Deep learning-based component identification for the Raman spectra of mixtures

Determination of Trace Organic Contaminant Concentration via Machine Classification of Surface-Enhanced Raman Spectra

Surface-enhanced Raman spectroscopy (SERS) has been well explored as a highly effective characterization technique that is capable of chemical pollutant detection and identification at very low concentrations. Machine learning has been previously used to identify compounds based on SERS spectral data. However, utilization of SERS to quantify concentrations, with or without machine learning, has been difficult due to the spectral intensity being sensitive to confounding factors such as the substrate parameters, orientation of the analyte, and sample preparation technique. Here, we demonstrate an approach for predicting the concentration of sample pollutants from SERS spectra using machine learning. Frequency domain transform methods, including the Fourier and Walsh-Hadamard transforms, are applied to spectral data sets of three analytes (rhodamine 6G, chlorpyrifos, and triclosan), which are then used to train machine learning algorithms. Using standard machine learning models, the concentration of the sample pollutants is predicted with >80% cross-validation accuracy from raw SERS data. A cross-validation accuracy of 85% was achieved using deep learning for a moderately sized data set (∼100 spectra), and 70-80% was achieved for small data sets (∼50 spectra). Performance can be maintained within this range even when combining various sample preparation techniques and environmental media interference. Additionally, as a spectral pretreatment, the Fourier and Hadamard transforms are shown to consistently improve prediction accuracy across multiple data sets. Finally, standard models were shown to accurately identify characteristic peaks of compounds via analysis of their importance scores, further verifying their predictive value.

Deep learning-based Raman spectroscopy qualitative analysis algorithm: A convolutional neural network and transformer approach

Raman spectroscopy is a general and non-destructive detection technique that can obtain detailed information of the chemical structure of materials. In the past, when using chemometric algorithms to analyze the Raman spectra of mixtures, the challenges of complex spectral overlap and noise often limited the accurate identification of components. The emergence of deep learning has introduced a novel approach to qualitative analysis of mixed Raman spectra. In this paper, we propose a deep learning-based Raman spectroscopy qualitative analysis algorithm (RST) by borrowing the ideas of convolutional neural network and Transformer. By transforming the Raman spectrum into 64 word vectors, the contribution weights of each word vector to the components are obtained. For the 75 spectral data used for validation, the positive identification rate can reach 100.00 %, the recall rate can reach 99.3 %, the average identification score can reach 9.51, and it is applicable to the fields of Raman and surface-enhanced Raman spectroscopy. Furthermore, compared with traditional CNN models, RST has excellent accuracy and robustness in identifying components in complex mixtures. The model's interpretability has been enhanced, aiding in a deeper understanding of spectroscopic learning patterns for future analysis of more complex mixtures.

A method for accurate identification of Uyghur medicinal components based on Raman spectroscopy and multi-label deep learning

Uyghur medicine is one of the four major ethnic medicines in China and is a component of traditional Chinese medicine. The intrinsic quality of Uyghur medicinal materials will directly affect the clinical efficacy of Uyghur medicinal preparations. However, in recent years, problems such as adulteration of Uyghur medicinal materials and foreign bodies with the same name still exist, so it is necessary to strengthen the quality control of Uyghur medicines to guarantee Uyghur medicinal efficacy. Identifying the components of Uyghur medicines can clarify the types of medicinal materials used, is a crucial step to realizing the quality control of Uyghur medicines, and is also an important step in screening the effective components of Uyghur medicines. Currently, the method of identifying the components of Uyghur medicines relies on manual detection, which has the problems of high toxicity of the unfolding agent, poor stability, high cost, low efficiency, etc. Therefore, this paper proposes a method based on Raman spectroscopy and multi-label deep learning model to construct a model Mix2Com for accurate identification of Uyghur medicine components. The experiments use computer-simulated mixtures as the dataset, introduce the Long Short-Term Memory Model (LSTM) and Attention mechanism to encode the Raman spectral data, use multiple parallel networks for decoding, and ultimately realize the macro parallel prediction of medicine components. The results show that the model is trained to achieve 90.76% accuracy, 99.41% precision, 95.42% recall value and 97.37% F1 score. Compared to the traditional XGBoost model, the method proposed in the experiment improves the accuracy by 49% and the recall value by 18%; compared with the DeepRaman model, the accuracy is improved by 9% and the recall value is improved by 14%. The method proposed in this paper provides a new solution for the accurate identification of Uyghur medicinal components. It helps to improve the quality standard of Uyghur medicinal materials, advance the research on screening of effective chemical components of Uyghur medicines and their action mechanisms, and then promote the modernization and development of Uyghur medicine.

