Deep Learning-Assisted Surface-Enhanced Raman Scattering for Rapid Bacterial Identification

Identification of surface-enhanced Raman spectroscopy using hybrid transformer network

Surface-enhanced Raman Spectroscopy (SERS) is extensively implemented in drug detection due to its sensitivity and non-destructive nature. Deep learning methods, which are represented by convolutional neural network (CNN), have been widely applied in identifying the spectra from SERS for powerful learning ability. However, the local receptive field of CNN limits the feature extraction of sequential spectra for suppressing the analysis results. In this study, a hybrid Transformer network, TMNet, was developed to identify SERS spectra by integrating the Transformer encoder and the multi-layer perceptron. The Transformer encoder can obtain precise feature representations of sequential spectra with the aid of self-attention, and the multi-layer perceptron efficiently transforms the representations to the final identification results. TMNet performed excellently, with identification accuracies of 99.07% for the spectra of hair containing drugs and 97.12% for those of urine containing drugs. For the spectra with additive white Gaussian, baseline background, and mixed noises, TMNet still exhibited the best performance among all the methods. Overall, the proposed method can accurately identify SERS spectra with outstanding noise resistance and excellent generalization and holds great potential for the analysis of other spectroscopy data.

Rapid identification of bloodstream infection pathogens and drug resistance using Raman spectroscopy enhanced by convolutional neural networks

Bloodstream infections (BSIs) are a critical medical concern, characterized by elevated morbidity, mortality, extended hospital stays, substantial healthcare costs, and diagnostic challenges. The clinical outcomes for patients with BSI can be markedly improved through the prompt identification of the causative pathogens and their susceptibility to antibiotics and antimicrobial agents. Traditional BSI diagnosis via blood culture is often hindered by its lengthy incubation period and its limitations in detecting pathogenic bacteria and their resistance profiles. Surface-enhanced Raman scattering (SERS) has recently gained prominence as a rapid and effective technique for identifying pathogenic bacteria and assessing drug resistance. This method offers molecular fingerprinting with benefits such as rapidity, sensitivity, and non-destructiveness. The objective of this study was to integrate deep learning (DL) with SERS for the rapid identification of common pathogens and their resistance to drugs in BSIs. To assess the feasibility of combining DL with SERS for direct detection, erythrocyte lysis and differential centrifugation were employed to isolate bacteria from blood samples with positive blood cultures. A total of 12,046 and 11,968 SERS spectra were collected from the two methods using Raman spectroscopy and subsequently analyzed using DL algorithms. The findings reveal that convolutional neural networks (CNNs) exhibit considerable potential in identifying prevalent pathogens and their drug-resistant strains. The differential centrifugation technique outperformed erythrocyte lysis in bacterial isolation from blood, achieving a detection accuracy of 98.68% for pathogenic bacteria and an impressive 99.85% accuracy in identifying carbapenem-resistant Klebsiella pneumoniae. In summary, this research successfully developed an innovative approach by combining DL with SERS for the swift identification of pathogenic bacteria and their drug resistance in BSIs. This novel method holds the promise of significantly improving patient prognoses and optimizing healthcare efficiency. Its potential impact could be profound, potentially transforming the diagnostic and therapeutic landscape of BSIs.

Sea hedgehog-inspired surface-enhanced Raman scattering biosensor probe for ultrasensitive determination of Staphylococcus aureus in food supplements

Staphylococcus aureus contamination in food supplements poses substantial challenges to public health and large-scale production but the sensitive detection in a timely manner remains a bottleneck. Drawing inspiration from the sea hedgehog, gold nanostars (AuNSs) were leveraged to design an ultrasensitive surface-enhanced Raman scattering (SERS) biosensor for the determination of Staphylococcus aureus in food supplements. Besides the surface enhancement furnished by the AuNSs, Raman reporter molecules and specific aptamers sequentially self-assembled onto these AuNSs to construct the "three-in-one" SERS biosensor probe for label-based quantitation of Staphylococcus aureus. Following incubation with contaminated health product samples, the gold nanostars@Raman reporter-aptamer specifically recognize and assemble around Staphylococcus aureus cells, forming a distinctive sea hedgehog structure. This unique configuration results in an amplified Raman signal at 1338 cm-1 and an enhancement factor of up to 6.71 × 107. The entire quantitative detection process can be completed within 30 min, boasting an exceptional limit of detection as low as 1.0 CFU mL-1. The method exhibits a broad working range for the determination of Staphylococcus aureus, with concentrations spanning 2.15 CFU mL-1 to 2.15 × 105 CFU mL-1. Furthermore, it demonstrates outstanding precision, with relative standard deviation values consistently below 5.0%. As a showcase to validate the practicality of the SERS method, we conducted tests on determining Staphylococcus aureus in a herbal food supplement, i.e., Ginkgo Biloba extract (GBE); the results align closely with those obtained through the conventional lysogeny broth agar plate method, pointing to the potential applicability in real-world scenarios.

