SERS-Based Biosensors Combined with Machine Learning for Medical Application

One-pot preparation of anionic ligand-stabilized gold nanoparticles with low SERS background for detecting reaction intermediates under strong oxidative conditions

Gold nanoparticle-based surface-enhanced Raman scattering (SERS) substrates exhibit better chemical stability compared with silver ones, making them suitable for characterizing reaction intermediates in the presence of strong oxidants such as H2O2. However, conventional wet-chemistry-synthesized gold nanoparticles often show strong background signals from organic stabilizers, which could overlap and disturb the SERS signals of reaction intermediates and products. In this work, a low-background corrosion-resistant gold-based SERS substrate was prepared via a facile one-pot method using anionic ligands as stabilizers, achieving the rapid characterization of the reaction process in the presence of H2O2. Anionic ligands (such as I-, SCN-, Br- and S2O32-) were used instead of commonly used surfactants as stabilizers to obtain monodisperse colloidal gold nanoparticles. The obtained gold nanoparticles displayed an ultralow SERS background signal, allowing for precise characterization of trace reaction intermediates. Moreover, the low-background gold substrate exhibited much better corrosion resistance (10 mM H2O2) compared with the low-background silver substrate, enabling sensitive and stable detection of target analytes even under harsh oxidative conditions. Finally, we successfully employed this SERS substrate for the direct detection and monitoring of degradation intermediates of sulfamerazine (SMR) through a UV-H2O2-induced degradation reaction without using any sample treatment. Combination of SERS spectroscopic data with DFT calculations provided a robust framework for elucidating the photodegradation mechanism. Results indicated that the SERS substrate has a robust and broad application prospect in the precise characterization of various reactions under harsh oxidative conditions. Moreover, this work may provide guidance for the synthesis of other colloidal nanoparticles using anionic ligands as universal stabilizers.

Detection of Cancer Biomarkers: Review of Methods and Applications Reported from Analytical Perspective

One in five deaths in developed countries is related to cancer. The cancer prevalence is likely to grow with aging population. The affordable and accurate early diagnostics of cancer based on detection of cancer biomarkers at low concentration during its early stages is one of the most efficient way to decrease mortality and human suffering from cancer. The data from 201 analytical papers are tabulated in 9 tables, illustrated in 8 figures and used for comparative analysis of methods applied for cancer biomarker detection, including polymerase chain reaction, Loop-mediated isothermal amplification (LAMP), mass spectrometry, enzyme-linked immunosorbent assay, electroanalytical methods, immunoassays, surface enhanced Raman scattering, Fourier Transform Infrared and others in terms of above-mentioned performance parameters. Median and/or average limit of detection (LOD) are calculated and compared between different analytical methods. We also described and compared LOD of the methods used for detection of three frequently detected cancer biomarkers: carcinoembryonic antigen, prostate-specific antigen and alpha-fetoprotein. Among those methods of detection, the reported electrochemical sensors often demonstrate relatively high sensitivity/low LOD while they often have a moderate instrumental cost and fast time to results. The review tabulates, compares and discusses analytical papers, which report LOD of cancer biomarkers and comprehensive quantitative comparison of various analytical methods is made. The discussion of those techniques applied for cancer biomarker detection included brief summary of pro and cons for each of those methods.

Discriminative detection of various organophosphorus nerve agents and analogues based on self-trapping probe coupled with SERS

Organophosphorus nerve agents (OPNAs) are highly lethal chemical warfare agents (CWAs), which poses a serious threat to human health and safety. The accurate and rapid identification of OPNAs is crucial for medical diagnosis and effective treatment. However, distinguishing between various OPNAs and their analogues using on-site point-of-care testing (POCT) remains challenging. Herein, we present a novel Raman-enhanced strategy that employs a chemical capture probe through a structural differential amplification derivative probe coupled with handheld Raman spectrometry. In this method, 2-(dimethylamino methyl)-3-hydroxypyridine (2-DMAMPD) was designed and used to capture target OPNAs in the plasmonic hotspot for the first time. The formation of strong Au-N bonds between nanoparticles and pyridine significantly enhances the cross-section and specific Raman intensity of OPNAs, facilitating effective amplification and differentiation of subtle structural variations among different OPNAs. In practical application, the probe solution can be directly sprayed on the surfaces contaminated by agents, allowing the entire detection process to be completed within five minutes, with a detection limit of 2 ng/mL (equivalent to an absolute content of 50 pg). It is worth noting that during the process of detection, highly toxic OPNAs can be quickly transformed into low-toxic or non-toxic derivatives, which is of great significance for green detection and protection of the operator.

