Combination of an Artificial Intelligence Approach and Laser Tweezers Raman Spectroscopy for Microbial Identification

NIR spectroscopy-CNN-enabled chemometrics for multianalyte monitoring in microbial fermentation

As the biopharmaceutical industry looks to implement Industry 4.0, the need for rapid and robust analytical characterization of analytes has become a pressing priority. Spectroscopic tools, like near-infrared (NIR) spectroscopy, are finding increasing use for real-time quantitative analysis. Yet detection of multiple low-concentration analytes in microbial and mammalian cell cultures remains an ongoing challenge, requiring the selection of carefully calibrated, resilient chemometrics for each analyte. The convolutional neural network (CNN) is a puissant tool for processing complex data and making it a potential approach for automatic multivariate spectral processing. This work proposes an inception module-based two-dimensional (2D) CNN approach (I-CNN) for calibrating multiple analytes using NIR spectral data. The I-CNN model, coupled with orthogonal partial least squares (PLS) preprocessing, converts the NIR spectral data into a 2D data matrix, after which the critical features are extracted, leading to model development for multiple analytes. Escherichia coli fermentation broth was taken as a case study, where calibration models were developed for 23 analytes, including 20 amino acids, glucose, lactose, and acetate. The I-CNN model result statistics depicted an average R2 values of prediction 0.90, external validation data set 0.86 and significantly lower root mean square error of prediction values ∼0.52 compared to conventional regression models like PLS. Preprocessing steps were applied to I-CNN models to evaluate any augmentation in prediction performance. Finally, the model reliability was assessed via real-time process monitoring and comparison with offline analytics. The proposed I-CNN method is systematic and novel in extracting distinctive spectral features from a multianalyte bioprocess data set and could be adapted to other complex cell culture systems requiring rapid quantification using spectroscopy.

RamanSPy: An Open-Source Python Package for Integrative Raman Spectroscopy Data Analysis

Raman spectroscopy is a nondestructive and label-free chemical analysis technique, which plays a key role in the analysis and discovery cycle of various branches of science. Nonetheless, progress in Raman spectroscopic analysis is still impeded by the lack of software, methodological and data standardization, and the ensuing fragmentation and lack of reproducibility of analysis workflows thereof. To address these issues, we introduce RamanSPy, an open-source Python package for Raman spectroscopic research and analysis. RamanSPy provides a comprehensive library of tools for spectroscopic analysis that supports day-to-day tasks, integrative analyses, the development of methods and protocols, and the integration of advanced data analytics. RamanSPy is modular and open source, not tied to a particular technology or data format, and can be readily interfaced with the burgeoning ecosystem for data science, statistical analysis, and machine learning in Python. RamanSPy is hosted at https://github.com/barahona-research-group/RamanSPy, supplemented with extended online documentation, available at https://ramanspy.readthedocs.io, that includes tutorials, example applications, and details about the real-world research applications presented in this paper.

Deep Learning-Assisted Spectrum-Structure Correlation: State-of-the-Art and Perspectives

Spectrum-structure correlation is playing an increasingly crucial role in spectral analysis and has undergone significant development in recent decades. With the advancement of spectrometers, the high-throughput detection triggers the explosive growth of spectral data, and the research extension from small molecules to biomolecules accompanies massive chemical space. Facing the evolving landscape of spectrum-structure correlation, conventional chemometrics becomes ill-equipped, and deep learning assisted chemometrics rapidly emerges as a flourishing approach with superior ability of extracting latent features and making precise predictions. In this review, the molecular and spectral representations and fundamental knowledge of deep learning are first introduced. We then summarize the development of how deep learning assist to establish the correlation between spectrum and molecular structure in the recent 5 years, by empowering spectral prediction (i.e., forward structure-spectrum correlation) and further enabling library matching and de novo molecular generation (i.e., inverse spectrum-structure correlation). Finally, we highlight the most important open issues persisted with corresponding potential solutions. With the fast development of deep learning, it is expected to see ultimate solution of establishing spectrum-structure correlation soon, which would trigger substantial development of various disciplines.

Deep learning-assisted mass spectrometry imaging for preliminary screening and pre-classification of psychoactive substances

Currently, it is of great urgency to develop a rapid pre-classification and screening method for suspected drugs as the constantly springing up of new psychoactive substances. In most researches, psychoactive substances classification approaches depended on the similar chemical structures and pharmacological action with known drugs. Such approaches could not face the complicated circumstance of emerging new psychoactive substances. Herein, mass spectrometry imaging and convolutional neural networks (CNN) were used for preliminary screening and pre-classification of suspected psychoactive substances. Mass spectrometry imaging was performed simultaneously on two brain slices as one was from blank group and another one was from psychoactive substance-induced group. Then, fused neurotransmitter variation mass spectrometry images (Nv-MSIs) reflecting the difference of neurotransmitters between two slices were achieved through two homemade programs. A CNN model was developed to classify the Nv-MSIs. Compared with traditional classification methods, CNN achieved better estimation accuracy and required minimal data preprocessing. Also, the specific region on Nv-MSIs and weight of each neurotransmitter that affected the classification most could be unraveled by CNN. Finally, the method was successfully applied to assist the identification of a new psychoactive substance seized recently. This sample was identified as cannabinoids, which greatly promoted the screening process.

Recent advances in microfluidic-based spectroscopic approaches for pathogen detection

Rapid identification of pathogens with higher sensitivity and specificity plays a significant role in maintaining public health, environmental monitoring, controlling food quality, and clinical diagnostics. Different methods have been widely used in food testing laboratories, quality control departments in food companies, hospitals, and clinical settings to identify pathogens. Some limitations in current pathogens detection methods are time-consuming, expensive, and laborious sample preparation, making it unsuitable for rapid detection. Microfluidics has emerged as a promising technology for biosensing applications due to its ability to precisely manipulate small volumes of fluids. Microfluidics platforms combined with spectroscopic techniques are capable of developing miniaturized devices that can detect and quantify pathogenic samples. The review focuses on the advancements in microfluidic devices integrated with spectroscopic methods for detecting bacterial microbes over the past five years. The review is based on several spectroscopic techniques, including fluorescence detection, surface-enhanced Raman scattering, and dynamic light scattering methods coupled with microfluidic platforms. The key detection principles of different approaches were discussed and summarized. Finally, the future possible directions and challenges in microfluidic-based spectroscopy for isolating and detecting pathogens using the latest innovations were also discussed.

Combined Mutual Learning Net for Raman Spectral Microbial Strain Identification

Infectious diseases pose a significant threat to global health, yet traditional microbiological identification methods suffer from drawbacks, such as high costs and long processing times. Raman spectroscopy, a label-free and noninvasive technique, provides rich chemical information and has tremendous potential in fast microbial diagnoses. Here, we propose a novel Combined Mutual Learning Net that precisely identifies microbial subspecies. It demonstrated an average identification accuracy of 87.96% in an open-access data set with thirty microbial strains, representing a 5.76% improvement. 50% of the microbial subspecies accuracies were elevated by 1% to 46%, especially for E. coli 2 improved from 31% to 77%. Furthermore, it achieved a remarkable subspecies accuracy of 92.4% in the custom-built fiber-optical tweezers Raman spectroscopy system, which collects Raman spectra at a single-cell level. This advancement demonstrates the effectiveness of this method in microbial subspecies identification, offering a promising solution for microbiology diagnosis.

