A Machine Learning-Based Raman Spectroscopic Assay for the Identification of Burkholderia mallei and Related Species

Intelligent identification of foodborne pathogenic bacteria by self-transfer deep learning and ensemble prediction based on single-cell Raman spectrum

Foodborne pathogenic infections pose a significant threat to human health. Accurate detection of foodborne diseases is essential in preventing disease transmission. This study proposed an AI model for precisely identifying foodborne pathogenic bacteria based on single-cell Raman spectrum. Self-transfer deep learning and ensemble prediction algorithms had been incorporated into the model framework to improve training efficiency and predictive performance, significantly improving prediction results. Our model can identify simultaneously gram-negative and positive, genus, species of foodborne pathogenic bacteria with an accuracy over 99.99 %, as well as recognized strain with over 99.49 %. At all four classification levels, unprecedented excellent predictive performance had been achieved. This advancement holds practical significance for medical detection and diagnosis of foodborne diseases by reducing false negatives.

Rapid, antibiotic incubation-free determination of tuberculosis drug resistance using machine learning and Raman spectroscopy

Tuberculosis (TB) is the world's deadliest infectious disease, with over 1.5 million deaths and 10 million new cases reported anually. The causative organism Mycobacterium tuberculosis (Mtb) can take nearly 40 d to culture, a required step to determine the pathogen's antibiotic susceptibility. Both rapid identification and rapid antibiotic susceptibility testing of Mtb are essential for effective patient treatment and combating antimicrobial resistance. Here, we demonstrate a rapid, culture-free, and antibiotic incubation-free drug susceptibility test for TB using Raman spectroscopy and machine learning. We collect few-to-single-cell Raman spectra from over 25,000 cells of the Mtb complex strain Bacillus Calmette-Guérin (BCG) resistant to one of the four mainstay anti-TB drugs, isoniazid, rifampicin, moxifloxacin, and amikacin, as well as a pan-susceptible wildtype strain. By training a neural network on this data, we classify the antibiotic resistance profile of each strain, both on dried samples and on patient sputum samples. On dried samples, we achieve >98% resistant versus susceptible classification accuracy across all five BCG strains. In patient sputum samples, we achieve ~79% average classification accuracy. We develop a feature recognition algorithm in order to verify that our machine learning model is using biologically relevant spectral features to assess the resistance profiles of our mycobacterial strains. Finally, we demonstrate how this approach can be deployed in resource-limited settings by developing a low-cost, portable Raman microscope that costs <$5,000. We show how this instrument and our machine learning model enable combined microscopy and spectroscopy for accurate few-to-single-cell drug susceptibility testing of BCG.

Non-destructive diagnostic testing of cardiac myxoma by serum confocal Raman microspectroscopy combined with multivariate analysis

The symptoms of cardiac myxoma (CM) mainly occur when the tumor is growing, and the diagnosis is determined by clinical presentation. Unfortunately, there is no evidence that specific blood tests are useful in CM diagnosis. Raman spectroscopy (RS) has emerged as a promising auxiliary diagnostic tool because of its ability to simultaneously detect multiple molecular features without labelling. The objective of this study was to identify spectral markers for CM, one of the most common benign cardiac tumors with insidious onset and rapid progression. In this study, a preliminary analysis was conducted based on serum Raman spectra to obtain the spectral differences between CM patients (CM group) and healthy control subjects (normal group). Principal component analysis-linear discriminant analysis (PCA-LDA) was constructed to highlight the differences in the distribution of biochemical components among the groups according to the obtained spectral information. Principal component analysis was combined with a support vector machine model (PCA-SVM) based on three different kernel functions (linear, polynomial, and Gaussian radial basis function (RBF)) to resolve spectral variations between all study groups. The results showed that CM patients had lower serum levels of phenylalanine and carotenoid than those in the normal group, and increased levels of fatty acids. The resulting Raman data was used in a multivariate analysis to determine the Raman range that could be used for CM diagnosis. Also, the chemical interpretation of the spectral results obtained is further presented in the discussion section based on the multivariate curve resolution-alternating least squares (MCR-ALS) method. These results suggest that RS can be used as an adjunct and promising tool for CM diagnosis, and that vibrations in the fingerprint region can be used as spectral markers for the disease under study.