Recent Advances in Food Safety: Nanostructure-Sensitized Surface-Enhanced Raman Sensing

Food safety is directly related to human health and has attracted intense attention all over the world. Surface-enhanced Raman scattering (SERS), as a rapid and selective technique, has been widely applied in monitoring food safety. SERS substrates, as an essential factor for sensing design, greatly influence the analytical performance. Currently, nanostructure-based SERS substrates have garnered significant interest due to their excellent merits in improving the sensitivity, specificity, and stability, holding great potential for the rapid and accurate sensing of food contaminants in complex matrices. This review summarizes the fundamentals of Raman spectroscopy and the used nanostructures for designing the SERS platform, including precious metal nanoparticles, metal-organic frameworks, polymers, and semiconductors. Moreover, it introduces the mechanisms and applications of nanostructures for enhancing SERS signals for monitoring hazardous substances, such as foodborne bacteria, pesticide and veterinary drug residues, food additives, illegal adulterants, and packaging material contamination. Finally, with the continuous progress of nanostructure technology and the continuous improvement of SERS technology, its application prospect in food safety testing will be broader.

Surface Enhanced Raman Scattering for Biomolecular Sensing in Human Healthcare Monitoring

Since the 1980s, surface enhanced Raman scattering (SERS) has been used for the rapid and sensitive detection of biomolecules. Whether a label-free or labeled assay is adopted, SERS has demonstrated low limits of detection in a variety of biological matrices. However, SERS analysis has been confined to the laboratory due to several reasons such as reproducibility and scalability, both of which have been discussed at length in the literature. Another possible issue with the lack of widespread adoption of SERS is that its application in point of use (POU) testing is only now being fully explored due to the advent of portable Raman spectrometers. Researchers are now investigating how SERS can be used as the output on several POU platforms such as lateral flow assays, wearable sensors, and in volatile organic compound (VOC) detection for human healthcare monitoring, with favorable results that rival the gold standard approaches. Another obstacle that SERS faces is the interpretation of the wealth of information obtained from the platform. To combat this, machine learning is being explored and has been shown to provide quick and accurate analysis of the generated data, leading to sensitive detection and discrimination of many clinically relevant biomolecules. This review will discuss the advancements of SERS combined with POU testing and the strength that machine learning can bring to the analysis to produce a powerful combined platform for human healthcare monitoring.

AI in SERS sensing moving from discriminative to generative

This perspective discusses the present and future role of artificial intelligence (AI) and machine learning (ML) in surface-enhanced Raman scattering (SERS) sensing. Our goal is to guide the reader through current applications, mainly focused on discriminative approaches aimed at developing new and improved SERS diagnostic capabilities, towards the future role of AI in SERS sensing, with the use of generative approaches to design new materials and biomaterials.

Diagnosis of Benign and Malignant Newly Developed Nodules on the Surgical Side After Breast Cancer Surgery Based on Machine Learning

Objective: To enhance the diagnostic accuracy of new nodules on the surgical side after breast cancer surgery using machine learning techniques and to explore the role of multifeature fusion. Methods: Data from 137 breast cancer postoperative patients with new nodules from January 2016 to April 2024 were analyzed. Clinical, ultrasound, immunohistochemistry, and surgical features were combined. Multiple machine learning models, including support vector machine (SVM), random forest, gradient boosting, AdaBoost, and XGBoost, were trained and tested. Model performance was evaluated using stratified ten-fold cross-validation. Ablation experiments assessed the impact of different feature combinations on diagnostic performance. Results: The SVM model performed best, with an AUC of 0.8664, an accuracy of 0.8099, a sensitivity of 0.565, and a specificity of 0.9267. Ablation experiments indicated that multifeature fusion significantly improved diagnostic performance, especially when combining clinical, ultrasound, immunohistochemistry, and surgical features. Gradient boosting and random forest models showed slightly inferior performance, while AdaBoost had balanced but lower effectiveness. Conclusion: Machine learning, particularly the multifeature fusion SVM model, shows significant potential in diagnosing new nodules after breast cancer surgery. It can assist doctors in developing more effective treatment plans, improving patient outcomes. Future studies should expand sample sizes, include multicenter data, and explore advanced algorithms to further enhance diagnostic performance.

