emergence in December 2019. COVID-19 diagnosis became a priority so as to isolate and treat infected individuals in order to break the contamination chain. Currently, the reference test for COVID-19 diagnosis is the molecular detection (RT-qPCR) of the virus from nasopharyngeal swab (NPS) samples. Although this sensitive and specific test remains the gold standard, it has several limitations, such as the invasive collection method, the relative high cost and the duration of the test. Moreover, the material shortage to perform tests due to the discrepancy between the high demand for tests and the production capacities puts additional constraints on RT-qPCR. Here, we propose a PCR-free method for diagnosing SARS-CoV-2 based on matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) profiling and machine learning (ML) models from salivary samples. Kinetic saliva samples were collected at enrollment and ten and thirty days later (D0, D10 and D30), to assess the classification performance of the ML models compared to the molecular tests performed on NPS specimens. Spectra were generated using an optimized protocol of saliva collection and successive quality control steps were developed to ensure the reliability of spectra. A total of 360 averaged spectra were included in the study. At D0, the comparison of MS spectra from SARS-CoV-2 positive patients (n = 105) with healthy healthcare controls (n = 51) revealed nine peaks that significantly distinguished the two groups. Among the five ML models tested, support vector machine with linear kernel (SVM-LK) provided the best performance on the training dataset (accuracy = 85.2%, sensitivity = 85.1%, specificity = 85.3%, F1-Score = 85.1%). The application of the SVM-LK model on independent datasets confirmed its performances with 88.9% and 80.8% of correct classification for samples collected at D0 and D30, respectively. Conversely, at D10, the proportion of correct classification had fallen to 64.3%. The analysis of saliva samples by MALDI-TOF MS and ML appears as an interesting supplementary tool for COVID-19 diagnosis, despite the mitigated results obtained for convalescent patients (D10).

Download Full-text

Exploratory Study on Application of MALDI-TOF-MS to Detect SARS-CoV-2 Infection in Human Saliva

10.20944/preprints202109.0426.v1 ◽

2021 ◽

Author(s):

Monique Melo Costa ◽

Hugo Martin ◽

Bertrand Estellon ◽

François-Xavier Dupé ◽

Floriant Saby ◽

...

Keyword(s):

Human Saliva ◽

Classification Performance ◽

Training Dataset ◽

Support Vector ◽

Nasopharyngeal Swab ◽

Correct Classification ◽

Specific Test ◽

Maldi Tof Ms ◽

Maldi Tof ◽

Tof Ms

SARS-CoV-2 caused a large outbreak since its emergence in December 2019. The COVID-19 diagnosis became a priority to isolate and treat infected individuals in order to break the contamination chain. Currently, the reference test for COVID-19 diagnosis is the molecular detection (RT-qPCR) of the virus from nasopharyngeal swab (NPS) samples. Although this sensitive and specific test remains the gold standard, it has several limitations, such as the invasive collection method, the relative high cost and the duration of the test. Moreover, the material shortage to perform tests due to the discrepancy between the high demand for tests and the production capacities puts additional constraints on RT-qPCR. Here, we propose a PCR-free method for diagnosing SARS-CoV-2 based on Matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) profiling and machine learning (ML) models from salivary samples. Kinetic saliva samples were collected at enrollment and ten and thirty days later (D0, D10 and D30), to assess the classification performance of the ML models compared to the molecular tests performed on NPS specimens. Spectra were generated using an optimized protocol of saliva collection and successive quality control steps were developed to ensure the reliability of spectra. A total of 360 averaged spectra were included in the study. At D0, the comparison of MS spectra from SARS-CoV-2 positive patients (n=105) with healthy healthcare controls (n=51) revealed nine peaks that significantly distinguished the two groups. Among the five ML models tested, Support Vector Machine with Linear Kernel (SVM-LK) provided the best performance on the training dataset (accuracy = 85.2 %, sensitivity = 85.1 %, specificity = 85.3 %, F1-Score = 85.1 %). The application of the SVM-LK model on independent datasets confirmed it performances with 88.9% and 80.8% of correct classification for samples collected at D0 and D30, respectively. Conversely, at D10, the proportion of correct classification fallen to 64.3%. The analysis of saliva samples by MALDI-TOF MS and ML appears as an interesting supplementary tool for COVID-19 diagnosis, despite the mitigated results obtained for convalescent patients (D10).

Download Full-text

Implementation of MALDI-TOF Mass Spectrometry and Peak Analysis: Application to the Discrimination of Cryptococcus neoformans Species Complex and Their Interspecies Hybrids

Journal of Fungi ◽

10.3390/jof6040330 ◽

2020 ◽

Vol 6 (4) ◽

pp. 330

Author(s):

Margarita E. Zvezdanova ◽

Manuel J. Arroyo ◽

Gema Méndez ◽

Jesús Guinea ◽

Luis Mancera ◽

...