Recent Trends of Bioanalytical Sensors with Smart Health Monitoring Systems: From Materials to Applications

Smart biosensors attract significant interest due to real-time monitoring of user health status, where bioanalytical electronic devices designed to detect various activities and biomarkers in the human body have potential applications in physical sign monitoring and health care. Bioelectronics can be well integrated by output signals with wireless communication modules for transferring data to portable devices used as smart biosensors in performing real-time diagnosis and analysis. In this review, the scientific keys of biosensing devices and the current trends in the field of smart biosensors, (functional materials, technological approaches, sensing mechanisms, main roles, potential applications and challenges in health monitoring) will be summarized. Recent advances in the design and manufacturing of bioanalytical sensors with smarter capabilities and enhanced reliability indicate a forthcoming expansion of these smart devices from laboratory to clinical analysis. Therefore, a general description of functional materials and technological approaches used in bioelectronics will be presented after the sections of scientific keys to bioanalytical sensors. A careful introduction to the established systems of smart monitoring and prediction analysis using bioelectronics, regarding the integration of machine-learning-based basic algorithms, will be discussed. Afterward, applications and challenges in development using these smart bioelectronics in biological, clinical, and medical diagnostics will also be analyzed. Finally, the review will conclude with outlooks of smart biosensing devices assisted by machine learning algorithms, wireless communications, or smartphone-based systems on current trends and challenges for future works in wearable health monitoring.

Quantitative analysis of the quality constituents of Lonicera japonica Thunberg based on Raman spectroscopy

Quantitative analysis of the quality constituents of Lonicera japonica (Jinyinhua [JYH]) using a feasible method provides important information on its evaluation and applications. Limitations of sample pretreatment, experimental site, and analysis time should be considered when identifying new methods. In response to these considerations, Raman spectroscopy combined with deep learning was used to establish a quantitative analysis model to determine the quality of JYH. Chlorogenic acid and total flavonoids were identified as analysis targets via network pharmacology. High performance liquid chromatograph and ultraviolet spectroscopy were used to construct standard curves for quantitative analysis. Raman spectra of JYH extracts (1200) were collected. Subsequently, models were built using partial least squares regression, Support Vector Machine, Back Propagation Neural Network, and One-dimensional Convolutional Neural Network (1D-CNN). Among these, the 1D-CNN model showed superior prediction capability and had higher accuracy (R2 = 0.971), and lower root mean square error, indicating its suitability for rapid quantitative analysis.

RamanFormer: A Transformer-Based Quantification Approach for Raman Mixture Components

Raman spectroscopy is a noninvasive technique to identify materials by their unique molecular vibrational fingerprints. However, distinguishing and quantifying components in mixtures present challenges due to overlapping spectra, especially when components share similar features. This study presents "RamanFormer", a transformer-based model designed to enhance the analysis of Raman spectroscopy data. By effectively managing sequential data and integrating self-attention mechanisms, RamanFormer identifies and quantifies components in chemical mixtures with high precision, achieving a mean absolute error of 1.4% and a root mean squared error of 1.6%, significantly outperforming traditional methods such as least squares, MLP, VGG11, and ResNet50. Tested extensively on binary and ternary mixtures under varying conditions, including noise levels with a signal-to-noise ratio of up to 10 dB, RamanFormer proves to be a robust tool, improving the reliability of material identification and broadening the application of Raman spectroscopy in fields, such as material science, forensics, and biomedical diagnostics.

Discrimination of Genetic Biomarkers of Disease through Machine-Learning-Based Hypothesis Testing of Direct SERS Spectra of DNA and RNA

Cancer is globally a leading cause of death that would benefit from diagnostic approaches detecting it in its early stages. However, despite much research and investment, cancer early diagnosis is still underdeveloped. Owing to its high sensitivity, surface-enhanced Raman spectroscopy (SERS)-based detection of biomarkers has attracted growing interest in this area. Oligonucleotides are an important type of genetic biomarkers as their alterations can be linked to the disease prior to symptom onset. We propose a machine-learning (ML)-enabled framework to analyze complex direct SERS spectra of short, single-stranded DNA and RNA targets to identify relevant mutations occurring in genetic biomarkers, which are key disease indicators. First, by employing ad hoc-synthesized colloidal silver nanoparticles as SERS substrates, we analyze single-base mutations in ssDNA and RNA sequences using a direct SERS-sensing approach. Then, an ML-based hypothesis test is proposed to identify these changes and differentiate the mutated sequences from the corresponding native ones. Rooted in "functional data analysis," this ML approach fully leverages the rich information and dependencies within SERS spectral data for improved modeling and detection capability. Tested on a large set of DNA and RNA SERS data, including from miR-21 (a known cancer miRNA biomarker), our approach is shown to accurately differentiate SERS spectra obtained from different oligonucleotides, outperforming various data-driven methods across several performance metrics, including accuracy, sensitivity, specificity, and F1-scores. Hence, this work represents a step forward in the development of the combined use of SERS and ML as effective methods for disease diagnosis with real applicability in the clinic.