Recent advances in SERS assays for detection of multiple extracellular vesicles biomarkers for cancer diagnosis

As the prevalence of cancer is escalating, there is an increased demand for early and sensitive diagnostic tools. A major challenge in early detection is the lack of specific biomarkers, and a readily accessible, sensitive and rapid detection method. To meet these challenges, cancer-derived small extracellular vesicles (sEVs) have been discovered as a new promising cancer biomarker due to the high abundance of sEVs in body fluids and their extensive cargo of biomarkers. Additionally, surface-enhanced Raman scattering (SERS) presents a sensitive, multiplexed, and rapid method that has gained attraction with recent studies showing promising results from patient samples for the multiplex detection of cancer sEVs. Various label-based SERS multiplex assays have been developed in the field of SERS including bead assays, lateral flow immunoassays, microfluidic devices, and artificial intelligence (AI)-based label-free SERS chips, targeting multiple surface proteins to ensure comprehensive multiplex diagnostics. These assays hold promise for enabling early detection, quantification, and subtyping of cancer-derived sEVs for cancer diagnostic applications. This review aims to provide a summary of the recent advances in the field of SERS multiplex assays for detection, quantification, and subtyping of sEVs to facilitate cancer diagnosis. This review further provides unique insights into the use of sEVs as a biomarker and aims to address the issues surrounding their translation from laboratories to clinics.

Recent advances in lateral flow assays for MicroRNA detection

Lateral flow assays (LFAs) have emerged as pivotal tools for the rapid and reliable detection of microRNAs (miRNAs). It is believed that these biomarkers are crucial for the diagnosis and prognosis of various diseases, particularly cancer. Traditional miRNA detection techniques, such as quantitative PCR, are highly sensitive but have limited efficacy due to their complexity, high cost, and technical requirements. LFAs are valuable due to their simplicity, affordability, and portability, making them ideal for point-of-care testing in low-resource environments. However, challenges remain in developing highly sensitive and accurate LFA devices for miRNA detection. This review explores recent advancements in LFAs to improve miRNA detection sensitivity and specificity. Key innovations include signal amplification using isothermal methods, the application of CRISPR (Clustered Regularly Interspaced Short Palindromic Repeats)/Cas systems for direct targeting of miRNAs, and the incorporation of nanomaterials, such as gold nanoparticles and nanorods, to enhance signal intensity. Using artificial intelligence (AI) algorithms enables precise, automated, and rapid quantification of miRNAs. Moreover, this review examines the ability of LFA-based devices to detect multiple miRNAs simultaneously. One of the most significant advancements is the detection of miR-21 levels as low as 20 pM and let-7a levels as low as 40 pM within ten minutes. This highlights the potential of these devices for clinical diagnostics.

On-site SERS analysis and intelligent multi-identification of fentanyl class substances by deep machine learning

As the types of fentanyl class substances continue to grow, a universal SERS sensor is essential for the application of discriminant detection of fentanyl substances. A new nanomaterial SERS sensor-Ag@Au NPs-paper was developed. The SERS sensitivity and stability of Ag@Au NPs-paper were investigated by using R6G molecule, and the results showed that Ag@Au NPs-paper has excellent performance. In combination with visual analysis and machine learning methods, Ag@Au NPs-paper has been successfully applied to the analysis of fentanyl class substances and the component identification of binary fentanyl mixtures, and thus it can be effectively used in food safety, environmental toxicants and other fields.

Solid-phase extraction coupled to automated centrifugal microfluidics SERS: Improving quantification of therapeutic drugs in human serum

Surface-enhanced Raman spectroscopy (SERS) is a powerful method in analytical chemistry, but its application in real-life medical settings has been limited due to technical challenges. In this work, we introduce an innovative approach that is meant to advance the automation of microfluidics SERS to improve reproducibility and label-free quantification of two widely used therapeutic drugs, methotrexate (MTX) and lamotrigine (LTG), in human serum. Our methodology involves a miniaturized solid-phase extraction (μ-SPE) method coupled to a centrifugal microfluidics disc with incorporated SERS substrates (CD-SERS). The CD-SERS platform enables simultaneous controlled sample wetting and accurate SERS mapping. Together with the assay we implemented a machine learning method based on Partial Least Squares Regression (PLSR) for robust data analysis and drug quantification. The results indicate that combining μ-SPE with CD-SERS (μ-SPE to CD-SERS) led to a substantial improvement in the signal-to-noise ratio compared to combining CD-SERS with ultrafiltration or protein precipitation. The PLSR model enabled us to obtain the limit of detection and quantification for MTX as 2.90 and 8.92 μM, respectively, and for LTG as 10.76 and 32.29 μM. We also validated our μ-SPE to CD-SERS method for MTX against HPLC and immunoassay (p-value <0.05), using patient samples undergoing MTX therapy. In addition, we achieved a satisfactory recovery rate (80%) for LTG when quantifying it in patient samples. Our results show the potential of this newly developed approach as a strategy for therapeutic drugs in point-of-care clinical settings and highlight the benefits of automating label-free SERS assays.