Label-free differentiation of clinical E. coli and Klebsiella isolates with Raman spectroscopy

Raman spectroscopy is a promising spectroscopic technique for microbiological diagnostics. In routine diagnostic, the differentiation of pathogens of the Enterobacteriaceae family remain challenging. In this study, Raman spectroscopy was applied for the differentiation of 24 clinical E. coli, Klebsiella pneumoniae and Klebsiella oxytoca isolates. Spectra were collected with two spectroscopic approaches: UV-Resonance Raman spectroscopy (UVRR) and single-cell Raman microspectroscopy with 532 nm excitation. A description of the different biochemical profiles provided by the different excitation wavelengths was performed followed by machine-learning models for the classification at the genus and species levels. UVRR was shown to outperform 532 nm excitation, enabling correct classification at the genus level of 23/24 isolates. Furthermore, for the first time, Klebsiella species were correctly classified at the species level with 92% accuracy, classifying all three K. oxytoca isolates correctly. These findings should guide future applicative studies, increasing the scope of Raman spectroscopy's suitability for clinical applications.

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.

Machine Learning Approach for Application-Tailored Nanolubricants’ Design

The fascinating tribological phenomenon of carbon nanotubes (CNTs) observed at the nanoscale was confirmed in our numerous macroscale experiments. We designed and employed CNT-containing nanolubricants strictly for polymer lubrication. In this paper, we present the experiment characterising how the CNT structure determines its lubricity on various types of polymers. There is a complex correlation between the microscopic and spectral properties of CNTs and the tribological parameters of the resulting lubricants. This confirms indirectly that the nature of the tribological mechanisms driven by the variety of CNT–polymer interactions might be far more complex than ever described before. We propose plasmonic interactions as an extension for existing models describing the tribological roles of nanomaterials. In the absence of quantitative microscopic calculations of tribological parameters, phenomenological strategies must be employed. One of the most powerful emerging numerical methods is machine learning (ML). Here, we propose to use this technique, in combination with molecular and supramolecular recognition, to understand the morphology and macro-assembly processing strategies for the targeted design of superlubricants.

Machine Learning-Assisted Sampling of Surfance-Enhanced Raman Scattering (SERS) Substrates Improve Data Collection Efficiency

Surface-enhanced Raman scattering (SERS) is a powerful technique for sensitive label-free analysis of chemical and biological samples. While much recent work has established sophisticated automation routines using machine learning and related artificial intelligence methods, these efforts have largely focused on downstream processing (e.g., classification tasks) of previously collected data. While fully automated analysis pipelines are desirable, current progress is limited by cumbersome and manually intensive sample preparation and data collection steps. Specifically, a typical lab-scale SERS experiment requires the user to evaluate the quality and reliability of the measurement (i.e., the spectra) as the data are being collected. This need for expert user-intuition is a major bottleneck that limits applicability of SERS-based diagnostics for point-of-care clinical applications, where trained spectroscopists are likely unavailable. While application-agnostic numerical approaches (e.g., signal-to-noise thresholding) are useful, there is an urgent need to develop algorithms that leverage expert user intuition and domain knowledge to simplify and accelerate data collection steps. To address this challenge, in this work, we introduce a machine learning-assisted method at the acquisition stage. We tested six common algorithms to measure best performance in the context of spectral quality judgment. For adoption into future automation platforms, we developed an open-source python package tailored for rapid expert user annotation to train machine learning algorithms. We expect that this new approach to use machine learning to assist in data acquisition can serve as a useful building block for point-of-care SERS diagnostic platforms.