Surface-functionalized SERS platform for deep learning-assisted diagnosis of Alzheimer's disease

Early diagnosis of Alzheimer's disease is crucial to stall the deterioration of brain function, but conventional diagnostic methods require complicated analytical procedures or inflict acute pain on the patient. Then, label-free Surface-enhanced Raman spectroscopy (SERS) analysis of blood-based biomarkers is a convenient alternative to rapidly obtain spectral information from biofluids. However, despite the rapid acquisition of spectral information from biofluids, it is challenging to distinguish spectral features of biomarkers due to interference from biofluidic components. Here, we introduce a deep learning-assisted, SERS-based platform for separate analysis of blood-based amyloid β (1-42) and metabolites, enabling the diagnosis of Alzheimer's disease. SERS substrates consisting of Au nanowire arrays are fabricated and functionalized in two characteristic ways to compare the validity of different Alzheimer's disease biomarkers measured on our SERS system. The 6E10 antibody is immobilized for the capture of amyloid β (1-42) and analysis of its oligomerization process, while various self-assembled monolayers are attached for different dipole interactions with blood-based metabolites. Ultimately, SERS spectra of blood plasma of Alzheimer's disease patients and human controls are measured on the substrates and classified via advanced deep learning techniques that automatically extract informative features to learn generalizable representations. Accuracies up to 99.5% are achieved for metabolite-based analyses, which are verified with an explainable artificial intelligence technique that identifies key spectral features used for classification and for deducing significant biomarkers.

Reconstructing Randomly Masked Spectra Helps DNNs Identify Discriminant Wavenumbers

Nondestructive detection methods, based on vibrational spectroscopy, are vitally important in a wide range of applications including industrial chemistry, pharmacy and national defense. Recently, deep learning has been introduced into vibrational spectroscopy showing great potential. Different from images, text, etc. that offer large labeled data sets, vibrational spectroscopic data is very limited, which requires novel concepts beyond transfer and meta learning. To tackle this, we propose a task-enhanced augmentation network (TeaNet). The key component of TeaNet is a reconstruction module that inputs randomly masked spectra and outputs reconstructed samples that are similar to the original ones, but include additional variations learned from the domain. These augmented samples are used to train the classification model. The reconstruction and prediction parts are trained simultaneously, end-to-end with back-propagation. Results on both synthetic and real-world datasets verified the superiority of the proposed method. In the most difficult synthetic scenarios TeaNet outperformed CNN by 17%. We visualized and analysed the neuron responses of TeaNet and CNN, and found that TeaNet's ability to identify discriminant wavenumbers was excellent compared to CNN. Our approach is general and can be easily adapted to other domains, offering a solution to more accurate and interpretable few-shot learning.

Applications of Data Characteristic AI-Assisted Raman Spectroscopy in Pathological Classification

Raman spectroscopy has been widely used for label-free biomolecular analysis of cells and tissues for pathological diagnosis in vitro and in vivo. AI technology facilitates disease diagnosis based on Raman spectroscopy, including machine learning (PCA and SVM), manifold learning (UMAP), and deep learning (ResNet and AlexNet). However, it is not clear how to optimize the appropriate AI classification model for different types of Raman spectral data. Here, we selected five representative Raman spectral data sets, including endometrial carcinoma, hepatoma extracellular vesicles, bacteria, melanoma cell, diabetic skin, with different characteristics regarding sample size, spectral data size, Raman shift range, tissue sites, Kullback-Leibler (KL) divergence, and significant Raman shifts (i.e., wavenumbers with significant differences between groups), to explore the performance of different AI models (e.g., PCA-SVM, SVM, UMAP-SVM, ResNet or AlexNet). For data set of large spectral data size, Resnet performed better than PCA-SVM and UMAP. By building data characteristic-assisted AI classification model, we optimized the network parameters (e.g., principal components, activation function, and loss function) of AI model based on data size and KL divergence etc. The accuracy improved from 85.1 to 94.6% for endometrial carcinoma grading, from 77.1 to 90.7% for hepatoma extracellular vesicles detection, from 89.3 to 99.7% for melanoma cell detection, from 88.1 to 97.9% for bacterial identification, from 53.7 to 85.5% for diabetic skin screening, and mean time expense of 5 s.