Machine Learning-Assisted Surface-Enhanced Raman Spectroscopy Detection for Environmental Applications: A Review

Surface-enhanced Raman spectroscopy (SERS) has gained significant attention for its ability to detect environmental contaminants with high sensitivity and specificity. The cost-effectiveness and potential portability of the technique further enhance its appeal for widespread application. However, challenges such as the management of voluminous quantities of high-dimensional data, its capacity to detect low-concentration targets in the presence of environmental interferents, and the navigation of the complex relationships arising from overlapping spectral peaks have emerged. In response, there is a growing trend toward the use of machine learning (ML) approaches that encompass multivariate tools for effective SERS data analysis. This comprehensive review delves into the detailed steps needed to be considered when applying ML techniques for SERS analysis. Additionally, we explored a range of environmental applications where different ML tools were integrated with SERS for the detection of pathogens and (in)organic pollutants in environmental samples. We sought to comprehend the intricate considerations and benefits associated with ML in these contexts. Additionally, the review explores the future potential of synergizing SERS with ML for real-world applications.

Quantitative SERS sensor for mycotoxins with extraction and identification function

The development of new sensors for on-site food toxin monitoring that combine extraction, analytes distinction and detection is important in resource-limited environments. Surface-enhanced Raman scattering (SERS)-based signal readout features fast response and high sensitivity, making it a powerful method for detecting mycotoxins. In this work, a SERS-based assay for the detection of multiple mycotoxins is presented that combines extraction and subsequent detection, achieving an analytically relevant detection limit (∼ 1 ng/mL), which is also tested in corn samples. This sensor consists of a magnetic-core and mycotoxin-absorbing polydopamine-shell, with SERS-active Au nanoparticles on the outer surface. The assay can concentrate multiple mycotoxins, which are identified through multiclass partite least squares analysis based on their SERS spectra. We developed a strategy for the analysis of multiple mycotoxins with minimal sample pretreatment, enabling in situ analytical extraction and subsequent detection, displaying the potential to rapidly identify lethal mycotoxin contamination on site.

SERS analysis of single cells and subcellular components: A review

SERS is a rapidly advancing and non-destructive technique that has been proven to be more reliable and convenient than other traditional analytical methods. Due to its sensitivity and specificity, this technique is earning its place as a routine and powerful tool in biological and medical studies, especially for the analysis of living cells and subcellular components. This paper reviewed the research progress of single-cell SERS that has been made in the last few years and discussed challenges and future perspectives of this technique. The reviewed SERS platforms have been categorized according to their nature into the following types: (1) colloid-based, substrate-based, or hybrid; (2) ligand-based or ligand-free, and (3) label-based or label-free. The advantages and disadvantages of each type and their potential applications in various fields are thoroughly discussed.

Analytical Methods for Assessing Thiol Antioxidants in Biological Fluids: A Review

Redox metabolism is an integral part of the glutathione system, encompassing reduced and oxidized glutathione, hydrogen peroxide, and associated enzymes. This core process orchestrates a network of thiol antioxidants like thioredoxins and peroxiredoxins, alongside critical thiol-containing proteins such as mercaptoalbumin. Modifications to thiol-containing proteins, including oxidation and glutathionylation, regulate cellular signaling influencing gene activities in inflammation and carcinogenesis. Analyzing thiol antioxidants, especially glutathione, in biological fluids offers insights into pathological conditions. This review discusses the analytical methods for biothiol determination, mainly in blood plasma. The study includes all key methodological aspects of spectroscopy, chromatography, electrochemistry, and mass spectrometry, highlighting their principles, benefits, limitations, and recent advancements that were not included in previously published reviews. Sample preparation and factors affecting thiol antioxidant measurements are discussed. The review reveals that the choice of analytical procedures should be based on the specific requirements of the research. Spectrophotometric methods are simple and cost-effective but may need more specificity. Chromatographic techniques have excellent separation capabilities but require longer analysis times. Electrochemical methods enable real-time monitoring but have disadvantages such as interference. Mass spectrometry-based approaches have high sensitivity and selectivity but require sophisticated instrumentation. Combining multiple techniques can provide comprehensive information on thiol antioxidant levels in biological fluids, enabling clearer insights into their roles in health and disease. This review covers the time span from 2010 to mid-2024, and the data were obtained from the SciFinder® (ACS), Google Scholar (Google), PubMed®, and ScienceDirect (Scopus) databases through a combination search approach using keywords.

