Aug 2026· Frontiers in Microbiology· Vol 17· 0 citations· 52 references
Medicine
TL;DR
The feasibility of portable Raman spectroscopy combined with machine learning for bacterial recognition under standardized sample conditions is supported, and pairwise binary classification showed variable performance among bacterial pairs.
Abstract
Introduction Antimicrobial resistance (AMR) continues to rise globally, highlighting the need for rapid, label-free, and cost-effective bacterial identification methods. In this proof-of-concept study, portable Raman spectroscopy combined with machine learning was used to identify five clinically relevant bacterial species: Escherichia coli, Pseudomonas aeruginosa, Staphylococcus aureus, Porphyromonas gingivalis, and Streptococcus mutans. Methods Raman spectra were acquired from cultured, washed, PBS-resuspended, and OD-standardized bacterial suspensions. After SNIP baseline correction, binary and five-class classification models were constructed using Auto-Sklearn with eight algorithms: ADB, ET, GB, LDA, SVM, MLP, PA, and QDA. Model performance was evaluated using accuracy, precision, recall, F1-score, MCC, and ROC-AUC. Results Pairwise binary classification showed variable performance among bacterial pairs. The best result was obtained for P. gingivalis versus S. aureus, with a testing accuracy of 98.3%, precision of 0.984, recall of 0.983, F1-score of 0.983, MCC of 0.967, and ROC-AUC of 1.000. Five-class classification was more limited, with LDA achieving the highest testing accuracy of 60.1%, MCC of 0.506, and ROC-AUC of 0.867. Discussion These findings support the feasibility of portable Raman spectroscopy combined with machine learning for bacterial recognition under standardized sample conditions.
To address the challenge of mixed contamination of foodborne pathogenic bacteria in food, in this study, a machine learning (ML) assisted surface-enhanced Raman scattering (SERS) sensing platform was proposed for multiple and rapid screening of foodborne pathogenic bacteria. 4-Mercaptophenylboronic acid-functionalized gold nanoparticles (AuNPs@4-MPBA) was introduced as SERS substrate and the molecular recognition and electromagnetic enhancement mechanisms for target analytes were elucidated by theoretical simulation. The sensing platform achieved efficient identification and differentiation of single and mixed contaminations of Escherichia coli, Salmonella typhimurium, Shigella, Listeria monocytogenes, and Staphylococcus aureus in three tea samples. The ability of the model to generalize across varying conditions was evaluated using a mixed spectral dataset from different tea sample matrices. After spectral preprocessing, the Random Forest (RF) model was used to classify 31 samples, achieving a classification accuracy of 97.34% and an out-of-bag accuracy of 95.98%, demonstrating excellent stability and generalization capability. The proposed approach enabled the rapid and accurate classification of foodborne pathogenic bacteria in complex food matrices, offering a promising strategy for rapid food safety emergency screening.
Simin Dai, Ceping Yin, Xuejing Fan et al.· Food Quality and Safety· 0 citations
Acinetobacter baumannii (A. baumannii) is a critical multidrug-resistant pathogen capable of environmental dissemination through water and veterinary sources. Rapid analytical methods to identify high-risk strains are essential for One Health surveillance. Here, we report a proof-of-concept surface-enhanced Raman spectroscopy and machine learning (SERS-ML) framework for rapid, label-free virulence-associated profiling of A. baumannii. Interestingly, whole-cell SERS spectra from 20 environmental and veterinary isolates (10 virulent, 10 avirulent) with silver nanoparticles (AgNPs) colloid yielded reproducible biochemical fingerprints in the 400-1800 cm-1 region. Particularly, virulent isolates exhibited enhanced spectral features corresponding to nucleic acids, proteins, and lipids, reflecting elevated metabolic activity, membrane complexity, and biofilm formation. To address replicate-level data leakage, we evaluated classification models across three validation schemes. While naïve spectrum-level cross-validation yielded inflated accuracies, strain-blocked GroupKFold and leave-one-strain-out (LOSO) cross-validations provided realistic accuracy of 78-88%, with partial least-squares discriminant analysis (PLS-DA) achieving optimal performance under LOSO (87.9% accuracy, receiver operating characteristic-area under the curve (ROC-AUC) = 0.959). Moreover, confounding audits further revealed that geographic and host metadata are partially embedded within spectral signatures. Overall, this study highlights SERS-ML as a promising analytical technique for bacterial risk profiling, while emphasizing the critical necessity of strain-aware validation strategies in spectroscopic machine learning.