Rapid identification of lactic acid bacteria at species/subspecies level via ensemble learning of Ramanomes

Rapid and accurate identification of lactic acid bacteria (LAB) species would greatly improve the screening rate for functional LAB. Although many conventional and molecular methods have proven efficient and reliable, LAB identification using these methods has generally been slow and tedious. Single-cell Raman spectroscopy (SCRS) provides the phenotypic profile of a single cell and can be performed by Raman spectroscopy (which directly detects vibrations of chemical bonds through inelastic scattering by a laser light) using an individual live cell. Recently, owing to its affordability, non-invasiveness, and label-free features, the Ramanome has emerged as a potential technique for fast bacterial detection. Here, we established a reference Ramanome database consisting of SCRS data from 1,650 cells from nine LAB species/subspecies and conducted further analysis using machine learning approaches, which have high efficiency and accuracy. We chose the ensemble meta-classifier (EMC), which is suitable for solving multi-classification problems, to perform in-depth mining and analysis of the Ramanome data. To optimize the accuracy and efficiency of the machine learning algorithm, we compared nine classifiers: LDA, SVM, RF, XGBoost, KNN, PLS-DA, CNN, LSTM, and EMC. EMC achieved the highest average prediction accuracy of 97.3% for recognizing LAB at the species/subspecies level. In summary, Ramanomes, with the integration of EMC, have promising potential for fast LAB species/subspecies identification in laboratories and may thus be further developed and sharpened for the direct identification and prediction of LAB species from fermented food.

Rapid discrimination of four Salmonella enterica serovars: A performance comparison between benchtop and handheld Raman spectrometers

Foodborne illnesses, particularly those caused by Salmonella enterica with its extensive array of over 2600 serovars, present a significant public health challenge. Therefore, prompt and precise identification of S. enterica serovars is essential for clinical relevance, which facilitates the understanding of S. enterica transmission routes and the determination of outbreak sources. Classical serotyping methods via molecular subtyping and genomic markers currently suffer from various limitations, such as labour intensiveness, time consumption, etc. Therefore, there is a pressing need to develop new diagnostic techniques. Surface-enhanced Raman spectroscopy (SERS) is a non-invasive diagnostic technique that can generate Raman spectra, based on which rapid and accurate discrimination of bacterial pathogens could be achieved. To generate SERS spectra, a Raman spectrometer is needed to detect and collect signals, which are divided into two types: the expensive benchtop spectrometer and the inexpensive handheld spectrometer. In this study, we compared the performance of two Raman spectrometers to discriminate four closely associated S. enterica serovars, that is, S. enterica subsp. enterica serovar dublin, enteritidis, typhi and typhimurium. Six machine learning algorithms were applied to analyse these SERS spectra. The support vector machine (SVM) model showed the highest accuracy for both handheld (99.97%) and benchtop (99.38%) Raman spectrometers. This study demonstrated that handheld Raman spectrometers achieved similar prediction accuracy as benchtop spectrometers when combined with machine learning models, providing an effective solution for rapid, accurate and cost-effective identification of closely associated S. enterica serovars.

Advances in Bio-Optical Imaging Systems for Spatiotemporal Monitoring of Intestinal Bacteria

Vast and complex intestinal communities are regulated and balanced through interactions with their host organisms, and disruption of gut microbial balance can cause a variety of diseases. Studying the mechanisms of pathogenic intestinal flora in the host and early detection of bacterial translocation and colonization can guide clinical diagnosis, provide targeted treatments, and improve patient prognosis. The use of in vivo imaging techniques to track microorganisms in the intestine, and study structural and functional changes of both cells and proteins, may clarify the governing equilibrium between the flora and host. Despite the recent rapid development of in vivo imaging of intestinal microecology, determining the ideal methodology for clinical use remains a challenge. Advances in optics, computer technology, and molecular biology promise to expand the horizons of research and development, thereby providing exciting opportunities to study the spatio-temporal dynamics of gut microbiota and the origins of disease. Here, this study reviews the characteristics and problems associated with optical imaging techniques, including bioluminescence, conventional fluorescence, novel metabolic labeling methods, nanomaterials, intelligently activated imaging agents, and photoacoustic (PA) imaging. It hopes to provide a valuable theoretical basis for future bio-intelligent imaging of intestinal bacteria.

Raman spectrum combined with deep learning for precise recognition of Carbapenem-resistant Enterobacteriaceae

Carbapenem-resistant Enterobacteriaceae (CRE) is a major pathogen that poses a serious threat to human health. Unfortunately, currently, there are no effective measures to curb its rapid development. To address this, an in-depth study on the surface-enhanced Raman spectroscopy (SERS) of 22 strains of 7 categories of CRE using a gold silver composite SERS substrate was conducted. The residual networks with an attention mechanism to classify the SERS spectrum from three perspectives (pathogenic bacteria type, enzyme-producing subtype, and sensitive antibiotic type) were performed. The results show that the SERS spectrum measured by the composite SERS substrate was repeatable and consistent. The SERS spectrum of CRE showed varying degrees of species differences, and the strain difference in the SERS spectrum of CRE was closely related to the type of enzyme-producing subtype. The introduced attention mechanism improved the classification accuracy of the residual network (ResNet) model. The accuracy of CRE classification for different strains and enzyme-producing subtypes reached 94.0% and 96.13%, respectively. The accuracy of CRE classification by pathogen sensitive antibiotic combination reached 93.9%. This study is significant for guiding antibiotic use in CRE infection, as the sensitive antibiotic used in treatment can be predicted directly by measuring CRE spectra. Our study demonstrates the potential of combining SERS with deep learning algorithms to identify CRE without culture labels and classify its sensitive antibiotics. This approach provides a new idea for rapid and accurate clinical detection of CRE and has important significance for alleviating the rapid development of resistance to CRE.

Fungicide-tolerant persister formation during cryptococcal pulmonary infection

Bacterial persisters, a subpopulation of genetically susceptible cells that are normally dormant and tolerant to bactericides, have been studied extensively because of their clinical importance. In comparison, much less is known about the determinants underlying fungicide-tolerant fungal persister formation in vivo. Here, we report that during mouse lung infection, Cryptococcus neoformans forms persisters that are highly tolerant to amphotericin B (AmB), the standard of care for treating cryptococcosis. By exploring stationary-phase indicator molecules and developing single-cell tracking strategies, we show that in the lung, AmB persisters are enriched in cryptococcal cells that abundantly produce stationary-phase molecules. The antioxidant ergothioneine plays a specific and key role in AmB persistence, which is conserved in phylogenetically distant fungi. Furthermore, the antidepressant sertraline (SRT) shows potent activity specifically against cryptococcal AmB persisters. Our results provide evidence for and the determinant of AmB-tolerant persister formation in pulmonary cryptococcosis, which has potential clinical significance.