SERS biosensors for liquid biopsy towards cancer diagnosis by detection of various circulating biomarkers: current progress and perspectives

Liquid biopsy has emerged as a promising non-invasive strategy for cancer diagnosis, enabling the detection of various circulating biomarkers, including circulating tumor cells (CTCs), circulating tumor nucleic acids (ctNAs), circulating tumor-derived small extracellular vesicles (sEVs), and circulating proteins. Surface-enhanced Raman scattering (SERS) biosensors have revolutionized liquid biopsy by offering sensitive and specific detection methodologies for these biomarkers. This review comprehensively examines the application of SERS-based biosensors for identification and analysis of various circulating biomarkers including CTCs, ctNAs, sEVs and proteins in liquid biopsy for cancer diagnosis. The discussion encompasses a diverse range of SERS biosensor platforms, including label-free SERS assay, magnetic bead-based SERS assay, microfluidic device-based SERS system, and paper-based SERS assay, each demonstrating unique capabilities in enhancing the sensitivity and specificity for detection of liquid biopsy cancer biomarkers. This review critically assesses the strengths, limitations, and future directions of SERS biosensors in liquid biopsy for cancer diagnosis.

AI-Enhanced Visual-Spectral Synergy for Fast and Ultrasensitive Biodetection of Breast Cancer-Related miRNAs

In biomedical testing, artificial intelligence (AI)-enhanced analysis has gradually been applied to the diagnosis of certain diseases. This research employs AI algorithms to refine the precision of integrative detection, encompassing both visual results and fluorescence spectra from lateral flow assays (LFAs), which signal the presence of cancer-linked miRNAs. Specifically, the color shift of gold nanoparticles (GNPs) is paired with the red fluorescence from nitrogen vacancy color centers (NV-centers) in fluorescent nanodiamonds (FNDs) and is integrated into LFA strips. While GNPs amplify the fluorescence of FNDs, in turn, FNDs enhance the color intensity of GNPs. This reciprocal intensification of fluorescence and color can be synergistically augmented with AI algorithms, thereby improving the detection sensitivity for early diagnosis. Supported by the detection platform based on this strategy, the fastest detection results with a limit of detection (LOD) at the fM level and the R2 value of ∼0.9916 for miRNA can be obtained within 5 min. Meanwhile, by labeling the capture probes for miRNA-21 and miRNA-96 (both of which are early indicators of breast cancer) on separate T-lines, simultaneous detection of them can be achieved. The miRNA detection methods employed in this study may potentially be applied in the future for the early detection of breast cancer.

Key steps for improving bacterial SERS signals in complex samples: Separation, recognition, detection, and analysis

Rapid and reliable detection of pathogenic bacteria is absolutely essential for research in environmental science, food quality, and medical diagnostics. Surface-enhanced Raman spectroscopy (SERS), as an emerging spectroscopic technique, has the advantages of high sensitivity, good selectivity, rapid detection speed, and portable operation, which has been broadly used in the detection of pathogenic bacteria in different kinds of complex samples. However, the SERS detection method is also challenging in dealing with the detection difficulties of bacterial samples in complex matrices, such as interference from complex matrices, confusion of similar bacteria, and complexity of data processing. Therefore, researchers have developed some technologies to assist in SERS detection of bacteria, including both the front-end process of obtaining bacterial sample data and the back-end data processing process. The review summarizes the key steps for improving bacterial SERS signals in complex samples: separation, recognition, detection, and analysis, highlighting the principles of each step and the key roles for SERS pathogenic bacteria analysis, and the interconnectivity between each step. In addition, the current challenges in the practical application of SERS technology and the development trends are discussed. The purpose of this review is to deepen researchers' understanding of the various stages of using SERS technology to detect bacteria in complex sample matrices, and help them find new breakthroughs in different stages to facilitate the detection and control of bacteria in complex samples.