Keyword(s):

Mass Spectrometry ◽

Support Vector Machine ◽

Cryptococcus Neoformans ◽

Support Vector ◽

Its2 Region ◽

Maldi Tof Ms ◽

Maldi Tof ◽

Interspecies Hybrids ◽

Correct Discrimination ◽

Tof Ms

Matrix-assisted laser desorption–ionization/time of flight mass spectrometry (MALDI-TOF MS) has been widely implemented for the rapid identification of microorganisms. Although most bacteria, yeasts and filamentous fungi can be accurately identified with this method, some closely related species still represent a challenge for MALDI-TOF MS. In this study, two MALDI-TOF-based approaches were applied for discrimination at the species-level of isolates belonging to the Cryptococcus neoformans complex, previously characterized by Amplified Fragment Length Polymorphism (AFLP) and sequencing of the ITS1-5.8S-ITS2 region: (i) an expanded database was built with 26 isolates from the main Cryptococcus species found in our setting (C. neoformans, C. deneoformans and AFLP3 interspecies hybrids) and (ii) peak analysis and data modeling were applied to the protein spectra of the analyzed Cryptococcus isolates. The implementation of the in-house database did not allow for the discrimination of the interspecies hybrids. However, the performance of peak analysis with the application of supervised classifiers (partial least squares-discriminant analysis and support vector machine) in a two-step analysis allowed for the 96.95% and 96.55% correct discrimination of C. neoformans from the interspecies hybrids, respectively. In addition, PCA analysis prior to support vector machine (SVM) provided 98.45% correct discrimination of the three analyzed species in a one-step analysis. This novel method is cost-efficient, rapid and user-friendly. The procedure can also be automatized for an optimized implementation in the laboratory routine.

Download Full-text

Discrimination among Cryptococcus deneoformans, C. neoformans and interspecies hybrids using MALDI-TOF Mass Spectrometry

10.1101/2020.03.13.991661 ◽

2020 ◽

Author(s):

Margarita Estreya Zvezdanova ◽

Manuel J. Arroyo ◽

Gema Méndez ◽

Jesús Guinea ◽

Luis Mancera ◽

...

Keyword(s):

Hierarchical Clustering ◽

Support Vector ◽

Correct Identification ◽

Differential Analysis ◽

Maldi Tof Ms ◽

Maldi Tof ◽

Interspecies Hybrids ◽

Protein Spectra ◽

Correct Discrimination ◽

Tof Ms

ABSTRACTBackgroundDifferentiation of the species within the Cryptococcus neoformans complex (C. deneoformans, C. neoformans and C. neoformans interspecies hybrids –C. deneoformans x C. neoformans-) is important to define the epidemiology of the infection.ObjectivesIn this study we attempted the discrimination of three C. neoformans species using MALDI-TOF MS coupled with an in-house library.MethodsAll Cryptococcus spp. isolates were identified by AFLP markers. An in-house database was constructed 26 well characterized C. deneoformans, C. neoformans and interspecies hybrids. Forty-four Cryptococcus spp. isolates were blindly identified using MALDI-TOF MS (Bruker Daltonics) and the expanded library. Their protein spectra were also submitted to hierarchical clustering and the resulting species were verified via Partial Least Squares Differential Analysis (PLS-DA) and Support-Vector Machine (SVM).ResultsMALDI-TOF MS coupled with the in-house library allowed 100% correct identification of C. deneoformans and C. neoformans but misidentified the interspecies hybrids. The same level of discrimination among C. deneoformans and C. neoformans was achieved applying SVM. The application of the PLS-DA and SVM algorithms in a two-step analysis allowed 96.95% and 96.55% correct discrimination of C. neoformans from the interspecies hybrids, respectively. Besides, PCA analysis prior to SVM provided 98.45% correct discrimination of the 3 species analysed in a one-step analysis.ConclusionsOur results indicate that MALDI-TOF MS could be a rapid and reliable tool for the correct discrimination of C. deneoformans and C. neoformans. The correct identification of the interspecies hybrids could only be achieved by hierarchical clustering with other protein spectra from the same species.

Download Full-text

Optimization and Standardization of Human Saliva Collection for MALDI-TOF MS

Diagnostics ◽

10.3390/diagnostics11081304 ◽

2021 ◽

Vol 11 (8) ◽

pp. 1304

Author(s):

Monique Melo Costa ◽

Nicolas Benoit ◽

Florian Saby ◽

Bruno Pradines ◽

Samuel Granjeaud ◽

...

Keyword(s):

