Classification of Preeclamptic Placental Extracellular Vesicles Using Femtosecond Laser Fabricated Nanoplasmonic Sensors

Deep autoencoder as an interpretable tool for Raman spectroscopy investigation of chemical and extracellular vesicle mixtures

Surface-enhanced Raman spectroscopy (SERS) is a powerful tool that provides valuable insight into the molecular contents of chemical and biological samples. However, interpreting Raman spectra from complex or dynamic datasets remains challenging, particularly for highly heterogeneous biological samples like extracellular vesicles (EVs). To overcome this, we developed a tunable and interpretable deep autoencoder for the analysis of several challenging Raman spectroscopy applications, including synthetic datasets, chemical mixtures, a chemical milling reaction, and mixtures of EVs. We compared the results with classical methods (PCA and UMAP) to demonstrate the superior performance of the proposed technique. Our method can handle small datasets, provide a high degree of generalization such that it can fill unknown gaps within spectral datasets, and even quantify relative ratios of cell line-derived EVs to fetal bovine serum-derived EVs within mixtures. This simple yet robust approach will greatly improve the analysis capabilities for many other Raman spectroscopy applications.

Manifold Learning Enables Interpretable Analysis of Raman Spectra from Extracellular Vesicle and Other Mixtures

Extracellular vesicles (EVs) have emerged as promising diagnostic and therapeutic candidates in many biomedical applications. However, EV research continues to rely heavily on in vitro cell cultures for EV production, where the exogenous EVs present in fetal bovine (FBS) or other required serum supplementation can be difficult to remove entirely. Despite this and other potential applications involving EV mixtures, there are currently no rapid, robust, inexpensive, and label-free methods for determining the relative concentrations of different EV subpopulations within a sample. In this study, we demonstrate that surface-enhanced Raman spectroscopy (SERS) can biochemically fingerprint fetal bovine serum-derived and bioreactor-produced EVs, and after applying a novel manifold learning technique to the acquired spectra, enables the quantitative detection of the relative amounts of different EV populations within an unknown sample. We first developed this method using known ratios of Rhodamine B to Rhodamine 6G, then using known ratios of FBS EVs to breast cancer EVs from a bioreactor culture. In addition to quantifying EV mixtures, the proposed deep learning architecture provides some knowledge discovery capabilities which we demonstrate by applying it to dynamic Raman spectra of a chemical milling process. This label-free characterization and analytical approach should translate well to other EV SERS applications, such as monitoring the integrity of semipermeable membranes within EV bioreactors, ensuring the quality or potency of diagnostic or therapeutic EVs, determining relative amounts of EVs produced in complex co-culture systems, as well as many Raman spectroscopy applications.

Machine learning-augmented surface-enhanced spectroscopy toward next-generation molecular diagnostics

The world today is witnessing the significant role and huge demand for molecular detection and screening in healthcare and medical diagnosis, especially during the outbreak of COVID-19. Surface-enhanced spectroscopy techniques, including Surface-Enhanced Raman Scattering (SERS) and Infrared Absorption (SEIRA), provide lattice and molecular vibrational fingerprint information which is directly linked to the molecular constituents, chemical bonds, and configuration. These properties make them an unambiguous, nondestructive, and label-free toolkit for molecular diagnostics and screening. However, new issues in molecular diagnostics, such as increasing molecular species, faster spread of viruses, and higher requirements for detection accuracy and sensitivity, have brought great challenges to detection technology. Advancements in artificial intelligence and machine learning (ML) techniques show promising potential in empowering SERS and SEIRA with rapid analysis and automatic data processing to jointly tackle the challenge. This review introduces the combination of ML and SERS/SEIRA by investigating how ML algorithms can be beneficial to SERS/SEIRA, discussing the general process of combining ML and SEIRA/SERS, highlighting the molecular diagnostics and screening applications based on ML-combined SEIRA/SERS, and providing perspectives on the future development of ML-integrated SEIRA/SERS. In general, this review offers comprehensive knowledge about the recent advances and the future outlook regarding ML-integrated SEIRA/SERS for molecular diagnostics and screening.

SERS-Based Biosensors Combined with Machine Learning for Medical Application

Surface-enhanced Raman spectroscopy (SERS) has shown strength in non-invasive, rapid, trace analysis and has been used in many fields in medicine. Machine learning (ML) is an algorithm that can imitate human learning styles and structure existing content with the knowledge to effectively improve learning efficiency. Integrating SERS and ML can have a promising future in the medical field. In this review, we summarize the applications of SERS combined with ML in recent years, such as the recognition of biological molecules, rapid diagnosis of diseases, developing of new immunoassay techniques, and enhancing SERS capabilities in semi-quantitative measurements. Ultimately, the possible opportunities and challenges of combining SERS with ML are addressed.

Cascaded Deep Convolutional Neural Networks as Improved Methods of Preprocessing Raman Spectroscopy Data

Machine learning has had a significant impact on the value of spectroscopic characterization tools, particularly in biomedical applications, due to its ability to detect latent patterns within complex spectral data. However, it often requires extensive data preprocessing, including baseline correction and denoising, which can lead to an unintentional bias during classification. To address this, we developed two deep learning methods capable of fully preprocessing raw Raman spectroscopy data without any human input. First, cascaded deep convolutional neural networks (CNN) based on either ResNet or U-Net architectures were trained on randomly generated spectra with augmented defects. Then, they were tested using simulated Raman spectra, surface-enhanced Raman spectroscopy (SERS) imaging of chemical species, low resolution Raman spectra of human bladder cancer tissue, and finally, classification of SERS spectra from human placental extracellular vesicles (EVs). Both approaches resulted in faster training and complete spectral preprocessing in a single step, with more speed, defect tolerance, and classification accuracy compared to conventional methods. These findings indicate that cascaded CNN preprocessing is ideal for biomedical Raman spectroscopy applications in which large numbers of heterogeneous spectra with diverse defects need to be automatically, rapidly, and reproducibly preprocessed.