Bacterial species identification using MALDI-TOF mass spectrometry and machine learning techniques: A large-scale benchmarking study

Mortier, Thomas; Wieme, Anneleen D.; Vandamme, Peter; Waegeman, Willem

doi:10.1016/j.csbj.2021.11.004

Cited by 42 publications

(31 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results show that acceptable identification rates were obtained, but these numbers are typically lower than reported in studies with more limited analyses. Using hierarchical classification methods, researchers also showed that taxonomic information is generally not well preserved in MALDI-TOF mass spectrometry data [ 71 ].…”

Section: Bacteria Identificationmentioning

confidence: 99%

“Omic” Approaches to Bacteria and Antibiotic Resistance Identification

Janiszewska

Szultka‐Młyńska

Pomastowski

et al. 2022

IJMS

View full text Add to dashboard Cite

The quick and accurate identification of microorganisms and the study of resistance to antibiotics is crucial in the economic and industrial fields along with medicine. One of the fastest-growing identification methods is the spectrometric approach consisting in the matrix-assisted laser ionization/desorption using a time-of-flight analyzer (MALDI-TOF MS), which has many advantages over conventional methods for the determination of microorganisms presented. Thanks to the use of a multiomic approach in the MALDI-TOF MS analysis, it is possible to obtain a broad spectrum of data allowing the identification of microorganisms, understanding their interactions and the analysis of antibiotic resistance mechanisms. In addition, the literature data indicate the possibility of a significant reduction in the time of the sample preparation and analysis time, which will enable a faster initiation of the treatment of patients. However, it is still necessary to improve the process of identifying and supplementing the existing databases along with creating new ones. This review summarizes the use of “-omics” approaches in the MALDI TOF MS analysis, including in bacterial identification and antibiotic resistance mechanisms analysis.

show abstract

Section: Bacteria Identificationmentioning

confidence: 99%

“Omic” Approaches to Bacteria and Antibiotic Resistance Identification

Janiszewska

Szultka‐Młyńska

Pomastowski

et al. 2022

IJMS

View full text Add to dashboard Cite

show abstract

“…In most of the microbiology papers combining machine learning and MALDI-TOF, the preparation of the spectra is one of the highlights of the methodology. Delavy et al [14], Yan et al [32] and Mortier et al [33] have processed the raw data with R software allowing them to use the MALDIquant package offering several processing techniques. Apart from the main processing like smoothing, baseline subtraction and soft peak selection technique, most of the methods push the processing of the spectra to recalibration, peak extraction and normalization.…”

Section: Comparison With Other Work Coupling Maldi-tof and Machine Le...mentioning

confidence: 99%

“…The identi cation is highly dependent on this step. Articles whose method requires the use of the MALDIquant package tend to perform a peak extraction step in the pre-processing [14], [32], for feature extraction because traditional machine learning models are the most used [33]. Some research uses deep learning to lter the peaks of interest and ll the feature extraction step just before the classi cation by a machine learning model [34].…”

Section: Comparison With Other Work Coupling Maldi-tof and Machine Le...mentioning

confidence: 99%

Deep learning model coupled with proteomics to detect yeast epidemic clones across multiple hospitals

Mohammad

Normand

Nabet

et al. 2022

Preprint

View full text Add to dashboard Cite

The ongoing worldwide emergence of epidemic azole-resistant Candida parapsilosis clones is a threat to human health. In order to monitor a clonal outbreak which involved 2 hospitals in Paris, we used a technology that most clinical laboratories are equipped with: Matrix-Assisted Laser Desorption-Ionization Time of Flight mass spectrometry (MALDI-TOF MS). This physico-chemical analysis technique was combined with machine learning algorithm to evaluate the possibility of monitoring a multi-center epidemic. A total of 96 isolates of Candida parapsilosis constituted of resistant clones, susceptible clones and other susceptible isolates were cultured on various culture conditions. Spectra were acquired on four different mass spectrometers from three hospitals. We used convolutional neural networks (CNN) to classify the isolates and identified the main parameters that can influence the identification of epidemic clonal isolates. We have shown results up to 94% accuracy in a multi-center context, and between 81 and 91% accuracy when the tested site is not part of the training set, showing that it is possible to differentiate the spectra of a clone and a non-clone presenting a very strong similarity. This study shows that it is possible to monitor a certain type of clone, namely the R2 clones in our case study, using MALDI-TOF coupled to CNN. The experimental conditions that impacted the results should be considered for future work to improve performances for difficult classification tasks like clonal fungal identification.

show abstract

“…MALDI-TOF has been recognized as a fast and reliable tool to identify bacteria, once mass spectra can be viewed as species-specific fingerprints, allowing for accurate identification of purified strains at the genus and species level. 12,13…”

Section: Culture and Bacterial Identificationmentioning

confidence: 99%

Impact of alcohol gel on hand bacteria in healthcare professionals

Faria

Menezes²,

Alves³

et al. 2021

Rev Epidemiol Control Infect

View full text Add to dashboard Cite

Background and objectives: Healthcare-Associated Infections are a problem reported by hospitals worldwide, increasing patient morbidity and mortality, prolonging hospitalization, and increasing health care costs. The hands of health professionals are still the main source of infections, making hand hygiene extremely important for spreading infection control. The objective of this study was to analyze the presence of bacteria on the hands of health professionals after hygiene with alcohol gel in a Neonatal Unit and describe the resistance of microorganisms to antimicrobials. Methods: Hand samples were collected using the modified glove-juice method on both occasions, before and after hand hygiene with alcohol gel. Bacteria were identified by MALDI-TOF and susceptibility tests according to Clinical and Laboratory Standards Institute document M100-E29. Results: A total of 214 samples were obtained, of which 104 (48.6%) showed bacterial growth before hand hygiene and 52 (24.3%) after hand hygiene with alcohol gel. There were 217 isolates from the cultures, of which coagulase-negative Staphylococcus was the most frequent with 41 (27.2%) and 24 (36.4%) positive cultures, respectively before and after hand hygiene. The second most frequent microorganism was Klebsiella pneumoniae with 32 (21.2%) and 16 (24.2%), respectively before and after hand hygiene. Multidrug resistance to antimicrobials was detected in 58.1% of gram-positive bacteria and in 34.3% of gram-negative bacteria. Conclusion: A decrease was observed, but not an elimination of the microbial load after hand hygiene with alcohol gel, demonstrating the need for improvements in hand hygiene.

show abstract

Bacterial species identification using MALDI-TOF mass spectrometry and machine learning techniques: A large-scale benchmarking study

Abstract: Graphical abstract

Cited by 42 publications

References 60 publications

“Omic” Approaches to Bacteria and Antibiotic Resistance Identification

“Omic” Approaches to Bacteria and Antibiotic Resistance Identification

Deep learning model coupled with proteomics to detect yeast epidemic clones across multiple hospitals

Impact of alcohol gel on hand bacteria in healthcare professionals

Contact Info

Product

Resources

About