Enhanced classification and identification of bacterial and viral microorganisms by integration of MALDI-TOF mass spectrometry with artificial intelligence

This study explores the integration of Matrix-Assisted Laser Desorption Ionization Time-Of-Flight (MALDI-TOF) mass spectrometry with artificial intelligence techniques to enhance the classification and identification of bacterial and viral microorganisms. By training eight Machine Learning (ML) and two Deep Learning (DL) models using 5-fold cross-validation on a dataset of 255 MALDI-TOF mass spectra from seven cultured bacteria and five viral agents, the research demonstrates that up to seven models achieved robust classification across various tasks, including binary classification of viruses from bacteria and Gram-positive from Gram-negative bacteria, as well as multi-class classification of individual bacterial and viral species.

The Extra Trees Classifier, Support Vector Classifier, and 1-D Convolutional Neural Network were subsequently cross-validated on an external dataset from a large MALDI-TOF MS database of highly pathogenic bacteria. The Extra Trees Classifier consistently achieved the highest average accuracy and F1-score in both Gram type classification and species-level identification, demonstrating superior generalization across datasets.

This research highlights the potential of this model to improve MALDI-TOF-based classification frameworks in clinical microbiology and biodefense applications, particularly in the context of Biological Warfare Agents (BWA) and the need for robust response capabilities to mitigate the threat of biological weapons.

Brief written by urgent.news from Scientific Reports's own syndicated text. Machine-written — may contain errors; check the original before relying on it.