Detection of multi-resistant clinical strains of E. coli with Raman spectroscopy

In recent years, we have seen a steady rise in the prevalence of antibiotic-resistant bacteria. This creates many challenges in treating patients who carry these infections, as well as stopping and preventing outbreaks. Identifying these resistant bacteria is critical for treatment decisions and epidemiological studies. However, current methods for identification of resistance either require long cultivation steps or expensive reagents. Raman spectroscopy has been shown in the past to enable the rapid identification of bacterial strains from single cells and cultures. In this study, Raman spectroscopy was applied for the differentiation of resistant and sensitive strains of Escherichia coli. Our focus was on clinical multi-resistant (extended-spectrum β-lactam and carbapenem-resistant) bacteria from hospital patients. The spectra were collected using both UV resonance Raman spectroscopy in bulk and single-cell Raman microspectroscopy, without exposure to antibiotics. We found resistant strains have a higher nucleic acid/protein ratio, and used the spectra to train a machine learning model that differentiates resistant and sensitive strains. In addition, we applied a majority of voting system to both improve the accuracy of our models and make them more applicable for a clinical setting. This method could allow rapid and accurate identification of antibiotic resistant bacteria, and thus improve public health.

Methodological tools to study species of the genus Burkholderia

Bacteria belonging to the Burkholderia genus are extremely versatile and diverse. They can be environmental isolates, opportunistic pathogens in cystic fibrosis, immunocompromised or chronic granulomatous disease patients, or cause disease in healthy people (e.g., Burkholderia pseudomallei) or animals (as in the case of Burkholderia mallei). Since the genus was separated from the Pseudomonas one in the 1990s, the methodological tools to study and characterize these bacteria are evolving fast. Here we reviewed the techniques used in the last few years to update the taxonomy of the genus, to study gene functions and regulations, to deepen the knowledge on the drug resistance which characterizes these bacteria, and to elucidate their mechanisms to establish infections. The availability of these tools significantly impacts the quality of research on Burkholderia and the choice of the most appropriated is fundamental for a precise characterization of the species of interest.

Key points

• Updated techniques to study the genus Burkholderia were reviewed.

• Taxonomy, genomics, assays, and animal models were described.

• A comprehensive overview on recent advances in Burkholderia studies was made.

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.

Applications of Raman Spectroscopy in Bacterial Infections: Principles, Advantages, and Shortcomings

Infectious diseases caused by bacterial pathogens are important public issues. In addition, due to the overuse of antibiotics, many multidrug-resistant bacterial pathogens have been widely encountered in clinical settings. Thus, the fast identification of bacteria pathogens and profiling of antibiotic resistance could greatly facilitate the precise treatment strategy of infectious diseases. So far, many conventional and molecular methods, both manual or automatized, have been developed for in vitro diagnostics, which have been proven to be accurate, reliable, and time efficient. Although Raman spectroscopy (RS) is an established technique in various fields such as geochemistry and material science, it is still considered as an emerging tool in research and diagnosis of infectious diseases. Based on current studies, it is too early to claim that RS may provide practical guidelines for microbiologists and clinicians because there is still a gap between basic research and clinical implementation. However, due to the promising prospects of label-free detection and noninvasive identification of bacterial infections and antibiotic resistance in several single steps, it is necessary to have an overview of the technique in terms of its strong points and shortcomings. Thus, in this review, we went through recent studies of RS in the field of infectious diseases, highlighting the application potentials of the technique and also current challenges that prevent its real-world applications.

