Data mining with graphical models

Kruse, Rudolf; Borgelt, Christian

doi:10.1007/bfb0095424

Cited by 1 publication

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PCA is an unsupervised ML method to reduce the dimensionality of a dataset comprising many interrelated variables. To explore and compare spectra in multidimensional space, PCA was conducted using the R FactoMineR 20 and factoextra 21 packages (data were scaled to unit variance). PCA was performed on all samples, and for each laboratory separately, using FS methods and without FS.…”

Section: Methodsmentioning

confidence: 99%

Detection of SARS-CoV-2 in nasal swabs using MALDI-MS

et al. 2020

View full text Add to dashboard Cite

Detection of SARS-CoV-2 using RT-PCR and other advanced methods can achieve high accuracy. However, their application is limited in countries that lack sufficient resources to handle large-scale testing during the COVID-19 pandemic. Here, we describe a method to detect SARS-CoV-2 in nasal swabs using matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) and machine learning analysis. This approach uses equipment and expertise commonly found in clinical laboratories in developing countries. We obtained mass spectra from a total of 362 samples (211 SARS-CoV-2-positive and 151 negative by RT-PCR) without prior sample preparation from three different laboratories. We tested two feature selection methods and six machine learning approaches to identify the top performing analysis approaches and determine the accuracy of SARS-CoV-2 detection. The support vector machine model provided the highest accuracy (93.9%), with 7% false positives and 5% false negatives. Our results suggest that MALDI-MS and machine learning analysis can be used to reliably detect SARS-CoV-2 in nasal swab samples. The outbreak of coronavirus disease 2019 (COVID-19) is a crisis that affects rich and poor countries alike 1. Detection of SARS-CoV-2 in patient samples is a critical tool for monitoring spread of the disease, guiding therapeutic decisions and devising social distancing protocols 2. Detection assays based on RT-PCR are the most effective and sensitive method for diagnosis of SARS-CoV-2 infection and are used in laboratories around the world 3. However, some countries lack the laboratory resources and access to PCR kits to conduct testing at the required levels. Therefore, other reliable diagnostic techniques are needed. Most clinical diagnostic laboratories have MALDI-MS equipment, which is used to identify bacterial and fungal infections. We propose to leverage the ease-of-use and robustness of MALDI-MS pathogen identification for large-scale SARS-CoV-2 testing in developing countries. MALDI-MS-based assays rely on reference spectra of strains and bioinformatics for high-sensitivity and high-specificity species identification through proteomic profiling. This approach is well established and accepted in many countries for routine diagnostics of yeast and bacterial infections. However, no spectral libraries for SARS-CoV-2 identification using MALDI-MS are publicly available to our knowledge. We first acquired MALDI mass spectra of nasal swab samples that had been tested for SARS-CoV-2 by RT-PCR and analyzed them using machine learning (ML). In this experiment (Fig. 1a), a total of 362 samples (211 SARS-CoV-2-positive and 151 negative, unequivocally confirmed by PCR), which came from three different countries, Argentina (Lab 1), Chile (Lab 2) and Peru (Lab 3), were placed on the MALDI plate without prior sample purification.

show abstract

Section: Methodsmentioning

confidence: 99%