Patch-Based Convolutional Encoder: A Deep Learning Algorithm for Spectral Classification Balancing the Local and Global Information

Molecular vibrational spectroscopies, including infrared absorption and Raman scattering, provide molecular fingerprint information and are powerful tools for qualitative and quantitative analysis. They benefit from the recent development of deep-learning-based algorithms to improve the spectral, spatial, and temporal resolutions. Although a variety of deep-learning-based algorithms, including those to simultaneously extract the global and local spectral features, have been developed for spectral classification, the classification accuracy is still far from satisfactory when the difference becomes very subtle. Here, we developed a lightweight algorithm named patch-based convolutional encoder (PACE), which effectively improved the accuracy of spectral classification by extracting spectral features while balancing local and global information. The local information was captured well by segmenting the spectrum into patches with an appropriate patch size. The global information was extracted by constructing the correlation between different patches with depthwise separable convolutions. In the five open-source spectral data sets, PACE achieved a state-of-the-art performance. The more difficult the classification, the better the performance of PACE, compared with that of residual neural network (ResNet), vision transformer (ViT), and other commonly used deep learning algorithms. PACE helped improve the accuracy to 92.1% in Raman identification of pathogen-derived extracellular vesicles at different physiological states, which is much better than those of ResNet (85.1%) and ViT (86.0%). In general, the precise recognition and extraction of subtle differences offered by PACE are expected to facilitate vibrational spectroscopy to be a powerful tool toward revealing the relevant chemical reaction mechanisms in surface science or realizing the early diagnosis in life science.

Species identification and strain discrimination of fermentation yeasts Saccharomyces cerevisiae and Saccharomyces uvarum using Raman spectroscopy and convolutional neural networks

IMPORTANCE

The use of S. cerevisiae and S. uvarum yeast starter cultures is a common practice in the alcoholic beverage fermentation industry. As yeast strains from different or the same species have variable fermentation properties, rapid and reliable typing of yeast strains plays an important role in the final quality of the product. In this study, Raman spectroscopy combined with CNN achieved accurate identification of S. cerevisiae and S. uvarum isolates at both the species and strain levels in a rapid, non-destructive, and easy-to-operate manner. This approach can be utilized to test the identity of commercialized dry yeast products and to monitor the diversity of yeast strains during fermentation. It provides great benefits as a high-throughput screening method for agri-food and the alcoholic beverage fermentation industry. This proposed method has the potential to be a powerful tool to discriminate S. cerevisiae and S. uvarum strains in taxonomic, ecological studies and fermentation applications.

Combination of deep learning and 2D CARS figures for identification of amyloid-β plaques

In vivo imaging and accurate identification of amyloid-β (Aβ) plaque are crucial in Alzheimer's disease (AD) research. In this work, we propose to combine the coherent anti-Stokes Raman scattering (CARS) microscopy, a powerful detection technology for providing Raman spectra and label-free imaging, with deep learning to distinguish Aβ from non-Aβ regions in AD mice brains in vivo. The 1D CARS spectra is firstly converted to 2D CARS figures by using two different methods: spectral recurrence plot (SRP) and spectral Gramian angular field (SGAF). This can provide more learnable information to the network, improving the classification precision. We then devise a cross-stage attention network (CSAN) that automatically learns the features of Aβ plaques and non-Aβ regions by taking advantage of the computational advances in deep learning. Our algorithm yields higher accuracy, precision, sensitivity and specificity than the results of conventional multivariate statistical analysis method and 1D CARS spectra combined with deep learning, demonstrating its competence in identifying Aβ plaques. Last but not least, the CSAN framework requires no prior information on the imaging modality and may be applicable to other spectroscopy analytical fields.

Classification and prediction of Klebsiella pneumoniae strains with different MLST allelic profiles via SERS spectral analysis

The Gram-negative non-motile Klebsiella pneuomoniae is currently a major cause of hospital-acquired (HA) and community-acquired (CA) infections, leading to great public health concern globally, while rapid identification and accurate tracing of the pathogenic bacterium is essential in facilitating monitoring and controlling of K. pneumoniae outbreak and dissemination. Multi-locus sequence typing (MLST) is a commonly used typing approach with low cost that is able to distinguish bacterial isolates based on the allelic profiles of several housekeeping genes, despite low resolution and labor intensity of the method. Core-genome MLST scheme (cgMLST) is recently proposed to sub-type and monitor outbreaks of bacterial strains with high resolution and reliability, which uses hundreds or thousands of genes conserved in all or most members of the species. However, the method is complex and requires whole genome sequencing of bacterial strains with high costs. Therefore, it is urgently needed to develop novel methods with high resolution and low cost for bacterial typing. Surface enhanced Raman spectroscopy (SERS) is a rapid, sensitive and cheap method for bacterial identification. Previous studies confirmed that classification and prediction of bacterial strains via SERS spectral analysis correlated well with MLST typing results. However, there is currently no similar comparative analysis in K. pneumoniae strains. In this pilot study, 16 K. pneumoniae strains with different sequencing typings (STs) were selected and a phylogenetic tree was constructed based on core genome analysis. SERS spectra (N = 45/each strain) were generated for all the K. pneumoniae strains, which were then comparatively classified and predicted via six representative machine learning (ML) algorithms. According to the results, SERS technique coupled with the ML algorithm support vector machine (SVM) could achieve the highest accuracy (5-Fold Cross Validation = 100%) in terms of differentiating and predicting all the K. pneumoniae strains that were consistent to corresponding MLSTs. In sum, we show in this pilot study that the SERS-SVM based method is able to accurately predict K. pneumoniae MLST types, which has the application potential in clinical settings for tracing dissemination and controlling outbreak of K. pneumoniae in hospitals and communities with low costs and high rapidity.

Multi-scale sequential feature selection for disease classification using Raman spectroscopy data

Raman spectroscopy (RS) optical technology promises non-destructive and fast application in medical disease diagnosis in a single step. However, achieving clinically relevant performance levels remains challenging due to the inability to search for significant Raman signals at different scales. Here we propose a multi-scale sequential feature selection method that can capture global sequential features and local peak features for disease classification using RS data. Specifically, we utilize the Long short-term memory network (LSTM) module to extract global sequential features in the Raman spectra, as it can capture long-term dependencies present in the Raman spectral sequences. Meanwhile, the attention mechanism is employed to select local peak features that were ignored before and are the key to distinguishing different diseases. Experimental results on three public and in-house datasets demonstrate the superiority of our model compared with state-of-the-art methods for RS classification. In particular, our model achieves an accuracy of 97.9 ± 0.2% on the COVID-19 dataset, 76.3 ± 0.4% on the H-IV dataset, and 96.8 ± 1.9% on the H-V dataset.