Surface-enhanced Raman spectroscopy for bioanalysis and diagnosis

In recent years, bioanalytical surface-enhanced Raman spectroscopy (SERS) has blossomed into a fast-growing research area. Owing to its high sensitivity and outstanding multiplexing ability, SERS is an effective analytical technique that has excellent potential in bioanalysis and diagnosis, as demonstrated by its increasing applications in vivo. SERS allows the rapid detection of molecular species based on direct and indirect strategies. Because it benefits from the tunable surface properties of nanostructures, it finds a broad range of applications with clinical relevance, such as biological sensing, drug delivery and live cell imaging assays. Of particular interest are early-stage-cancer detection and the fast detection of pathogens. Here, we present a comprehensive survey of SERS-based assays, from basic considerations to bioanalytical applications. Our main focus is on SERS-based pathogen detection methods as point-of-care solutions for early bacterial infection detection and chronic disease diagnosis. Additionally, various promising in vivo applications of SERS are surveyed. Furthermore, we provide a brief outlook of recent endeavours and we discuss future prospects and limitations for SERS, as a reliable approach for rapid and sensitive bioanalysis and diagnosis.

Artificial Intelligence in Chemistry: Current Trends and Future Directions

The application of artificial intelligence (AI) to chemistry has grown tremendously in recent years. In this Review, we studied the growth and distribution of AI-related chemistry publications in the last two decades using the CAS Content Collection. The volume of both journal and patent publications have increased dramatically, especially since 2015. Study of the distribution of publications over various chemistry research areas revealed that analytical chemistry and biochemistry are integrating AI to the greatest extent and with the highest growth rates. We also investigated trends in interdisciplinary research and identified frequently occurring combinations of research areas in publications. Furthermore, topic analyses were conducted for journal and patent publications to illustrate emerging associations of AI with certain chemistry research topics. Notable publications in various chemistry disciplines were then evaluated and presented to highlight emerging use cases. Finally, the occurrence of different classes of substances and their roles in AI-related chemistry research were quantified, further detailing the popularity of AI adoption in the life sciences and analytical chemistry. In summary, this Review offers a broad overview of how AI has progressed in various fields of chemistry and aims to provide an understanding of its future directions.

Culture-Free Identification and Metabolic Profiling of Microalgal Single Cells via Ensemble Learning of Ramanomes

Microalgae are among the most genetically and metabolically diverse organisms on earth, yet their identification and metabolic profiling have generally been slow and tedious. Here, we established a reference ramanome database consisting of single-cell Raman spectra (SCRS) from >9000 cells of 27 phylogenetically diverse microalgal species, each under stationary and exponential states. When combined, prequenching ("pigment spectrum" (PS)) and postquenching ("whole spectrum" (WS)) signals can classify species and states with 97% accuracy via ensemble machine learning. Moreover, the biosynthetic profile of Raman-sensitive metabolites was unveiled at single cells, and their interconversion was detected via intra-ramanome correlation analysis. Furthermore, not-yet-cultured cells from the environment were functionally characterized via PS and WS and then phylogenetically identified by Raman-activated sorting and sequencing. This PS-WS combined approach for rapidly identifying and metabolically profiling single cells, either cultured or uncultured, greatly accelerates the mining of microalgae and their products.

Deep Learning for Biospectroscopy and Biospectral Imaging: State-of-the-Art and Perspectives

With the advances in instrumentation and sampling techniques, there is an explosive growth of data from molecular and cellular samples. The call to extract more information from the large data sets has greatly challenged the conventional chemometrics method. Deep learning, which utilizes very large data sets for finding hidden features therein and for making accurate predictions for a wide range of applications, has been applied in an unbelievable pace in biospectroscopy and biospectral imaging in the recent 3 years. In this Feature, we first introduce the background and basic knowledge of deep learning. We then focus on the emerging applications of deep learning in the data preprocessing, feature detection, and modeling of the biological samples for spectral analysis and spectroscopic imaging. Finally, we highlight the challenges and limitations in deep learning and the outlook for future directions.

