Identification of triazole-resistant Candida tropicalis based on MALDI-TOF MS platform and machine learning algorithm
10.19405/j.cnki.issn1000-1492.2022.05.024
- Author:
Jinyu Wang
1
;
Ke Zhang
1
;
Cuiping Xia
1
;
Zhongxin Wang
1
Author Information
1. Dept of Clinical Laboratory , The First Afiliated Hospital of Anhui Medical University, Hefei 230022
- Publication Type:Journal Article
- Keywords:
matrix⁃assisted laser desorption/ionization⁃time⁃of⁃flight mass spectrometry;
machine learning algo⁃ rithms;
Candida tropicalis;
support vector machine;
random forest algorithm
- From:
Acta Universitatis Medicinalis Anhui
2022;57(5):801-804
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To rapidly identify triazole(fluconazole, voliconazole, iriconazole) drug resistance and sensitiveCandida tropicalusing matrix-assisted laser desorption/ionization-time-of-flight mass spectrometry(MALDI-TOF MS) platform data analysis and machine learning algorithms.
Methods:A total of 191Candida tropicalwere collected from various clinical specimens, 71 of which were triazole-resistantCandida tropicaland 120 were triazole-sensitiveCandida tropicalstrains. Data acquisition was performed using the MALDI-TOF MS platform, and the mass and charge ratio features of resistant and susceptible strains were classified and selected based on the Mann-Whitney Rank-sum Test(Mann-WhitneyU-test) and the importance score obtained by the Random Forest(RF) algorithm. The classification model was constructed using the RF algorithm and a nonlinear support vector machine with a radial basis function kernel(RBF-SVM), calculating the accuracy, sensitivity, specificity, F1 value and the area under the subject worker curve(AUC) of the RBF-SVM model under the same experimental data to evaluate the model discrimination performance.
Results:All strains obtained 76 unique mass spectrum peaks after analysis on the MALDI-TOF MS platform. Among them, six peaks 3 481,7 549,6 500,3 048,6 892,2 596 m/z were selected as the model feature peaks established by the feature dimensionality reduction treatment. The accuracy of both the RBF-SVM and RF models was 0.84, and the AUC scores were 0.930 5 and 0.927 3, respectively.
Conclusion:Machine learning algorithms combined with the MALDI-TOF MS platform for data analysis can serve as a possible method to rapidly distinguish triazole-resistantCandida tropicaland triazole-sensitive strains.
- Full text:2025022015382346398基于MALDI-TOF_M...算法鉴别三唑耐药热带念珠菌_王金宇.pdf