Dynamically Quantifying Intracellular Elemental Sulfur and Predicting Pertinent Gene Transcription by Raman Spectroscopy in Living Cells

The ability to monitor changes in metabolites and corresponding gene transcription within living cells is highly desirable. However, most current assays for quantification of metabolites or for gene transcription are destructive, precluding tracking the real-time dynamics of living cells. Here, we used the intracellular elemental sulfur in a Thiophaeococcus mangrovi cell as a proof-of-concept to link the quantity of metabolites and relevant gene transcription in living cells by a nondestructive Raman approach. Raman spectroscopy was utilized to quantify intracellular elemental sulfur noninvasively, and a computational mRR (mRNA and Raman) model was developed to infer the transcription of genes relevant to elemental sulfur. The results showed a significant linear correlation between the exponentially transformed Raman spectral intensity of intracellular elemental sulfur and the mRNA levels of genes encoding sulfur globule proteins in T. mangrovi. The mRR model was verified independently in two genera of Thiocapsa and Thiorhodococcus, and the mRNA levels predicted by mRR showed high consistency with actual gene expression detected by real-time polymerase chain reaction (PCR). This approach could enable noninvasive assessment of the quantity of metabolites and link the pertinent gene expression profiles in living cells, providing useful baseline data to spectroscopically map various omics in real time.

Rapid discrimination of Shigella spp. and Escherichia coli via label-free surface enhanced Raman spectroscopy coupled with machine learning algorithms

Shigella and enterotoxigenic Escherichia coli (ETEC) are major bacterial pathogens of diarrheal disease that is the second leading cause of childhood mortality globally. Currently, it is well known that Shigella spp., and E. coli are very closely related with many common characteristics. Evolutionarily speaking, Shigella spp., are positioned within the phylogenetic tree of E. coli. Therefore, discrimination of Shigella spp., from E. coli is very difficult. Many methods have been developed with the aim of differentiating the two species, which include but not limited to biochemical tests, nucleic acids amplification, and mass spectrometry, etc. However, these methods suffer from high false positive rates and complicated operation procedures, which requires the development of novel methods for accurate and rapid identification of Shigella spp., and E. coli. As a low-cost and non-invasive method, surface enhanced Raman spectroscopy (SERS) is currently under intensive study for its diagnostic potential in bacterial pathogens, which is worthy of further investigation for its application in bacterial discrimination. In this study, we focused on clinically isolated E. coli strains and Shigella species (spp.), that is, S. dysenteriae, S. boydii, S. flexneri, and S. sonnei, based on which SERS spectra were generated and characteristic peaks for Shigella spp., and E. coli were identified, revealing unique molecular components in the two bacterial groups. Further comparative analysis of machine learning algorithms showed that, the Convolutional Neural Network (CNN) achieved the best performance and robustness in bacterial discrimination capacity when compared with Random Forest (RF) and Support Vector Machine (SVM) algorithms. Taken together, this study confirmed that SERS paired with machine learning could achieve high accuracy in discriminating Shigella spp., from E. coli, which facilitated its application potential for diarrheal prevention and control in clinical settings.

Raman spectroscopy combined with deep learning for rapid detection of melanoma at the single cell level

Melanoma is an aggressive and metastatic skin cancer caused by genetic mutations in melanocytes, and its incidence is increasing year by year. Understanding the gene mutation information of melanoma cases is very important for its precise treatment. The current diagnostic methods for melanoma include radiological, pharmacological, histological, cytological and molecular techniques, but the gold standard for diagnosis is still pathological biopsy, which is time consuming and destructive. Raman spectroscopy is a rapid, sensitive and nondestructive detection method. In this study, a total of 20,000 Surface-enhanced Raman scattering (SERS) spectra of melanocytes and melanoma cells were collected using a positively charged gold nanoparticles planar solid SERS substrate, and a classification network system based on convolutional neural networks (CNN) was constructed to achieve the classification of melanocytes and melanoma cells, wild-type and mutant melanoma cells and their drug resistance. Among them, the classification accuracy of melanocytes and melanoma cells was over 98%. Raman spectral differences between melanocytes and melanoma cells were analyzed and compared, and the response of cells to antitumor drugs were also evaluated. The results showed that Raman spectroscopy provided a basis for the medication of melanoma, and SERS spectra combined with CNN classification model realized classification of melanoma, which is of great significance for rapid diagnosis and identification of melanoma.

Rapid Detection of SARS-CoV-2 RNA in Human Nasopharyngeal Specimens Using Surface-Enhanced Raman Spectroscopy and Deep Learning Algorithms

A rapid and cost-effective method to detect the infection of SARS-CoV-2 is fundamental to mitigating the current COVID-19 pandemic. Herein, a surface-enhanced Raman spectroscopy (SERS) sensor with a deep learning algorithm has been developed for the rapid detection of SARS-CoV-2 RNA in human nasopharyngeal swab (HNS) specimens. The SERS sensor was prepared using a silver nanorod array (AgNR) substrate by assembling DNA probes to capture SARS-CoV-2 RNA. The SERS spectra of HNS specimens were collected after RNA hybridization, and the corresponding SERS peaks were identified. The RNA detection range was determined to be 103-109 copies/mL in saline sodium citrate buffer. A recurrent neural network (RNN)-based deep learning model was developed to classify 40 positive and 120 negative specimens with an overall accuracy of 98.9%. For the blind test of 72 specimens, the RNN model gave a 97.2% accuracy prediction for positive specimens and a 100% accuracy for negative specimens. All the detections were performed in 25 min. These results suggest that the DNA-functionalized AgNR array SERS sensor combined with a deep learning algorithm could serve as a potential rapid point-of-care COVID-19 diagnostic platform.

Identification of pathogens and detection of antibiotic susceptibility at single-cell resolution by Raman spectroscopy combined with machine learning

Rapid, accurate, and label-free detection of pathogenic bacteria and antibiotic resistance at single-cell resolution is a technological challenge for clinical diagnosis. Overcoming the cumbersome culture process of pathogenic bacteria and time-consuming antibiotic susceptibility assays will significantly benefit early diagnosis and optimize the use of antibiotics in clinics. Raman spectroscopy can collect molecular fingerprints of pathogenic bacteria in a label-free and culture-independent manner, which is suitable for pathogen diagnosis at single-cell resolution. Here, we report a method based on Raman spectroscopy combined with machine learning to rapidly and accurately identify pathogenic bacteria and detect antibiotic resistance at single-cell resolution. Our results show that the average accuracy of identification of 12 species of common pathogenic bacteria by the machine learning method is 90.73 ± 9.72%. Antibiotic-sensitive and antibiotic-resistant strains of Acinetobacter baumannii isolated from hospital patients were distinguished with 99.92 ± 0.06% accuracy using the machine learning model. Meanwhile, we found that sensitive strains had a higher nucleic acid/protein ratio and antibiotic-resistant strains possessed abundant amide II structures in proteins. This study suggests that Raman spectroscopy is a promising method for rapidly identifying pathogens and detecting their antibiotic susceptibility.

Microfluidic SERS devices: brightening the future of bioanalysis

A new avenue has opened up for applications of surface-enhanced Raman spectroscopy (SERS) in the biomedical field, mainly due to the striking advantages offered by SERS tags. SERS tags provide indirect identification of analytes with rich and highly specific spectral fingerprint information, high sensitivity, and outstanding multiplexing potential, making them very useful in in vitro and in vivo assays. The recent and innovative advances in nanomaterial science, novel Raman reporters, and emerging bioconjugation protocols have helped develop ultra-bright SERS tags as powerful tools for multiplex SERS-based detection and diagnosis applications. Nevertheless, to translate SERS platforms to real-world problems, some challenges, especially for clinical applications, must be addressed. This review presents the current understanding of the factors influencing the quality of SERS tags and the strategies commonly employed to improve not only spectral quality but the specificity and reproducibility of the interaction of the analyte with the target ligand. It further explores some of the most common approaches which have emerged for coupling SERS with microfluidic technologies, for biomedical applications. The importance of understanding microfluidic production and characterisation to yield excellent device quality while ensuring high throughput production are emphasised and explored, after which, the challenges and approaches developed to fulfil the potential that SERS-based microfluidics have to offer are described.

