SVM Classification Model of Similar Bacteria Species using Negative Marker: Based on Matrix-Assisted Laser Desorption/Ionization Time-of-Flight Mass Spectrometry

Lee, Jongseo; Shin, Yoonsu; Kim, Songkuk; Rho, Kyoohyoung; Park, Kyu H.

doi:10.1109/bibe.2017.00-64

Cited by 4 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After choosing the best machine learning model based on the AUC performance in a 5-fold CV with the default parameter setting, we further tuned the hyperparameter in the 5-fold CV and trained the final model with the best tuned hyperparameter and all subset data. Most studies investigating MS spectra used decision trees (DT) ( 14 ), RF ( 28 , 29 ), SVM ( 14 , 28 , 30 – 33 ), neural network (NN) ( 32 , 34 ), and k-nearest neighbor (KNN) ( 14 , 28 ). In our study, after clustering, we tested four machine learning methods (LR, SVM, RF, and XGBoost) to classify the resistance of CIP in a 5-fold CV with default parameter settings.…”

Section: Methodsmentioning

confidence: 99%

Data-Driven Two-Stage Framework for Identification and Characterization of Different Antibiotic-Resistant Escherichia coli Isolates Based on Mass Spectrometry Data

et al. 2023

View full text Add to dashboard Cite

Based on a large amount of matrix-assisted laser desorption ionization–time-of-flight mass spectrometry (MALDI-TOF MS) clinical data, comprising 37,918 Escherichia coli isolates, a data-driven two-stage framework was established to evaluate the antimicrobial resistance of E. coli . Five antibiotics, including amoxicillin (AMC), ceftazidime (CAZ), ciprofloxacin (CIP), ceftriaxone (CRO), and cefuroxime (CXM), were considered for the two-stage model training, and the values of the area under the receiver operating characteristic curve (AUC) were 0.62 for AMC, 0.72 for CAZ, 0.87 for CIP, 0.72 for CRO, and 0.72 for CXM.

show abstract

Section: Methodsmentioning

confidence: 99%

Data-Driven Two-Stage Framework for Identification and Characterization of Different Antibiotic-Resistant Escherichia coli Isolates Based on Mass Spectrometry Data

et al. 2023

View full text Add to dashboard Cite

show abstract

“…These create a specific microbial fingerprint (a peptide mass fingerprint) allowing identification upon comparison with databases. The whole process takes only minutes and can distinguish even between the most closely related microbial species (Bader et al, 2011;Hendrickx et al, 2011;Lee et al, 2017;Rychert, 2019) and detect antimicrobial resistance (Burckhardt and Zimmermann, 2018;Florio et al, 2020). However, the procedure involves multiple-step-sample preparation and relatively costly consumables.…”

Section: Mass Spectrometrymentioning

confidence: 99%

Raman Spectroscopy—A Novel Method for Identification and Characterization of Microbes on a Single-Cell Level in Clinical Settings

Rebrošová

Samek

Kizovský

et al. 2022

Front. Cell. Infect. Microbiol.

View full text Add to dashboard Cite

Rapid and accurate identification of pathogens causing infections is one of the biggest challenges in medicine. Timely identification of causative agents and their antimicrobial resistance profile can significantly improve the management of infection, lower costs for healthcare, mitigate ever-growing antimicrobial resistance and in many cases, save lives. Raman spectroscopy was shown to be a useful—quick, non-invasive, and non-destructive —tool for identifying microbes from solid and liquid media. Modifications of Raman spectroscopy and/or pretreatment of samples allow single-cell analyses and identification of microbes from various samples. It was shown that those non-culture-based approaches could also detect antimicrobial resistance. Moreover, recent studies suggest that a combination of Raman spectroscopy with optical tweezers has the potential to identify microbes directly from human body fluids. This review aims to summarize recent advances in non-culture-based approaches of identification of microbes and their virulence factors, including antimicrobial resistance, using methods based on Raman spectroscopy in the context of possible use in the future point-of-care diagnostic process.

show abstract

“…In the field of microbiology, several studies have shown how the combination of ML algorithms with mass spectra information can enhance discrimination between closely related sublineages within the genera Mycobacterium [8] and Bacillus [9,10], as well as the identification of different antimicrobial resistant groups of Staphylococcus aureus [11,12].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Algorithms for Classification of MALDI-TOF MS Spectra from Phylogenetically Closely Related Species Brucella melitensis, Brucella abortus and Brucella suis

et al. 2022

View full text Add to dashboard Cite

(1) Background: MALDI-TOF mass spectrometry (MS) is the gold standard for microbial fingerprinting, however, for phylogenetically closely related species, the resolution power drops down to the genus level. In this study, we analyzed MALDI-TOF spectra from 44 strains of B. melitensis, B. suis and B. abortus to identify the optimal classification method within popular supervised and unsupervised machine learning (ML) algorithms. (2) Methods: A consensus feature selection strategy was applied to pinpoint from among the 500 MS features those that yielded the best ML model and that may play a role in species differentiation. Unsupervised k-means and hierarchical agglomerative clustering were evaluated using the silhouette coefficient, while the supervised classifiers Random Forest, Support Vector Machine, Neural Network, and Multinomial Logistic Regression were explored in a fine-tuning manner using nested k-fold cross validation (CV) with a feature reduction step between the two CV loops. (3) Results: Sixteen differentially expressed peaks were identified and used to feed ML classifiers. Unsupervised and optimized supervised models displayed excellent predictive performances with 100% accuracy. The suitability of the consensus feature selection strategy for learning system accuracy was shown. (4) Conclusion: A meaningful ML approach is here introduced, to enhance Brucella spp. classification using MALDI-TOF MS data.

show abstract

SVM Classification Model of Similar Bacteria Species using Negative Marker: Based on Matrix-Assisted Laser Desorption/Ionization Time-of-Flight Mass Spectrometry

Cited by 4 publications

References 19 publications

Data-Driven Two-Stage Framework for Identification and Characterization of Different Antibiotic-Resistant Escherichia coli Isolates Based on Mass Spectrometry Data

Data-Driven Two-Stage Framework for Identification and Characterization of Different Antibiotic-Resistant Escherichia coli Isolates Based on Mass Spectrometry Data

Raman Spectroscopy—A Novel Method for Identification and Characterization of Microbes on a Single-Cell Level in Clinical Settings

Machine Learning Algorithms for Classification of MALDI-TOF MS Spectra from Phylogenetically Closely Related Species Brucella melitensis, Brucella abortus and Brucella suis

Contact Info

Product

Resources

About