GCMSFormer: A Fully Automatic Method for the Resolution of Overlapping Peaks in Gas Chromatography-Mass Spectrometry

Gas chromatography-mass spectrometry (GC-MS) is one of the most important instruments for analyzing volatile organic compounds. However, the complexity of real samples and the limitations of chromatographic separation capabilities lead to coeluting compounds without ideal separation. In this study, a Transformer-based automatic resolution method (GCMSFormer) is proposed to resolve mass spectra from GC-MS peaks in an end-to-end manner, predicting the mass spectra of components directly from the raw overlapping peaks data. Furthermore, orthogonal projection resolution (OPR) was integrated into GCMSFormer to resolve minor components. The GCMSFormer model was trained, validated, and tested using 100,000 augmented data. It achieves 99.88% of the bilingual evaluation understudy (BLEU) value on the test set, significantly higher than the 97.68% BLEU value of the baseline sequence-to-sequence model long short-term memory (LSTM). GCMSFormer was also compared with two nondeep learning resolution tools (MZmine and AMDIS) and two deep learning resolution tools (PARAFAC2 with DL and MSHub/GNPS) on a real plant essential oil GC-MS data set. Their resolution results were compared on evaluation metrics, including the number of compounds resolved, mass spectral match score, correlation coefficient, explained variance, and resolution speed. The results demonstrate that GCMSFormer has better resolution performance, higher automation, and faster resolution speed. In summary, GCMSFormer is an end-to-end, fast, fully automatic, and accurate method for analyzing GC-MS data of complex samples.

A Comparative Analysis of Data Synthesis Techniques to Improve Classification Accuracy of Raman Spectroscopy Data

Raman spectra are examples of high dimensional data that can often be limited in the number of samples. This is a primary concern when Deep Learning frameworks are developed for tasks such as chemical species identification, quantification, and diagnostics. Open-source data are difficult to obtain and often sparse; furthermore, the collecting and curating of new spectra require expertise and resources. Deep generative modeling utilizes Deep Learning architectures to approximate high dimensional distributions and aims to generate realistic synthetic data. The evaluation of the data and the performance of the deep models is usually conducted on a per-task basis and provides no indication of an increase to robustness, or generalization, on a wider scale. In this study, we compare the benefits and limitations of a standard statistical approach to data synthesis (weighted blending) with a popular deep generative model, the Variational Autoencoder. Two binary data sets are divided into 3-fold to simulate small, limited samples. Synthetic data distributions are created per fold using the two methods and then augmented into the training of two Deep Learning algorithms, a Convolutional Neural Network and a Fully-Connected Neural Network. The goal of this study is to observe the trends in learning as synthetic data are continually augmented to the training data in increasing batches. To determine the impact of each synthetic method, Principal Component Analysis and the discrete Fréchet distance are implemented to visualize and measure the distance between the source and synthetic distributions along with the Machine Learning metric balanced accuracy for evaluating performance on imbalanced data.

The application of laser‑induced fluorescence in oil spill detection

Over the past two decades, oil spills have been one of the most serious ecological disasters, causing massive damage to the aquatic and terrestrial ecosystems as well as the socio-economy. In view of this situation, several methods have been developed and utilized to analyze oil samples. Among these methods, laser-induced fluorescence (LIF) technology has been widely used in oil spill detection due to its classification method, which is based on the fluorescence characteristics of chemical material in oil. This review systematically summarized the LIF technology from the perspective of excitation wavelength selection and the application of traditional and novel machine learning algorithms to fluorescence spectrum processing, both of which are critical for qualitative and quantitative analysis of oil spills. It can be seen that an appropriate excitation wavelength is indispensable for spectral discrimination due to different kinds of polycyclic aromatic hydrocarbons' (PAHs) compounds in petroleum products. By summarizing some articles related to LIF technology, we discuss the influence of the excitation wavelength on the accuracy of the oil spill detection model and proposed several suggestions on the selection of excitation wavelength. In addition, we introduced some traditional and novel machine learning (ML) algorithms and discussed the strengths and weaknesses of these algorithms and their applicable scenarios. With an appropriate excitation wavelength and data processing algorithm, it is believed that laser-induced fluorescence technology will become an efficient technique for real-time detection and analysis of oil spills.

Learning algorithms for identification of whisky using portable Raman spectroscopy

Reliable identification of high-value products such as whisky is vital due to rising issues of brand substitution and quality control in the industry. We have developed a novel framework that can perform whisky analysis directly from raw spectral data with no human intervention by integrating machine learning models with a portable Raman device. We demonstrate that machine learning models can achieve over 99% accuracy in brand or product identification across twenty-eight commercial samples. To demonstrate the flexibility of this approach, we utilized the same algorithms to quantify ethanol concentrations, as well as measuring methanol levels in spiked whisky samples. To demonstrate the potential use of these algorithms in a real-world environment we tested our algorithms on spectral measurements performed through the original whisky bottle. Through the bottle measurements are facilitated by a beam geometry hitherto not applied to whisky brand identification in conjunction with machine learning. Removing the need for decanting greatly enhances the practicality and commercial potential of this technique, enabling its use in detecting counterfeit or adulterated spirits and other high-value liquids. The techniques established in this paper aim to function as a rapid and non-destructive initial screening mechanism for detecting falsified and tampered spirits, complementing more comprehensive and stringent analytical methods.