Rapid and Precise Differentiation and Authentication of Agricultural Products via Deep Learning-Assisted Multiplex SERS Fingerprinting

Accurate and rapid differentiation and authentication of agricultural products based on their origin and quality are crucial to ensuring food safety and quality control. However, similar chemical compositions and complex matrices often hinder precise identification, particularly for adulterated samples. Herein, we propose a novel method combining multiplex surface-enhanced Raman scattering (SERS) fingerprinting with a one-dimensional convolutional neural network (1D-CNN), which enables the effective differentiation of the category, origin, and grade of agricultural products. This strategy leverages three different SERS-active nanoparticles as multiplex sensors, each tailored to selectively amplify the signals of preferentially adsorbed chemicals within the sample. By strategically combining SERS spectra from different NPs, a 'SERS super-fingerprint' is constructed, offering a more comprehensive representation of the characteristic information on agricultural products. Subsequently, utilizing a custom-designed 1D-CNN model for feature extraction from the 'super-fingerprint' significantly enhances the predictive accuracy for agricultural products. This strategy successfully identified various agricultural products and simulated adulterated samples with exceptional accuracy, reaching 97.7% and 94.8%, respectively. Notably, the entire identification process, encompassing sample preparation, SERS measurement, and deep learning analysis, takes only 35 min. This development of deep learning-assisted multiplex SERS fingerprinting establishes a rapid and reliable method for the identification and authentication of agricultural products.

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.

Artificial Intelligence for Surface-Enhanced Raman Spectroscopy

Surface-enhanced Raman spectroscopy (SERS), well acknowledged as a fingerprinting and sensitive analytical technique, has exerted high applicational value in a broad range of fields including biomedicine, environmental protection, food safety among the others. In the endless pursuit of ever-sensitive, robust, and comprehensive sensing and imaging, advancements keep emerging in the whole pipeline of SERS, from the design of SERS substrates and reporter molecules, synthetic route planning, instrument refinement, to data preprocessing and analysis methods. Artificial intelligence (AI), which is created to imitate and eventually exceed human behaviors, has exhibited its power in learning high-level representations and recognizing complicated patterns with exceptional automaticity. Therefore, facing up with the intertwining influential factors and explosive data size, AI has been increasingly leveraged in all the above-mentioned aspects in SERS, presenting elite efficiency in accelerating systematic optimization and deepening understanding about the fundamental physics and spectral data, which far transcends human labors and conventional computations. In this review, the recent progresses in SERS are summarized through the integration of AI, and new insights of the challenges and perspectives are provided in aim to better gear SERS toward the fast track.

Surface-Enhanced Raman Scattering-Based Surface Chemotaxonomy: Combining Bacteria Extracellular Matrices and Machine Learning for Rapid and Universal Species Identification

Rapid, universal, and accurate identification of bacteria in their natural states is necessary for on-site environmental monitoring and fundamental microbial research. Surface-enhanced Raman scattering (SERS) spectroscopy emerges as an attractive tool due to its molecule-specific spectral fingerprinting and multiplexing capabilities, as well as portability and speed of readout. Here, we develop a SERS-based surface chemotaxonomy that uses bacterial extracellular matrices (ECMs) as proxy biosignatures to hierarchically classify bacteria based on their shared surface biochemical characteristics to eventually identify six distinct bacterial species at >98% classification accuracy. Corroborating with in silico simulations, we establish a three-way inter-relation between the bacteria identity, their ECM surface characteristics, and their SERS spectral fingerprints. The SERS spectra effectively capture multitiered surface biochemical insights including ensemble surface characteristics, e.g., charge and biochemical profiles, and molecular-level information, e.g., types and numbers of functional groups. Our surface chemotaxonomy thus offers an orthogonal taxonomic definition to traditional classification methods and is achieved without gene amplification, biochemical testing, or specific biomarker recognition, which holds great promise for point-of-need applications and microbial research.