Rapid Detection of COVID-19 Using MALDI-TOF-Based Serum Peptidome Profiling

Area of Science:

• Biochemistry
• Proteomics
• Mass Spectrometry

Background:

• The ongoing coronavirus disease 2019 (COVID-19) pandemic necessitates rapid and accurate diagnostic tools.
• Current diagnostic methods like PCR and immunoassays have limitations, including false negatives and diagnostic delays.
• Effective disease detection is crucial for isolating infected individuals and controlling SARS-CoV-2 spread.

Purpose of the Study:

• To develop and validate a high-throughput serum peptidome profiling method for efficient COVID-19 detection.
• To evaluate the performance of machine learning models in classifying COVID-19 cases based on serum peptidome data.
• To establish a potential diagnostic tool for large-scale screening and surveillance of COVID-19.

Main Methods:

• Serum samples from 146 COVID-19 patients and 152 controls were analyzed using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS).
• Peptidome profiling data underwent processing and feature selection.
• Eight machine learning algorithms were employed to build classification models for COVID-19 detection.

Main Results:

• A logistic regression model utilizing 25 feature peaks demonstrated high diagnostic accuracy.
• The model achieved 99% accuracy, 98% sensitivity, and 100% specificity in detecting COVID-19.
• The method effectively distinguished COVID-19 patients from various control groups.

Conclusions:

• Serum peptidome profiling via MALDI-TOF MS is a promising method for COVID-19 detection.
• The developed machine learning model shows significant potential for high-throughput screening and routine surveillance.
• This approach can contribute to effective pandemic control strategies by enabling rapid and accurate diagnosis in large populations.