Low Cost ◽

Storage Conditions ◽

Human Saliva ◽

Learning Approaches ◽

Sample Collection ◽

Maldi Tof Ms ◽

Maldi Tof ◽

Key Factor ◽

Diagnosis Method ◽

Tof Ms

SARS-CoV-2 outbreak led to unprecedented innovative scientific research to preclude the virus dissemination and limit its impact on life expectancy. Waiting for the collective immunity by vaccination, mass-testing, and isolation of positive cases remain essential. The development of a diagnosis method requiring a simple and non-invasive sampling with a quick and low-cost approach is on demand. We hypothesized that the combination of saliva specimens with MALDI-TOF MS profiling analyses could be the winning duo. Before characterizing MS saliva signatures associated with SARS-CoV-2 infection, optimization and standardization of sample collection, preparation and storage up to MS analyses appeared compulsory. In this view, successive experiments were performed on saliva from healthy healthcare workers. Specimen sampling with a roll cotton of Salivette® devices appeared the most appropriate collection mode. Saliva protein precipitation with organic buffers did not improved MS spectra profiles compared to a direct loading of samples mixed with acetonitrile/formic acid buffer onto MS plate. The assessment of sample storage conditions and duration revealed that saliva should be stored on ice until MS analysis, which should occur on the day of sampling. Kinetic collection of saliva highlighted reproducibility of saliva MS profiles over four successive days and also at two-week intervals. The intra-individual stability of saliva MS profiles should be a key factor in the future investigation for biomarkers associated with SARS-CoV-2 infection. However, the singularity of MS profiles between individuals will require the development of sophisticated bio-statistical analyses such as machine learning approaches. MALDI-TOF MS profiling of saliva could be a promising PCR-free tool for SARS-CoV-2 screening.

Download Full-text

Two Classifiers Based on Serum Peptide Pattern for Prediction of HBV-Induced Liver Cirrhosis Using MALDI-TOF MS

BioMed Research International ◽

10.1155/2013/814876 ◽

2013 ◽

Vol 2013 ◽

pp. 1-7 ◽

Cited By ~ 3

Author(s):

Yuan Cao ◽

Kun He ◽

Ming Cheng ◽

Hai-Yan Si ◽

He-Lin Zhang ◽

...

Keyword(s):

Liver Cirrhosis ◽

Reference Method ◽

Invasive Procedure ◽

Serum Biomarkers ◽

Supervised Machine Learning ◽

Support Vector ◽

Maldi Tof Ms ◽

Maldi Tof ◽

Peptide Pattern ◽

Tof Ms

Chronic infection with hepatitis B virus (HBV) is associated with the majority of cases of liver cirrhosis (LC) in China. Although liver biopsy is the reference method for evaluation of cirrhosis, it is an invasive procedure with inherent risk. The aim of this study is to discover novel noninvasive specific serum biomarkers for the diagnosis of HBV-induced LC. We performed bead fractionation/MALDI-TOF MS analysis on sera from patients with LC. Thirteen feature peaks which had optimal discriminatory performance were obtained by using support-vector-machine-(SVM-) based strategy. Based on the previous results, five supervised machine learning methods were employed to construct classifiers that discriminated proteomic spectra of patients with HBV-induced LC from those of controls. Here, we describe two novel methods for prediction of HBV-induced LC, termed LC-NB and LC-MLP, respectively. We obtained a sensitivity of 90.9%, a specificity of 94.9%, and overall accuracy of 93.8% on an independent test set. Comparisons with the existing methods showed that LC-NB and LC-MLP held better accuracy. Our study suggests that potential serum biomarkers can be determined for discriminating LC and non-LC cohorts by using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry. These two classifiers could be used for clinical practice in HBV-induced LC assessment.

Download Full-text

Rapid and reproducible MALDI-TOF-based method for detection Vancomycin-resistant Enterococcus faecium using classifying algorithms

10.1101/2021.06.23.449689 ◽

2021 ◽

Author(s):

Ana Candela ◽

Manuel J Arroyo ◽

Angela Sanchez-Molleda ◽

Gema Méndez ◽

David Rodriguez-Temporal ◽

...

Keyword(s):

Enterococcus Faecium ◽

Principal Component ◽

Resistance Mechanisms ◽

Support Vector ◽

Accurate Identification ◽

Maldi Tof Ms ◽

Maldi Tof ◽

Vancomycin Resistant ◽

Lower Variability ◽

Tof Ms

Vancomycin-resistant Enterococcus faecium has become a health threat over the last 20 years due to its ability to rapidly spread and cause outbreaks in hospital settings. Although MALDI-TOF MS has already demonstrated its usefulness for accurate identification of E. faecium, its implementation for antimicrobial resistance detection is still under evaluation. The reproducibility of MALDI-TOF MS for peak analysis and its performance for correct discrimination of vancomycin susceptible isolates (VSE) from those hosting the VanA and VanB resistance mechanisms was evaluated in this study. For the first goal, intra-spot, inter-spot -technical- and inter-day -biological- reproducibility was assayed. The capability of MALDI-TOF to discriminate VSE isolates from VanA VRE and VanB VRE strains was carried out on protein spectra from 178 E. faecium unique clinical isolates -92 VSE, 31 VanA VRE, 55 VanB VRE-, processed with Clover MS Data Analysis software. Unsupervised (Principal Component Analysis –PCA-) and supervised algorithms (Support Vector Machine -SVM-, Random Forest -RF- and Partial Least Squares-Discriminant Analysis -PLS-DA-) were applied. The reproducibility assay showed lower variability for normalized data (p<0.0001) and for the peaks within the 3000-9000 m/z range. Besides, 80.9%, 79.21% and 77.53% VSE vs VRE (VanA + VanB) discrimination was achieved by applying SVM, RF and PLS-DA, respectively. Correct differentiation of VanA from VanB VRE isolates was obtained by SVM in 86.65% cases. The implementation MALDI-TOF MS and peak analysis could represent a rapid and effective tool for VRE screening. However, further improvements are needed to increase the accuracy of this approach.

Download Full-text