Identification of extracellular vesicles from their Raman spectra via self-supervised learning

Extracellular vesicles (EVs) released from cells attract interest for their possible role in health and diseases. The detection and characterization of EVs is challenging due to the lack of specialized methodologies. Raman spectroscopy, however, has been suggested as a novel approach for biochemical analysis of EVs. To extract information from the spectra, a novel deep learning architecture is explored as a versatile variant of autoencoders. The proposed architecture considers the frequency range separately from the intensity of the spectra. This enables the model to adapt to the frequency range, rather than requiring that all spectra be pre-processed to the same frequency range as it was trained on. It is demonstrated that the proposed architecture accepts Raman spectra of EVs and lipoproteins from 13 biological sources and from two laboratories. High reconstruction accuracy is maintained despite large variances in frequency range and noise level. It is also shown that the architecture is able to cluster the biological nanoparticles by their Raman spectra and differentiate them by their origin without pre-processing of the spectra or supervision during learning. The model performs label-free differentiation, including separating EVs from activated vs. non-activated blood platelets and EVs/lipoproteins from prostate cancer patients versus non-cancer controls. The differentiation is evaluated by creating a neural network classifier that observes the features extracted by the model to classify the spectra according to their sample origin. The classification reveals a test sensitivity of 92.2 % and selectivity of 92.3 % over 769 measurements from two labs that have different measurement configurations.

An integrated computational pipeline for machine learning-driven diagnosis based on Raman spectra of saliva samples

Raman Spectroscopy promises the ability to encode in spectral data the significant differences between biological samples belonging to patients affected by a disease and samples of healthy patients (controls). However, the decoding and interpretation of the Raman spectral fingerprint is still a difficult and time-consuming procedure even for domain experts. In this work, we test an end-to-end deep-learning diagnostic pipeline able to classify spectral data from saliva samples. The pipeline has been validated against the SARS-COV-2 Infection and for the screening of neurodegenerative diseases such as Parkinson's and Alzheimer's diseases. The proposed system can be used for the fast prototyping of promising non-invasive, cost and time-efficient diagnostic screening tests.

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.

Spectroscopy-Guided Deep Learning Predicts Solid-Liquid Surface Adsorbate Properties in Unseen Solvents

Accurately and rapidly acquiring the microscopic properties of a material is crucial for catalysis and electrochemistry. Characterization tools, such as spectroscopy, can be a valuable tool to infer these properties, and when combined with machine learning tools, they can theoretically achieve fast and accurate prediction results. However, on the path to practical applications, training a reliable machine learning model is faced with the challenge of uneven data distribution in a vast array of non-negligible solvent types. Herein, we employ a combination of the first-principles-based approach and data-driven model. Specifically, we utilize density functional theory (DFT) to calculate theoretical spectral data of CO-Ag adsorption in 23 different solvent systems as a data source. Subsequently, we propose a hierarchical knowledge extraction multiexpert neural network (HMNN) to bridge the knowledge gaps among different solvent systems. HMNN undergoes two training tiers: in tier I, it learns fundamental quantitative spectra-property relationships (QSPRs), and in tier II, it inherits the fundamental QSPR knowledge from previous steps through a dynamic integration of expert modules and subsequently captures the solvent differences. The results demonstrate HMNN's superiority in estimating a range of molecular adsorbate properties, with an error range of less than 0.008 eV for zero-shot predictions on unseen solvents. The findings underscore the usability, reliability, and convenience of HMNN and could pave the way for real-time access to microscopic properties by exploiting QSPR.

Machine learning-assisted structure annotation of natural products based on MS and NMR data

Covering: up to March 2023Machine learning (ML) has emerged as a popular tool for analyzing the structures of natural products (NPs). This review presents a summary of the recent advancements in ML-assisted mass spectrometry (MS) and nuclear magnetic resonance (NMR) data analysis to establish the chemical structures of NPs. First, ML-based MS/MS analyses that rely on library matching are discussed, which involves the utilization of ML algorithms to calculate similarity, predict the MS/MS fragments, and form molecular fingerprint. Then, ML assisted MS/MS structural annotation without library matching is reviewed. Furthermore, the cases of ML algorithms in assisting structural studies of NPs based on NMR are discussed from four perspectives: NMR prediction, functional group identification, structural categorization and quantum chemical calculation. Finally, the review concludes with a discussion of the challenges and the trends associated with the structural establishment of NPs based on ML algorithms.

