Validation of a MALDI-TOF MS method for SARS-CoV-2 detection on the Bruker Biotyper and nasopharyngeal swabs. A Brazil - UK collaborative study.
Keywords: infectious diseases
We had developed a MALDI-TOF mass spectrometry method for detection of SARS-CoV-2 virus in saliva-gargle samples using Shimadzu MALDI-TOF mass spectrometers in the UK. This was validated in the USA to CLIA-LDT standards for asymptomatic infection detection remotely via sharing protocols, shipping key reagents, video conference and data exchange. In Brazil, more so than in the UK and USA, there is a need to develop non-PCR dependent rapid affordable SARS-CoV-2 infection screening tests, which also identify variant SARS-CoV-2 and other virus infections. Travel restrictions necessitated remote collaboration with validation on the available Clinical MALDI-TOF – the Bruker Biotyper (microflex® LT/SH) – and on nasopharyngeal swab samples, as salivary gargle samples were not available. The Bruker Biotyper was shown to be almost log10^3 more sensitive at detection of high molecular weight spike proteins. A protocol for saline swab soaks out was developed and duplicate swab samples collected in Brazil were analysed by MALDI-TOF MS. The swab collected sample spectra varied from that of gargle-saliva in three additional mass peaks in the mass region expected for IgG heavy chains and human serum albumin. A subset of clinical samples with additional high mass, probably Spike-related proteins, were also found. Spectral data comparisons and analysis, subjected to machine learning algorithms in order to resolve RT-qPCR positive from RT-qPCR negative swab samples, showed a 78% agreement with RT-qPCR scoring for SARS-CoV-2 infection.
An Explainable-AI approach for Diagnosis of COVID-19 using MALDI-ToF Mass Spectrometry
Keywords: LearningArtificial Intelligence
Authors: Venkata Devesh Reddy SeethiZane LaCassePrajkta ChivteJoshua BlandShrihari S. KadkolElizabeth R. GaillardPratool BhartiHamed Alhoori
The severe acute respiratory syndrome coronavirus type-2 (SARS-CoV-2) caused a global pandemic and imposed immense effects on the global economy. Accurate, cost-effective, and quick tests have proven substantial in identifying infected people and mitigating the spread. Recently, multiple alternative platforms for testing coronavirus disease 2019 (COVID-19) have been published that show high agreement with current gold standard real-time polymerase chain reaction (RT-PCR) results. These new methods do away with nasopharyngeal (NP) swabs, eliminate the need for complicated reagents, and reduce the burden on RT-PCR test reagent supply. In the present work, we have designed an artificial intelligence-based (AI) testing method to provide confidence in the results. Current AI applications to COVID-19 studies often lack a biological foundation in the decision-making process, and our AI approach is one of the earliest to leverage explainable-AI (X-AI) algorithms for COVID-19 diagnosis using mass spectrometry. Here, we have employed X-AI to explain the decision-making process on a local (per-sample) and global (all samples) basis underscored by biologically relevant features. We evaluated our technique with data extracted from human gargle samples and achieved a testing accuracy of 94.44%. Such techniques would strengthen the relationship between AI and clinical diagnostics by providing biomedical researchers and healthcare workers with trustworthy and, most importantly, explainable test results.
A la carte, Streptococcus pneumoniae capsular typing: using MALDI-TOF mass spectrometry and machine learning algorithms as complementary tools for the determination of PCV13 serotypes and the most prevalent NON PCV13 serotypes according to Argentina's epidemiology.
Laboratory surveillance of Streptococcus pneumoniae serotypes is crucial for the successful implementation of vaccines to prevent invasive pneumococcal diseases. The reference method of serotyping is the Quellung reaction, which is labor-intensive and expensive.In the last few years, the introduction of MALDI-TOF MS into the microbiology laboratory has been revolutionary. In brief, this new technology compares protein profiles by generating spectra based on the mass to charge ratio (m/z).We evaluated the performance of MALDI-TOF MS for typing serotypes of S. pneumoniae isolates included in the PCV13 vaccine using a machine learning approach. We challenged our classification algorithms in “real time” with a total of new 100 isolates of S. pneumoniae from Argentinian nationwide surveillance.In this work, it was possible to demonstrate that the combination of MALDI-TOF mass spectrometry and multivariate analysis allows the development of new strategies for the identification and characterization of Spn isolates of clinical importance; and we consider that by using AI, as more data becomes available the models will get better and more precise.