Application of Microfluidics for Bacterial Identification

Bacterial infections continue to pose serious public health challenges. Though anti-bacterial therapeutics are effective remedies for treating these infections, the emergence of antibiotic resistance has imposed new challenges to treatment. Often, there is a delay in prescribing antibiotics at initial symptom presentation as it can be challenging to clinically differentiate bacterial infections from other organisms (e.g., viruses) causing infection. Moreover, bacterial infections can arise from food, water, or other sources. These challenges have demonstrated the need for rapid identification of bacteria in liquids, food, clinical spaces, and other environments. Conventional methods of bacterial identification rely on culture-based approaches which require long processing times and higher pathogen concentration thresholds. In the past few years, microfluidic devices paired with various bacterial identification methods have garnered attention for addressing the limitations of conventional methods and demonstrating feasibility for rapid bacterial identification with lower biomass thresholds. However, such culture-free methods often require integration of multiple steps from sample preparation to measurement. Research interest in using microfluidic methods for bacterial identification is growing; therefore, this review article is a summary of current advancements in this field with a focus on comparing the efficacy of polymerase chain reaction (PCR), loop-mediated isothermal amplification (LAMP), and emerging spectroscopic methods.

Laser tweezers Raman spectroscopy combined with machine learning for diagnosis of Alzheimer's disease

Alzheimer's disease (AD) is a common nervous system disease to affect mostly elderly people over the age of 65 years. However, the diagnosis of AD is mainly depend on the imaging examination, clinical assessments and neuropsychological tests, which may get error diagnosis results and are not able to detect early AD. Here, a rapid, non-invasive, and high accuracy diagnostic method for AD especially early AD is provided based on the laser tweezers Raman spectroscopy (LTRS) combined with machine learning algorithms. AD platelets from different 3xTg-AD transgenic rats at different stages of disease are captured to collect high signal-to-noise ratio Raman signals without contact by LTRS, which is then combined with partial least squares discriminant analysis (PLS-DA), support vector machine (SVM) and principal component analysis (PCA)-canonical discriminate function (CDA) for classification. The results show that the normal and diseased platelets at 3-, 6- and 12-month AD are successfully distinguished and the accuracy is 91%, 68% and 97% respectively, which demonstrates the suggested method can provide a precise detection for AD diagnosis at early, middle and advanced stages.

Culture-Independent Raman Spectroscopic Identification of Bacterial Pathogens from Clinical Samples Using Deep Transfer Learning

The rapid identification of bacterial pathogens in clinical samples like blood, urine, pus, and sputum is the need of the hour. Conventional bacterial identification methods like culturing and nucleic acid-based amplification have limitations like poor sensitivity, high cost, slow turnaround time, etc. Raman spectroscopy, a label-free and noninvasive technique, has overcome these drawbacks by providing rapid biochemical signatures from a single bacterium. Raman spectroscopy combined with chemometric methods has been used effectively to identify pathogens. However, a robust approach is needed to utilize Raman features for accurate classification while dealing with complex data sets such as spectra obtained from clinical isolates, showing high sample-to-sample heterogeneity. In this study, we have used Raman spectroscopy-based identification of pathogens from clinical isolates using a deep transfer learning approach at the single-cell level resolution. We have used the data-augmentation method to increase the volume of spectra needed for deep-learning analysis. Our ResNet model could specifically extract the spectral features of eight different pathogenic bacterial species with a 99.99% classification accuracy. The robustness of our model was validated on a set of blinded data sets, a mix of cultured and noncultured bacterial isolates of various origins and types. Our proposed ResNet model efficiently identified the pathogens from the blinded data set with high accuracy, providing a robust and rapid bacterial identification platform for clinical microbiology.

Accurate and fast identification of minimally prepared bacteria phenotypes using Raman spectroscopy assisted by machine learning

The worldwide increase of antimicrobial resistance (AMR) is a serious threat to human health. To avert the spread of AMR, fast reliable diagnostics tools that facilitate optimal antibiotic stewardship are an unmet need. In this regard, Raman spectroscopy promises rapid label- and culture-free identification and antimicrobial susceptibility testing (AST) in a single step. However, even though many Raman-based bacteria-identification and AST studies have demonstrated impressive results, some shortcomings must be addressed. To bridge the gap between proof-of-concept studies and clinical application, we have developed machine learning techniques in combination with a novel data-augmentation algorithm, for fast identification of minimally prepared bacteria phenotypes and the distinctions of methicillin-resistant (MR) from methicillin-susceptible (MS) bacteria. For this we have implemented a spectral transformer model for hyper-spectral Raman images of bacteria. We show that our model outperforms the standard convolutional neural network models on a multitude of classification problems, both in terms of accuracy and in terms of training time. We attain more than 96% classification accuracy on a dataset consisting of 15 different classes and 95.6% classification accuracy for six MR-MS bacteria species. More importantly, our results are obtained using only fast and easy-to-produce training and test data.

Rapid discrimination of glycogen particles originated from different eukaryotic organisms

There are many commercially available glycogen particles in the market due to their bioactive functions as food additive, drug carrier and natural moisturizer, etc. It would be beneficial to rapidly determine the origins of commercially-available glycogen particles, which could facilitate the establishment of quality control methodology for glycogen-containing products. With its non-destructive, label-free and low-cost features, surface enhanced Raman spectroscopy (SERS) is an attractive technique with high potential to discriminate chemical compounds in a rapid mode. In this study, we applied the combination of SERS technique and machine leaning algorithms on glycogen analysis, which successfully predicted the origins of glycogen particles from a variety of organisms with convolutional neural network (CNN) algorithm plus attention mechanism having the best computational performance (5-fold cross validation accuracy = 96.97 %). In sum, this is the first study focusing on the discrimination of commercial glycogen particles originated from different organisms, which holds the application potential in quality control of glycogen-containing products.

Analysis and comparison of machine learning methods for blood identification using single-cell laser tweezer Raman spectroscopy

Raman spectroscopy, a "fingerprint" spectrum of substances, can be used to characterize various biological and chemical samples. To allow for blood classification using single-cell Raman spectroscopy, several machine learning algorithms were implemented and compared. A single-cell laser optical tweezer Raman spectroscopy system was established to obtain the Raman spectra of red blood cells. The Boruta algorithm extracted the spectral feature frequency shift, reduced the spectral dimension, and determined the essential features that affect classification. Next, seven machine learning classification models are analyzed and compared based on the classification accuracy, precision, and recall indicators. The results show that support vector machines and artificial neural networks are the two most appropriate machine learning algorithms for single-cell Raman spectrum blood classification, and this finding provides essential guidance for future research studies.

