» Articles » PMID: 35323675

Machine Learning Approaches to Identify Discriminative Signatures of Volatile Organic Compounds (VOCs) from Bacteria and Fungi Using SPME-DART-MS

Overview
Journal Metabolites
Publisher MDPI
Date 2022 Mar 24
PMID 35323675
Authors
Affiliations
Soon will be listed here.
Abstract

Point-of-care screening tools are essential to expedite patient care and decrease reliance on slow diagnostic tools (e.g., microbial cultures) to identify pathogens and their associated antibiotic resistance. Analysis of volatile organic compounds (VOC) emitted from biological media has seen increased attention in recent years as a potential non-invasive diagnostic procedure. This work explores the use of solid phase micro-extraction (SPME) and ambient plasma ionization mass spectrometry (MS) to rapidly acquire VOC signatures of bacteria and fungi. The MS spectrum of each pathogen goes through a preprocessing and feature extraction pipeline. Various supervised and unsupervised machine learning (ML) classification algorithms are trained and evaluated on the extracted feature set. These are able to classify the type of pathogen as bacteria or fungi with high accuracy, while marked progress is also made in identifying specific strains of bacteria. This study presents a new approach for the identification of pathogens from VOC signatures collected using SPME and ambient ionization MS by training classifiers on just a few samples of data. This ambient plasma ionization and ML approach is robust, rapid, precise, and can potentially be used as a non-invasive clinical diagnostic tool for point-of-care applications.

Citing Articles

Rapid bacterial identification through volatile organic compound analysis and deep learning.

Yan B, Zeng L, Lu Y, Li M, Lu W, Zhou B BMC Bioinformatics. 2024; 25(1):347.

PMID: 39506632 PMC: 11539783. DOI: 10.1186/s12859-024-05967-4.


A Mass Spectrometry-Machine Learning Approach for Detecting Volatile Organic Compound Emissions for Early Fire Detection.

Kingsley S, Xu Z, Jones B, Saleh J, Orlando T J Am Soc Mass Spectrom. 2023; 34(5):826-835.

PMID: 37079759 PMC: 10161216. DOI: 10.1021/jasms.2c00304.


Population-Specific Plant-To-Plant Signaling in Wild Lima Bean.

Grof-Tisza P, Morelon S, Desurmont G, Benrey B Plants (Basel). 2022; 11(18).

PMID: 36145728 PMC: 9503452. DOI: 10.3390/plants11182320.

References
1.
Zamkah A, Hui T, Andrews S, Dey N, Shi F, Sherratt R . Identification of Suitable Biomarkers for Stress and Emotion Detection for Future Personal Affective Wearable Sensors. Biosensors (Basel). 2020; 10(4). PMC: 7235866. DOI: 10.3390/bios10040040. View

2.
Leong S, Leong Y, Tan E, Sim H, Koh C, Lee Y . Noninvasive and Point-of-Care Surface-Enhanced Raman Scattering (SERS)-Based Breathalyzer for Mass Screening of Coronavirus Disease 2019 (COVID-19) under 5 min. ACS Nano. 2022; 16(2):2629-2639. DOI: 10.1021/acsnano.1c09371. View

3.
Huang Y, Doh I, Bae E . Design and Validation of a Portable Machine Learning-Based Electronic Nose. Sensors (Basel). 2021; 21(11). PMC: 8201040. DOI: 10.3390/s21113923. View

4.
Reali S, Najib E, Treuerne Balazs K, Chern Hui Tan A, Varadi L, Hibbs D . Novel diagnostics for point-of-care bacterial detection and identification. RSC Adv. 2022; 9(37):21486-21497. PMC: 9066158. DOI: 10.1039/c9ra03118a. View

5.
Kusano M, Mendez E, Furton K . Comparison of the volatile organic compounds from different biological specimens for profiling potential. J Forensic Sci. 2012; 58(1):29-39. DOI: 10.1111/j.1556-4029.2012.02215.x. View