Toward rapid infectious disease diagnosis with advances in surface-enhanced Raman spectroscopy

In a pandemic era, rapid infectious disease diagnosis is essential. Surface-enhanced Raman spectroscopy (SERS) promises sensitive and specific diagnosis including rapid point-of-care detection and drug susceptibility testing. SERS utilizes inelastic light scattering arising from the interaction of incident photons with molecular vibrations, enhanced by orders of magnitude with resonant metallic or dielectric nanostructures. While SERS provides a spectral fingerprint of the sample, clinical translation is lagged due to challenges in consistency of spectral enhancement, complexity in spectral interpretation, insufficient specificity and sensitivity, and inefficient workflow from patient sample collection to spectral acquisition. Here, we highlight the recent, complementary advances that address these shortcomings, including (1) design of label-free SERS substrates and data processing algorithms that improve spectral signal and interpretability, essential for broad pathogen screening assays; (2) development of new capture and affinity agents, such as aptamers and polymers, critical for determining the presence or absence of particular pathogens; and (3) microfluidic and bioprinting platforms for efficient clinical sample processing. We also describe the development of low-cost, point-of-care, optical SERS hardware. Our paper focuses on SERS for viral and bacterial detection, in hopes of accelerating infectious disease diagnosis, monitoring, and vaccine development. With advances in SERS substrates, machine learning, and microfluidics and bioprinting, the specificity, sensitivity, and speed of SERS can be readily translated from laboratory bench to patient bedside, accelerating point-of-care diagnosis, personalized medicine, and precision health.

Mammalian cell and tissue imaging using Raman and coherent Raman microscopy

Direct imaging of metabolism in cells or multicellular organisms is important for understanding many biological processes. Raman scattering (RS) microscopy, particularly, coherent Raman scattering (CRS) such as coherent anti-Stokes Raman scattering (CARS) and stimulated Raman scattering (SRS), has emerged as a powerful platform for cellular imaging due to its high chemical selectivity, sensitivity, and imaging speed. RS microscopy has been extensively used for the identification of subcellular structures, metabolic observation, and phenotypic characterization. Conjugating RS modalities with other techniques such as fluorescence or infrared (IR) spectroscopy, flow cytometry, and RNA-sequencing can further extend the applications of RS imaging in microbiology, system biology, neurology, tumor biology and more. Here we overview RS modalities and techniques for mammalian cell and tissue imaging, with a focus on the advances and applications of CARS and SRS microscopy, for a better understanding of the metabolism and dynamics of lipids, protein, glucose, and nucleic acids in mammalian cells and tissues. This article is categorized under: Laboratory Methods and Technologies > Imaging Biological Mechanisms > Metabolism Analytical and Computational Methods > Analytical Methods.

Bioinspired cell-in-shell systems in biomedical engineering and beyond: Comparative overview and prospects

With the development in tissue engineering, cell transplantation, and genetic technologies, living cells have become an important therapeutic tool in clinical medical care. For various cell-based technologies including cell therapy and cell-based sensors in addition to fundamental studies on single-cell biology, the cytoprotection of individual living cells is a prerequisite to extend cell storage life or deliver cells from one place to another, resisting various external stresses. Nature has evolved a biological defense mechanism to preserve their species under unfavorable conditions by forming a hard and protective armor. Particularly, plant seeds covered with seed coat turn into a dormant state against stressful environments, due to mechanical and water/gas constraints imposed by hard seed coat. However, when the environmental conditions become hospitable to seeds, seed coat is ruptured, initiating seed germination. This seed dormancy and germination mechanism has inspired various approaches that artificially induce cell sporulation via chemically encapsulating individual living cells within a thin but tough shell forming a 3D "cell-in-shell" structure. Herein, the recent advance of cell encapsulation strategies along with the potential advantages of the 3D "cell-in-shell" system is reviewed. Diverse coating materials including polymeric shells and hybrid shells on different types of cells ranging from microbes to mammalian cells will be discussed in terms of enhanced cytoprotective ability, control of division, chemical functionalization, and on-demand shell degradation. Finally, current and potential applications of "cell-in-shell" systems for cell-based technologies with remaining challenges will be explored.