Highly Accurate Identification of Bacteria's Antibiotic Resistance Based on Raman Spectroscopy and U-Net Deep Learning Algorithms

Bacterial pathogens especially antibiotic-resistant ones are a public health concern worldwide. To oppose the morbidity and mortality associated with them, it is critical to select an appropriate antibiotic by performing a rapid bacterial diagnosis. Using a combination of Raman spectroscopy and deep learning algorithms to identify bacteria is a rapid and reliable method. Nevertheless, due to the loss of information during training a model, some deep learning algorithms suffer from low accuracy. Herein, we modify the U-Net architecture to fit our purpose of classifying the one-dimensional Raman spectra. The proposed U-Net model provides highly accurate identification of the 30 isolates of bacteria and yeast, empiric treatment groups, and antimicrobial resistance, thanks to its capability to concatenate and copy important features from the encoder layers to the decoder layers, thereby decreasing the data loss. The accuracies of the model for the 30-isolate level, empiric treatment level, and antimicrobial resistance level tasks are 86.3, 97.84, and 95%, respectively. The proposed deep learning model has a high potential for not only bacterial identification but also for other diagnostic purposes in the biomedical field.

Visible Particle Identification Using Raman Spectroscopy and Machine Learning

Visible particle identification is a crucial prerequisite step for process improvement and control during the manufacturing of injectable biotherapeutic drug products. Raman spectroscopy is a technology with several advantages for particle identification including high chemical sensitivity, minimal sample manipulation, and applicability to aqueous solutions. However, considerable effort and experience are required to extract and interpret Raman spectral data. In this study, we applied machine learning algorithms to analyze Raman spectral data for visible particle identification in order to minimize expert support and improve data analysis accuracy. We manually prepared ten types of particle standard solutions to simulate the particle types typically observed during manufacturing and established a Raman spectral library with accurate peak assignments for the visible particles. Five classification algorithms were trained using visible particle Raman spectral data. All models had high prediction accuracy of >98% for all types of visible particles. Our results demonstrate that the combination of Raman spectroscopy and machine learning can provide a simple and accurate data analysis approach for visible particle identification.

Rapid and accurate identification of pathogenic bacteria at the single-cell level using laser tweezers Raman spectroscopy and deep learning

We report a new method for the rapid identification of pathogenic bacterial species at the single-cell level that combines laser tweezers Raman spectroscopy (LTRS) with deep learning (DL). LTRS can accurately measure single-cell Raman spectra (scRS) without destroying and labeling cells. Based on the scRS data, DL rapidly and accurately identifies pathogenic bacteria. We measured scRS of 15 species bacteria using homemade LTRS. For each species, approximately, 160 cells from three different patients were measured, one patient's data were used as test set, and the rest after being augmented was used as training set. A residual network (ResNet) model, trained on the augmented training set, achieved an accuracy of 94.53% on the test set. Moreover, we applied gradient-weighted class activation mapping to visualize the proposed model. Finally, we demonstrated the advantages of ResNet over traditional machine-learning algorithms.

Deep Learning-Based Sensor Array: 3D Fluorescence Spectra of Gold Nanoclusters for Qualitative and Quantitative Analysis of Vitamin B6 Derivatives

Vitamin B₆ derivatives (VB6Ds) are of great importance for all living organisms to complete their physiological processes. However, their excess in the body can cause serious problems. What is more, the qualitative and quantitative analysis of different VB6Ds may present significant challenges due to the high similarity of their chemical structures. Also, the transfer of deep learning model from one task to a similar task needs to be present more in the fluorescence-based biosensor. Therefore, to address these problems, two deep learning models based on the intrinsic fingerprint of 3D fluorescence spectra have been developed to identify five VB6Ds. The accuracy ranges of a deep neural network (DNN) and a convolutional neural network (CNN) were 94.44-97.77% and 97.77-100%, respectively. After that, the developed models were transferred for quantitative analysis of the selected VB6Ds at a broad concentration range (1-100 μM). The determination coefficient (R²) values of the test set for DNN and CNN were 93.28 and 97.01%, respectively, which also represents the outperformance of CNN over DNN. Therefore, our approach opens new avenues for qualitative and quantitative sensing of small molecules, which will enrich fields related to deep learning, analytical chemistry, and especially sensor array chemistry.

Holographic Manipulation of Nanostructured Fiber Optics Enables Spatially-Resolved, Reconfigurable Optical Control of Plasmonic Local Field Enhancement and SERS

Integration of plasmonic structures on step-index optical fibers is attracting interest for both applications and fundamental studies. However, the possibility to dynamically control the coupling between the guided light fields and the plasmonic resonances is hindered by the turbidity of light propagation in multimode fibers (MMFs). This pivotal point strongly limits the range of studies that can benefit from nanostructured fiber optics. Fortunately, harnessing the interaction between plasmonic modes on the fiber tip and the full set of guided modes can bring this technology to a next generation progress. Here, the intrinsic wealth of information of guided modes is exploited to spatiotemporally control the plasmonic resonances of the coupled system. This concept is shown by employing dynamic phase modulation to structure both the response of plasmonic MMFs on the plasmonic facet and their response in the corresponding Fourier plane, achieving spatial selective field enhancement and direct control of the probe's work point in the dispersion diagram. Such a conceptual leap would transform the biomedical applications of holographic endoscopic imaging by integrating new sensing and manipulation capabilities.

Deep Learning-Based Spectral Extraction for Improving the Performance of Surface-Enhanced Raman Spectroscopy Analysis on Multiplexed Identification and Quantitation

Surface-enhanced Raman spectroscopy (SERS) has been recognized as a promising analytical technique for its capability of providing molecular fingerprint information and avoiding interference of water. Nevertheless, direct SERS detection of complicated samples without pretreatment to achieve the high-efficiency identification and quantitation in a multiplexed way is still a challenge. In this study, a novel spectral extraction neural network (SENN) model was proposed for synchronous SERS detection of each component in mixed solutions using a demonstration sample containing diquat dibromide (DDM), methyl viologen dichloride (MVD), and tetramethylthiuram disulfide (TMTD). A SERS spectra dataset including 3600 spectra of DDM, MVD, TMTD, and their mixtures was first constructed to train the SENN model. After the training step, the cosine similarity of the SENN model can achieve 0.999, 0.997, and 0.994 for DDM, MVD, and TMTD, respectively, which means that the spectra extracted from the mixture are highly consistent with those collected by the SERS experiment of the corresponding pure samples. Furthermore, a convolutional neural network model for quantitative analysis is combined with the SENN, which can simultaneously and rapidly realize the qualitative and quantitative SERS analysis of mixture solutions with lower than 8.8% relative standard deviation. The result demonstrates that the proposed strategy has great potential in improving SERS analysis in environmental monitoring, food safety, and so on.