Deep-Learning-Based Mixture Identification for Nuclear Magnetic Resonance Spectroscopy Applied to Plant Flavors

Nuclear magnetic resonance (NMR) is a crucial technique for analyzing mixtures consisting of small molecules, providing non-destructive, fast, reproducible, and unbiased benefits. However, it is challenging to perform mixture identification because of the offset of chemical shifts and peak overlaps that often exist in mixtures such as plant flavors. Here, we propose a deep-learning-based mixture identification method (DeepMID) that can be used to identify plant flavors (mixtures) in a formulated flavor (mixture consisting of several plant flavors) without the need to know the specific components in the plant flavors. A pseudo-Siamese convolutional neural network (pSCNN) and a spatial pyramid pooling (SPP) layer were used to solve the problems due to their high accuracy and robustness. The DeepMID model is trained, validated, and tested on an augmented data set containing 50,000 pairs of formulated and plant flavors. We demonstrate that DeepMID can achieve excellent prediction results in the augmented test set: ACC = 99.58%, TPR = 99.48%, FPR = 0.32%; and two experimentally obtained data sets: one shows ACC = 97.60%, TPR = 92.81%, FPR = 0.78% and the other shows ACC = 92.31%, TPR = 80.00%, FPR = 0.00%. In conclusion, DeepMID is a reliable method for identifying plant flavors in formulated flavors based on NMR spectroscopy, which can assist researchers in accelerating the design of flavor formulations.

Advances in the Application of Artificial Intelligence-Based Spectral Data Interpretation: A Perspective

The interpretation of spectral data, including mass, nuclear magnetic resonance, infrared, and ultraviolet-visible spectra, is critical for obtaining molecular structural information. The development of advanced sensing technology has multiplied the amount of available spectral data. Chemical experts must use basic principles corresponding to the spectral information generated by molecular fragments and functional groups. This is a time-consuming process that requires a solid professional knowledge base. In recent years, the rapid development of computer science and its applications in cheminformatics and the emergence of computer-aided expert systems have greatly reduced the difficulty in analyzing large quantities of data. For expert systems, however, the problem-solving strategy must be known in advance or extracted by human experts and translated into algorithms. Gratifyingly, the development of artificial intelligence (AI) methods has shown great promise for solving such problems. Traditional algorithms, including the latest neural network algorithms, have shown great potential for both extracting useful information and processing massive quantities of data. This Perspective highlights recent innovations covering all of the emerging AI-based spectral interpretation techniques. In addition, the main limitations and current obstacles are presented, and the corresponding directions for further research are proposed. Moreover, this Perspective gives the authors' personal outlook on the development and future applications of spectral interpretation.

Dense Convolutional Neural Network for Identification of Raman Spectra

The rapid development of cloud computing and deep learning makes the intelligent modes of applications widespread in various fields. The identification of Raman spectra can be realized in the cloud, due to its powerful computing, abundant spectral databases and advanced algorithms. Thus, it can reduce the dependence on the performance of the terminal instruments. However, the complexity of the detection environment can cause great interferences, which might significantly decrease the identification accuracies of algorithms. In this paper, a deep learning algorithm based on the Dense network has been proposed to satisfy the realization of this vision. The proposed Dense convolutional neural network has a very deep structure of over 40 layers and plenty of parameters to adjust the weight of different wavebands. In the kernel Dense blocks part of the network, it has a feed-forward fashion of connection for each layer to every other layer. It can alleviate the gradient vanishing or explosion problems, strengthen feature propagations, encourage feature reuses and enhance training efficiency. The network's special architecture mitigates noise interferences and ensures precise identification. The Dense network shows more accuracy and robustness compared to other CNN-based algorithms. We set up a database of 1600 Raman spectra consisting of 32 different types of liquid chemicals. They are detected using different postures as examples of interfered Raman spectra. In the 50 repeated training and testing sets, the Dense network can achieve a weighted accuracy of 99.99%. We have also tested the RRUFF database and the Dense network has a good performance. The proposed approach advances cloud-enabled Raman spectra identification, offering improved accuracy and adaptability for diverse identification tasks.