Machine Learning for COVID-19 Determination Using Surface-Enhanced Raman Spectroscopy

The rapid, low cost, and efficient detection of SARS-CoV-2 virus infection, especially in clinical samples, remains a major challenge. A promising solution to this problem is the combination of a spectroscopic technique: surface-enhanced Raman spectroscopy (SERS) with advanced chemometrics based on machine learning (ML) algorithms. In the present study, we conducted SERS investigations of saliva and nasopharyngeal swabs taken from a cohort of patients (saliva: 175; nasopharyngeal swabs: 114). Obtained SERS spectra were analyzed using a range of classifiers in which random forest (RF) achieved the best results, e.g., for saliva, the precision and recall equals 94.0% and 88.9%, respectively. The results demonstrate that even with a relatively small number of clinical samples, the combination of SERS and shallow machine learning can be used to identify SARS-CoV-2 virus in clinical practice.

Surface-Enhanced Raman Spectroscopy-Based Detection of Micro-RNA Biomarkers for Biomedical Diagnosis Using a Comparative Study of Interpretable Machine Learning Algorithms

Surface-enhanced Raman spectroscopy (SERS) has wide diagnostic applications due to narrow spectral features that allow multiplex analysis. We have previously developed a multiplexed, SERS-based nanosensor for micro-RNA (miRNA) detection called the inverse molecular sentinel (iMS). Machine learning (ML) algorithms have been increasingly adopted for spectral analysis due to their ability to discover underlying patterns and relationships within large and complex data sets. However, the high dimensionality of SERS data poses a challenge for traditional ML techniques, which can be prone to overfitting and poor generalization. Non-negative matrix factorization (NMF) reduces the dimensionality of SERS data while preserving information content. In this paper, we compared the performance of ML methods including convolutional neural network (CNN), support vector regression, and extreme gradient boosting combined with and without NMF for spectral unmixing of four-way multiplexed SERS spectra from iMS assays used for miRNA detection. CNN achieved high accuracy in spectral unmixing. Incorporating NMF before CNN drastically decreased memory and training demands without sacrificing model performance on SERS spectral unmixing. Additionally, models were interpreted using gradient class activation maps and partial dependency plots to understand predictions. These models were used to analyze clinical SERS data from single-plexed iMS in RNA extracted from 17 endoscopic tissue biopsies. CNN and CNN-NMF, trained on multiplexed data, performed most accurately with RMSElabel = 0.101 and 9.68 × 10-2, respectively. We demonstrated that CNN-based ML shows great promise in spectral unmixing of multiplexed SERS spectra, and the effect of dimensionality reduction on performance and training speed.

Paper-based substrates for surface-enhanced Raman spectroscopy sensing

Surface-enhanced Raman scattering (SERS) has been recognized as one of the most sensitive analytical methods by adsorbing the target of interest onto a plasmonic surface. Growing attention has been directed towards the fabrication of various substrates to broaden SERS applications. Among these, flexible SERS substrates, particularly paper-based ones, have gained popularity due to their easy-to-use features by full contact with the sample surface. Herein, we reviewed the latest advancements in flexible SERS substrates, with a focus on paper-based substrates. Firstly, it begins by introducing various methods for preparing paper-based substrates and highlights their advantages through several illustrative examples. Subsequently, we demonstrated the booming applications of these paper-based SERS substrates in abiotic and biological matrix detection, with particular emphasis on their potential application in clinical diagnosis. Finally, the prospects and challenges of paper-based SERS substrates in broader applications are discussed.

Handling DNA malfunctions by unsupervised machine learning model

The cell cycle is a rich field for research, especially, the DNA damage. DNA damage, which happened naturally or as a result of environmental influences causes change in the chemical structure of DNA. The extent of DNA damage has a significant impact on the fate of the cell in later stages. In this paper, we introduced an Unsupervised Machine learning Model for DNA Damage Diagnosis and Analysis. Mainly, we employed K-means clustering unsupervised machine learning algorithms. Unsupervised algorithms commonly draw conclusions from datasets by solely utilizing input vectors, disregarding any known or labeled outcomes. The model provided deep insight about DNA damage and exposes the protein levels for proteins when work together in sub-network model to deal with DNA damage occurrence, the unsupervised artificial model explained the sub-network biological model activities in regard to the changing in their concentrations in several clusters, they have been grouped in such as (0 - no damage, 1 - low, 2 - medium, 3 - high, and 4 - excess) DNA damage clusters. The results provided a rational and persuasive explanation for numerous important phenomena, including the oscillation of the protein p53, in a clear and understandable manner. Which is encouraging since it demonstrates that the K-means clustering approach can be easily applied to many similar biological systems, which aids in better understanding the key dynamics of these systems.