Recent Advances and Applications of Rapid Microbial Assessment from a Food Safety Perspective

Unsafe food is estimated to cause 600 million cases of foodborne disease, annually. Thus, the development of methods that could assist in the prevention of foodborne diseases is of high interest. This review summarizes the recent progress toward rapid microbial assessment through (i) spectroscopic techniques, (ii) spectral imaging techniques, (iii) biosensors and (iv) sensors designed to mimic human senses. These methods often produce complex and high-dimensional data that cannot be analyzed with conventional statistical methods. Multivariate statistics and machine learning approaches seemed to be valuable for these methods so as to "translate" measurements to microbial estimations. However, a great proportion of the models reported in the literature misuse these approaches, which may lead to models with low predictive power under generic conditions. Overall, all the methods showed great potential for rapid microbial assessment. Biosensors are closer to wide-scale implementation followed by spectroscopic techniques and then by spectral imaging techniques and sensors designed to mimic human senses.

High-Precision Intelligent Cancer Diagnosis Method: 2D Raman Figures Combined with Deep Learning

Raman spectroscopy, as a label-free detection technology, has been widely used in tumor diagnosis. However, most tumor diagnosis procedures utilize multivariate statistical analysis methods for classification, which poses a major bottleneck toward achieving high accuracy. Here, we propose a concept called the two-dimensional (2D) Raman figure combined with convolutional neural network (CNN) to improve the accuracy. Two-dimensional Raman figures can be obtained from four transformation methods: spectral recurrence plot (SRP), spectral Gramian angular field (SGAF), spectral short-time Fourier transform (SSTFT), and spectral Markov transition field (SMTF). Two-dimensional CNN models all yield more than 95% accuracy, which is higher than the PCA-LDA method and the Raman-spectrum-CNN method, indicating that 2D Raman figure inputs combined with CNN may be one reason for gaining excellent performances. Among 2D-CNN models, the main difference is the conversion, where SRP is based on the structure of wavenumber series with the best performances (98.9% accuracy, 99.5% sensitivity, 98.3% specificity), followed by SGAF on the wavenumber series, SSTFT on wavenumber and intensity information, and SMTF on wavenumber position information. The inclusion of external information in the conversion may be another reason for improvement in the accuracy. The excellent capability shows huge potential for tumor diagnosis via 2D Raman figures and may be applied in other spectroscopy analytical fields.

A Review of Raman-Based Technologies for Bacterial Identification and Antimicrobial Susceptibility Testing

Antimicrobial resistance (AMR) is a global medical threat that seriously endangers human health. Rapid bacterial identification and antimicrobial susceptibility testing (AST) are key interventions to combat the spread and emergence of AMR. Although current clinical bacterial identification and AST provide comprehensive information, they are labor-intensive, complex, inaccurate, and slow (requiring several days, depending on the growth of pathogenic bacteria). Recently, Raman-based identification and AST technologies have played an increasingly important role in fighting AMR. This review summarizes major Raman-based techniques for bacterial identification and AST, including spontaneous Raman scattering, surface-enhanced Raman scattering (SERS), and coherent Raman scattering (CRS) imaging. Then, we discuss recent developments in rapid identification and AST methods based on Raman technology. Finally, we highlight the major challenges and potential future efforts to improve clinical outcomes through rapid bacterial identification and AST.

Highly accurate diagnosis of lung adenocarcinoma and squamous cell carcinoma tissues by deep learning

Intraoperative detection of the marginal tissues is the last and most important step to complete the resection of adenocarcinoma and squamous cell carcinoma. However, the current intraoperative diagnosis is time-consuming and requires numerous steps including staining. In this paper, we present the use of Raman spectroscopy with deep learning to achieve accurate diagnosis with stain-free process. To make the spectrum more suitable for deep learning, we utilize an unusual way of thinking which regards Raman spectral signal as a sequence and then converts it into two-dimensional Raman spectrogram by short-time Fourier transform as input. The normal-adenocarcinoma deep learning model and normal-squamous carcinoma deep learning model both achieve more than 96% accuracy, 95% sensitivity and 98% specificity when test, which higher than the conventional principal components analysis-linear discriminant analysis method with normal-adenocarcinoma model (0.896 accuracy, 0.867 sensitivity, 0.926 specificity) and normal-squamous carcinoma model (0.821 accuracy, 0.776 sensitivity, 1.000 specificity). The high performance of deep learning models provides a reliable way for intraoperative detection of marginal tissue, and is expected to reduce the detection time and save human lives.

RamanNet: a lightweight convolutional neural network for bacterial identification based on Raman spectra

Raman spectroscopy combined convolutional neural network (CNN) enables rapid and accurate identification of the species of bacteria. However, the existing CNN requires a complex hyperparameters model design. Herein, we propose a new simple network architecture with less hyperparameter design and low computation cost, RamanNet, for rapid and accurate identifying of bacteria at the species level based on its Raman spectra. We verified that compared with the previous CNN methods, the RamanNet reached comparable results on the Bacteria-ID Raman spectral dataset and PKU-bacterial Raman spectral datasets, but using only about 1/45 and 1/297 network parameters, respectively. RamanNet achieved an average isolate-level accuracy of 84.7 ± 0.3%, antibiotic treatment identification accuracy of 97.1 ± 0.3%, and distinguished accuracy of 81.6 ± 0.9% for methicillin-resistant and -susceptible Staphylococcus aureus (MRSA and MSSA) on the Bacteria-ID dataset, respectively. Moreover, it achieved an average accuracy of 96.04% on the PKU-bacterial dataset. The RamanNet model benefited from fewer model parameters that can be quickly trained even using CPU. Therefore, our method has the potential to rapidly and accurately identify bacterial species based on their Raman spectra and can be easily extended to other classification tasks based on Raman spectra.

We propose a novel CNN model named RamanNet for rapid and accurate identification of bacteria at the species-level based on Raman spectra. Compared to previous CNN methods, the RamanNet reached comparable results on the Bacteria-ID Raman spectral dataset.

Classification and Identification of Archaea Using Single-Cell Raman Ejection and Artificial Intelligence: Implications for Investigating Uncultivated Microorganisms

Archaea can produce special cellular components such as polyhydroxyalkanoates, carotenoids, rhodopsin, and ether lipids, which have valuable applications in medicine and green energy production. Most of the archaeal species are uncultivated, posing challenges to investigating their biomarker components and biochemical properties. In this study, we applied Raman spectroscopy to examine the biological characteristics of nine archaeal isolates, including halophilic archaea (Haloferax larsenii, Haloarcula argentinensis, Haloferax mediterranei, Halomicrobium mukohataei, Halomicrobium salinus, Halorussus sp., Natrinema gari), thermophilic archaea (Sulfolobus acidocaldarius), and marine group I (MGI) archaea (Nitrosopumilus maritimus). Linear discriminant analysis of the Raman spectra allowed visualization of significant separations among the nine archaeal isolates. Machine-learning classification models based on support vector machine achieved accuracies of 88-100% when classifying the nine archaeal species. The predicted results were validated by DNA sequencing analysis of cells isolated from the mixture by Raman-activated cell sorting. Raman spectra of uncultured archaea (MGII) were also obtained based on Raman spectroscopy and fluorescence in situ hybridization. The results combining multiple Raman-based techniques indicated that MGII may have the ability to produce lipids distinct from other archaeal species. Our study provides a valuable approach for investigating and classifying archaea, especially uncultured species, at the single-cell level.