Simultaneous quantitative analysis of Escherichia coli, Staphylococcus aureus and Salmonella typhimurium using surface-enhanced Raman spectroscopy coupled with partial least squares regression and artificial neural networks

Simultaneous detection of mixed bacteria accurately and sensitively is a major challenge in microbial quality control field. In this study, we proposed a label-free SERS technique coupled with partial least squares regression (PLSR) and artificial neural networks (ANNs) for quantitative analysis of Escherichia coli, Staphylococcus aureus and Salmonella typhimurium simultaneously. SERS-active and reproducible Raman spectra can be acquired directly upon the bacteria and Au@Ag@SiO₂ nanoparticle composites on the surface of gold foil substrates. After applying different preprocessing models, SERS-PLSR and SERS-ANNs quantitative analysis models were developed to map SERS spectra of concentrations of the Escherichia coli, Staphylococcus aureus and Salmonella typhimurium, respectively. Both models achieved high prediction accuracy and low prediction error, while the performance of SERS-ANNs model in both quality of fit (R² > 0.95) and accuracy of predictions (RMSE < 0.06) was superior to SERS-PLSR model. Therefore, it is feasible to develop simultaneous quantitative analysis of mixed pathogenic bacteria by proposed SERS methodology.

Fundamentals and Applications of Raman-Based Techniques for the Design and Development of Active Biomedical Materials

Raman spectroscopy is an analytical method based on light-matter interactions that can interrogate the vibrational modes of matter and provide representative molecular fingerprints. Mediated by its label-free, non-invasive nature, and high molecular specificity, Raman-based techniques have become ubiquitous tools for in situ characterization of materials. This review comprehensively describes the theoretical and practical background of Raman spectroscopy and its advanced variants. The numerous facets of material characterization that Raman scattering can reveal, including biomolecular identification, solid-to-solid phase transitions, and spatial mapping of biomolecular species in bioactive materials, are highlighted. The review illustrates the potential of these techniques in the context of active biomedical material design and development by highlighting representative studies from the literature. These studies cover the use of Raman spectroscopy for the characterization of both natural and synthetic biomaterials, including engineered tissue constructs, biopolymer systems, ceramics, and nanoparticle formulations, among others. To increase the accessibility and adoption of these techniques, the present review also provides the reader with practical recommendations on the integration of Raman techniques into the experimental laboratory toolbox. Finally, perspectives on how recent developments in plasmon- and coherently-enhanced Raman spectroscopy can propel Raman from underutilized to critical for biomaterial development are provided.

A Universal and Accurate Method for Easily Identifying Components in Raman Spectroscopy Based on Deep Learning

Raman spectroscopy has been widely used to provide the structural fingerprint for molecular identification. Due to interference from coexisting components, noise, baseline, and systematic differences between spectrometers, component identification with Raman spectra is challenging, especially for mixtures. In this study, a method entitled DeepRaman has been proposed to solve those problems by combining the comparison ability of a pseudo-Siamese neural network (pSNN) and the input-shape flexibility of spatial pyramid pooling (SPP). DeepRaman was trained, validated, and tested with 41,564 augmented Raman spectra from two databases (pharmaceutical material and S.T. Japan). It can achieve 96.29% accuracy, 98.40% true positive rate (TPR), and 94.36% true negative rate (TNR) on the test set. Another six data sets measured on different instruments were used to evaluate the performance of the proposed method from different aspects. DeepRaman can provide accurate identification results and significantly outperform the hit quality index (HQI) method and other deep learning models. In addition, it performs well in cases of different spectral complexity and low-content components. Once the model is established, it can be used directly on different data sets without retraining or transfer learning. Furthermore, it also obtains promising results for the analysis of surface-enhanced Raman spectroscopy (SERS) data sets and Raman imaging data sets. In summary, it is an accurate, universal, and ready-to-use method for component identification in various application scenarios.

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.

Deep learning-based method for automatic resolution of gas chromatography-mass spectrometry data from complex samples

Modern gas chromatography-mass spectrometry (GC-MS) is the workhorse for the high-throughput profiling of volatile compounds in complex samples. It can produce a considerable amount of two-dimensional data, and automatic methods are required to distill chemical information from raw GC-MS data efficiently. In this study, we proposed an Automatic Resolution method (AutoRes) based on pseudo-Siamese convolutional neural networks (pSCNN) to extract the meaningful features swamped by the noises, baseline drifts, retention time shifts, and overlapped peaks. Two pSCNN models were trained with 400,000 augmented spectral pairs, respectively. They can predict the selective region (pSCNN1) and elution region (pSCNN2) of compounds in an untargeted manner. The accuracies of the pSCNN1 model and the pSCNN2 model on their test sets are 99.9% and 92.6%, respectively. Then, the chromatographic profile of each component was automatically resolved by full rank resolution (FRR) based on the predicted regions by these models. The performance of AutoRes was evaluated on the simulated and plant essential oil datasets. Compared to AMDIS and MZmine, AutoRes resolves more reasonable mass spectra, chromatograms, and peak areas to identify and quantify compounds. The average match scores of AutoRes (925 and 936) outperformed AMDIS (909 and 925) and MZmine (888 and 916) when resolving mass spectra from overlapped peaks on the Set Ⅰ and Set Ⅱ of plant essential oil dataset and matching them against the NIST17 library. It extracted peak areas and mass spectra automatically from 10 GC-MS files of plant essential oils, and the entire process was completed in 8 min without any prior information or manual intervention. It is implemented in Python and is available as an open-source package at https://github.com/dyjfan/AutoRes.

