Towards Accurate Identification of Antibiotic-Resistant Pathogens through the Ensemble of Multiple Preprocessing Methods Based on MALDI-TOF Spectra

• Published in: International journal of molecular sciences 2023-01, Vol.24 (2), p.998
• Main Authors: Chung, Chia-Ru, Wang, Hsin-Yao, Chou, Po-Han, Wu, Li-Ching, Lu, Jang-Jih, Horng, Jorng-Tzong, Lee, Tzong-Yi
• Format: Article
• Language: English
• Subjects: Accuracy; Acinetobacter baumannii - chemistry; Acinetobacter Infections; Algorithms; Anti-Bacterial Agents - pharmacology; Antibiotic resistance; Antibiotics; Bacteria; Bacterial infections; Bayes Theorem; Bayesian analysis; Classification; Continuous wavelet transform; Drug resistance; Feature selection; Health care facilities; Humans; Ions; Laboratories; Machine learning; MALDI-TOF MS; Mass spectrometry; Mass spectroscopy; Methods; Microorganisms; Open source software; Peptides; Prediction models; Preprocessing; Spectra; Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization - methods; Support vector machines; Wavelet transforms
• ISSN: 1422-0067; 1661-6596; 1422-0067
• DOI: 10.3390/ijms24020998

Matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) mass spectrometry (MS) has been used to identify microorganisms and predict antibiotic resistance. The preprocessing method for the MS spectrum is key to extracting critical information from complicated MS spectral data. Different preprocessing methods yield different data, and the optimal approach is unclear. In this study, we adopted an ensemble of multiple preprocessing methods--FlexAnalysis, MALDIquant, and continuous wavelet transform-based methods--to detect peaks and build machine learning classifiers, including logistic regressions, naïve Bayes classifiers, random forests, and a support vector machine. The aim was to identify antibiotic resistance in , , , and Group B (GBS) based on MALDI-TOF MS spectra collected from two branches of a referral tertiary medical center. The ensemble method was compared with the individual methods. Random forest models built with the data preprocessed by the ensemble method outperformed individual preprocessing methods and achieved the highest accuracy, with values of 84.37% ( ), 90.96% ( ), 78.54% ( ), and 70.12% (GBS) on independent testing datasets. Through feature selection, important peaks related to antibiotic resistance could be detected from integrated information. The prediction model can provide an opinion for clinicians. The discriminative peaks enabling better prediction performance can provide a reference for further investigation of the resistance mechanism.