Blood identification at the single-cell level based on a combination of laser tweezers Raman spectroscopy and machine learning

Laser tweezers Raman spectroscopy (LTRS) combines optical tweezers technology and Raman spectroscopy to obtain biomolecular compositional information from a single cell without invasion or destruction, so it can be used to "fingerprint" substances to characterize numerous types of biological cell samples. In the current study, LTRS was combined with two machine learning algorithms, principal component analysis (PCA)-linear discriminant analysis (LDA) and random forest, to achieve high-precision multi-species blood classification at the single-cell level. The accuracies of the two classification models were 96.60% and 96.84%, respectively. Meanwhile, compared with PCA-LDA and other classification algorithms, the random forest algorithm is proved to have significant advantages, which can directly explain the importance of spectral features at the molecular level.

Identification of antibiotic resistance and virulence-encoding factors in Klebsiella pneumoniae by Raman spectroscopy and deep learning

Klebsiella pneumoniae has become the number one bacterial pathogen that causes high mortality in clinical settings worldwide. Clinical K. pneumoniae strains with carbapenem resistance and/or hypervirulent phenotypes cause higher mortality comparing with classical K. pneumoniae strains. Rapid differentiation of clinical K. pneumoniae with high resistance/hypervirulence from classical K. pneumoniae would allow us to develop rational and timely treatment plans. In this study, we developed a convolution neural network (CNN) as a prediction method using Raman spectra raw data for rapid identification of ARGs, hypervirulence‐encoding factors and resistance phenotypes from K. pneumoniae strains. A total of 71 K. pneumoniae strains were included in this study. The minimum inhibitory concentrations (MICs) of 15 commonly used antimicrobial agents on K. pneumoniae strains were determined. Seven thousand four hundred fifty‐five spectra were obtained using the InVia Reflex confocal Raman microscope and used for deep learning‐based and machine learning (ML) algorithms analyses. The quality of predictors was estimated in an independent data set. The results of antibiotic resistance and virulence‐encoding factors identification showed that the CNN model not only simplified the classification system for Raman spectroscopy but also provided significantly higher accuracy to identify K. pneumoniae with high resistance and virulence when compared with the support vector machine (SVM) and logistic regression (LR) models. By back‐testing the Raman‐CNN platform on 71 K. pneumoniae strains, we found that Raman spectroscopy allows for highly accurate and rationally designed treatment plans against bacterial infections within hours. More importantly, this method could reduce healthcare costs and antibiotics misuse, limiting the development of antimicrobial resistance and improving patient outcomes.

Rapid SERS identification of methicillin-susceptible and methicillin-resistant Staphylococcus aureus via aptamer recognition and deep learning

Here, we report a label-free surface-enhanced Raman scattering (SERS) method for the rapid and accurate identification of methicillin-susceptible Staphylococcus aureus (MSSA) and methicillin-resistant Staphylococcus aureus (MRSA) based on aptamer-guided AgNP enhancement and convolutional neural network (CNN) classification. Sixty clinical isolates of Staphylococcus aureus (S. aureus), comprising 30 strains of MSSA and 30 strains of MRSA were used to build the CNN classification model. The developed method exhibited 100% identification accuracy for MSSA and MRSA, and is thus a promising tool for the rapid detection of drug-sensitive and drug-resistant bacterial strains.

Machine learning-assisted single-cell Raman fingerprinting for in situ and nondestructive classification of prokaryotes

Accessing enormous uncultivated microorganisms (microbial dark matter) in various Earth environments requires accurate, nondestructive classification, and molecular understanding of the microorganisms in in situ and at the single-cell level. Here we demonstrate a combined approach of random forest (RF) machine learning and single-cell Raman microspectroscopy for accurate classification of phylogenetically diverse prokaryotes (three bacterial and three archaeal species from different phyla). Our RF classifier achieved a 98.8 ± 1.9% classification accuracy among the six species in pure populations and 98.4% for three species in an artificially mixed population. Feature importance scores against each wavenumber reveal that the presence of carotenoids and structure of membrane lipids play key roles in distinguishing the prokaryotic species. We also find unique Raman markers for an ammonia-oxidizing archaeon. Our approach with moderate data pretreatment and intuitive visualization of feature importance is easy to use for non-spectroscopists, and thus offers microbiologists a new single-cell tool for shedding light on microbial dark matter.

•

Random forest models classify prokaryotic species with high accuracy of >98%

•

Both bacteria and archaea are classified using minimally preprocessed Raman data

•

Feature importance reveals what biomolecules contribute to species classification

•

Raman marker bands for some archaeal species are discovered

Interpreting convolutional neural network for real-time volatile organic compounds detection and classification using optical emission spectroscopy of plasma

This study presents the investigation of optical emission spectroscopy of plasma using interpretable convolutional neural network (CNN) for real-time volatile organic compounds (VOCs) classification. A microplasma-generation platform was developed to efficiently collect 64 k spectra from various types of VOCs at different concentrations, as training and testing sets for machine learning. A CNN model was trained to classify VOCs with accuracy of 99.9%. To interpret the CNN model and its predictions, the spectral processing mechanism of the CNN was visualized by feature maps and the critical spectral features were identified by gradient-weighted class activation mapping. Such approaches brought insights on how CNN analyzes the spectra and enables the CNN operation to be explainable. Finally, the CNN model was incorporated with the microplasma platform to demonstrate the application of real-time VOC monitoring. The type of VOCs can be identified and reported via messages within 10 s once the microplasma is ignited. We believe that using CNN brings a novel route for plasma spectroscopy analysis for VOC classification and impacts the fields of plasma, spectroscopy, and environmental monitoring.

Comparative Analysis of Machine Learning Algorithms on Surface Enhanced Raman Spectra of Clinical Staphylococcus Species

Raman spectroscopy (RS) is a widely used analytical technique based on the detection of molecular vibrations in a defined system, which generates Raman spectra that contain unique and highly resolved fingerprints of the system. However, the low intensity of normal Raman scattering effect greatly hinders its application. Recently, the newly emerged surface enhanced Raman spectroscopy (SERS) technique overcomes the problem by mixing metal nanoparticles such as gold and silver with samples, which greatly enhances signal intensity of Raman effects by orders of magnitudes when compared with regular RS. In clinical and research laboratories, SERS provides a great potential for fast, sensitive, label-free, and non-destructive microbial detection and identification with the assistance of appropriate machine learning (ML) algorithms. However, choosing an appropriate algorithm for a specific group of bacterial species remains challenging, because with the large volumes of data generated during SERS analysis not all algorithms could achieve a relatively high accuracy. In this study, we compared three unsupervised machine learning methods and 10 supervised machine learning methods, respectively, on 2,752 SERS spectra from 117 Staphylococcus strains belonging to nine clinically important Staphylococcus species in order to test the capacity of different machine learning methods for bacterial rapid differentiation and accurate prediction. According to the results, density-based spatial clustering of applications with noise (DBSCAN) showed the best clustering capacity (Rand index 0.9733) while convolutional neural network (CNN) topped all other supervised machine learning methods as the best model for predicting Staphylococcus species via SERS spectra (ACC 98.21%, AUC 99.93%). Taken together, this study shows that machine learning methods are capable of distinguishing closely related Staphylococcus species and therefore have great application potentials for bacterial pathogen diagnosis in clinical settings.