Bioinspired superhydrophobic SERS substrates for machine learning assisted miRNA detection in complex biomatrix below femtomolar limit

Surface-enhanced Raman spectroscopy (SERS) is an analytical method with high potential in the field of medicine. The design of SERS substrates, based on specific morphology and/or chemical modification, allow the recognition of the presence of specific analytes with precision close to a single-molecule detection limit. However, the SERS analysis of real samples is significantly complicated by the presence of a large number of "minor" molecules that can shield the signal from the target analyte and make it impossible to determine it in practice. In this work, an advanced SERS approach was used for the detection of cancer-related miRNA-21 in blood plasma, used as a molecular model background. The approach was based on the combination of the biomimetic plasmon-active SERS substrate, its tuned surface chemistry and advanced SERS data analysis, making use of artificial machine learning. In the first step, biomimetic SERS substrates were created using a butterfly wing as a starting template. The substrates were covered by thin Au layer and covalently grafted with hydrophobic chemical moieties to introduce superhydrophobic and water-adhesive properties. The self-concentration of the analyte on the substrates was achieved by minimizing the contact area between the analyte drop and the substrate, which is facilitated by surface superhydrophobicity and additionally enhanced by drop evaporation on the flipped over substrate. Due to the presence of cancer miRNA and blood plasma background, the measured SERS spectra represent a complex of interfering peaks. Thus, their interpretation was carried out using a specially trained machine learning model. As a result, reliable and repeatable quantitative detection of miRNAs below the femtomolar level (up to 10-16 M) on the background of human blood plasma becomes possible.

A Review on Photonic Sensing Technologies: Status and Outlook

In contemporary science and technology, photonic sensors are essential. They may be made to be extremely resistant to some physical parameters while also being extremely sensitive to other physical variables. Most photonic sensors may be incorporated on chips and operate with CMOS technology, making them suitable for use as extremely sensitive, compact, and affordable sensors. Photonic sensors can detect electromagnetic (EM) wave changes and convert them into an electric signal due to the photoelectric effect. Depending on the requirements, scientists have found ways to develop photonic sensors based on several interesting platforms. In this work, we extensively review the most generally utilized photonic sensors for detecting vital environmental parameters and personal health care. These sensing systems include optical waveguides, optical fibers, plasmonics, metasurfaces, and photonic crystals. Various aspects of light are used to investigate the transmission or reflection spectra of photonic sensors. In general, resonant cavity or grating-based sensor configurations that work on wavelength interrogation methods are preferred, so these sensor types are mostly presented. We believe that this paper will provide insight into the novel types of available photonic sensors.

Recent Trends in SERS-Based Plasmonic Sensors for Disease Diagnostics, Biomolecules Detection, and Machine Learning Techniques

Surface-enhanced Raman spectroscopy/scattering (SERS) has evolved into a popular tool for applications in biology and medicine owing to its ease-of-use, non-destructive, and label-free approach. Advances in plasmonics and instrumentation have enabled the realization of SERS's full potential for the trace detection of biomolecules, disease diagnostics, and monitoring. We provide a brief review on the recent developments in the SERS technique for biosensing applications, with a particular focus on machine learning techniques used for the same. Initially, the article discusses the need for plasmonic sensors in biology and the advantage of SERS over existing techniques. In the later sections, the applications are organized as SERS-based biosensing for disease diagnosis focusing on cancer identification and respiratory diseases, including the recent SARS-CoV-2 detection. We then discuss progress in sensing microorganisms, such as bacteria, with a particular focus on plasmonic sensors for detecting biohazardous materials in view of homeland security. At the end of the article, we focus on machine learning techniques for the (a) identification, (b) classification, and (c) quantification in SERS for biology applications. The review covers the work from 2010 onwards, and the language is simplified to suit the needs of the interdisciplinary audience.