Phularida Amulraj, Karpagavalli Palpandi, Sri Surya Charan Kondeti et al.· Journal of Hazardous Materia...· 0 citations
Raman spectroscopy combined with machine learning offers a rapid, label-free approach for bacterial identification, but robust translation remains challenged by spectral variability, biological heterogeneity, and limited model interpretability. Here, we present an integrated evaluation of an optimized Spectral Transformer (ST) framework for Raman-based bacterial classification benchmarked against a systematically optimized one-dimensional convolutional neural network (1D-CNN). The comparison was performed using a curated 36-class dataset comprising 15 Gram-negative bacterial entries, 15 Gram-positive bacterial entries, one non-bacterial microorganism, and five background/reference classes, enabling evaluation of both species-level and fine-grained bacterial classification. Under 15 dB noise-augmented evaluation, the ST achieved 80.6% ± 0.3% accuracy and a Matthews correlation coefficient (MCC) of 0.801 ± 0.003, outperforming the 1D-CNN baseline with 72.9% ± 0.3% accuracy and an MCC of 0.721 ± 0.003. Integrated Gradients analysis combined with attention map visualization enabled multi-level model interpretation, revealing that the ST’s improved robustness correlates with more bounded attribution patterns during misclassification, whereas the 1D-CNN’s feature attribution becomes scattered under noise perturbation. Importantly, this interpretability-driven analysis identified model-specific failure modes in the baseline architecture, including an over-reliance on non-specific spectral regions under noise, which can inform future data collection strategies and guide refinements to experimental protocols. These results demonstrate that attention-based spectral modeling improves Raman-based bacterial classification under noise-perturbed conditions while enabling multi-level interpretability that bridges model understanding with actionable feedback on experimental design and data quality requirements.
Yijian Meng, J. B. Christensen, C. Thirstrup et al.· Chemosensors· 0 citations
The Extra Trees Classifier consistently achieved the highest average accuracy and F1-score in both Gram type classification and species-level identification, demonstrating superior generalization across datasets.
Georgios Dolias, O. Bragina, Andres Udal et al.· Scientific Reports· 0 citations
Aquaculture expansion has exacerbated microplastics (MPs) contamination in aquaculture water bodies. MPs readily adsorb heavy metals and organic pollutants to form composite contamination and accumulate through food chains, imposing ecological and human health risks. Conventional detection techniques including microscopic observation, FTIR and Py-GC-MS are limited by low identification accuracy, matrix interference, destructiveness and cumbersome procedures, which cannot support rapid large-scale monitoring. Raman spectroscopy enables non-destructive detection with unique molecular fingerprinting, yet spectral overlap, background noise and subtle crystallinity differences among similar plastics hinder accurate manual classification. In this study, Raman spectroscopy was integrated with machine learning to establish a rapid plastic particle classification approach. Raman spectra of thirteen typical standard MPs were acquired, preprocessed and dimensionally reduced by PCA-LDA. Seven machine learning models were constructed and optimized by cross-validation, and further validated using spiked aquaculture wastewater samples. All models achieved classification accuracies above 98%. Among them, K-nearest neighbor (KNN), naive Bayes (NB), support vector machine (SVM), and logistic regression (LR) exhibited superior classification performance due to their effective feature discrimination capability and adaptability to high-dimensional Raman spectral data, enabling accurate classification of plastic particles according to polymer types under complex aquatic matrices. The proposed method integrates the molecular fingerprinting capability of Raman spectroscopy with the feature-learning advantages of machine learning, effectively overcoming the limitations of conventional spectral interpretation. This portable and non-destructive strategy provides a reliable approach for rapid plastic particle classification, pollution source tracing, and ecological risk assessment in aquatic environments.
A novel multi-label, multi-bacteria classification framework (MLMBC) that simultaneously predicts AMR across multiple bacterial species and antibiotics using MALDI-TOF mass spectrometry data and Convolutional Neural Networks (CNNs).
Leila Aro-Sati, Xaviera A. López-Cortés, José M. Manrıquez Troncoso et al.· Neural computing & applicati...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