PANOMICS at the interface of root-soil microbiome and BNI

Nitrification and denitrification are soil biological processes responsible for large nitrogen losses from agricultural soils and generation of the greenhouse gas (GHG) N₂O. Increased use of nitrogen fertilizer and the resulting decline in nitrogen use efficiency (NUE) are a major concern in agroecosystems. This nitrogen cycle in the rhizosphere is influenced by an intimate soil microbiome-root exudate interaction and biological nitrification inhibition (BNI). A PANOMICS approach can dissect these processes. We review breakthroughs in this area, including identification and characterization of root exudates by metabolomics and proteomics, which facilitate better understanding of belowground chemical communications and help identify new biological nitrification inhibitors (BNIs). We also address challenges for advancing the understanding of the role root exudates play in biotic and abiotic stresses.

Deep-learning framework for fully-automated recognition of TiO2 polymorphs based on Raman spectroscopy

Emerging machine learning techniques can be applied to Raman spectroscopy measurements for the identification of minerals. In this project, we describe a deep learning-based solution for automatic identification of complex polymorph structures from their Raman signatures. We propose a new framework using Convolutional Neural Networks and Long Short-Term Memory networks for compound identification. We train and evaluate our model using the publicly-available RRUFF spectral database. For model validation purposes, we synthesized and identified different TiO₂ polymorphs to evaluate the performance and accuracy of the proposed framework. TiO₂ is a ubiquitous material playing a crucial role in many industrial applications. Its unique properties are currently used advantageously in several research and industrial fields including energy storage, surface modifications, optical elements, electrical insulation to microelectronic devices such as logic gates and memristors. The results show that our model correctly identifies pure Anatase and Rutile with a high degree of confidence. Moreover, it can also identify defect-rich Anatase and modified Rutile based on their modified Raman Spectra. The model can also correctly identify the key component, Anatase, from the P25 Degussa TiO₂. Based on the initial results, we firmly believe that implementing this model for automatically detecting complex polymorph structures will significantly increase the throughput, while dramatically reducing costs.

Distributed Raman Spectrum Data Augmentation System Using Federated Learning with Deep Generative Models

Chemical agents are one of the major threats to soldiers in modern warfare, so it is so important to detect chemical agents rapidly and accurately on battlefields. Raman spectroscopy-based detectors are widely used but have many limitations. The Raman spectrum changes unpredictably due to various environmental factors, and it is hard for detectors to make appropriate judgments about new chemical substances without prior information. Thus, the existing detectors with inflexible techniques based on determined rules cannot deal with such problems flexibly and reactively. Artificial intelligence (AI)-based detection techniques can be good alternatives to the existing techniques for chemical agent detection. To build AI-based detection systems, sufficient amounts of data for training are required, but it is not easy to produce and handle fatal chemical agents, which causes difficulty in securing data in advance. To overcome the limitations, in this paper, we propose the distributed Raman spectrum data augmentation system that leverages federated learning (FL) with deep generative models, such as generative adversarial network (GAN) and autoencoder. Furthermore, the proposed system utilizes various additional techniques in combination to generate a large number of Raman spectrum data with reality along with diversity. We implemented the proposed system and conducted diverse experiments to evaluate the system. The evaluation results validated that the proposed system can train the models more quickly through cooperation among decentralized troops without exchanging raw data and generate realistic Raman spectrum data well. Moreover, we confirmed that the classification model on the proposed system performed learning much faster and outperformed the existing systems.

Single-model multi-tasks deep learning network for recognition and quantitation of surface-enhanced Raman spectroscopy

Surface-enhanced Raman scattering (SERS) spectroscopy analysis has long been the central task of nanoscience and nanotechnology to realize the ultrasensitive recognition/quantitation applications. Recently, the blooming of artificial intelligence algorithms provides an edge tool to revolutionize the spectroscopy analysis, especially for multiple substances analysis and large-scale data handling. In this study, a single-model multi-tasks deep learning network is proposed to simultaneously achieve the qualitative recognition and quantitative analysis of SERS spectroscopy. The SERS spectra of two kinds of hypoglycemic drugs (PHE, ROS) and the corresponding mixtures are collected, respectively, with the concentration grade from 10^-4 M to 10^-8 M. Based on the SERS spectroscopy dataset, the loss functions and hyperparameters of the multi-tasks classifications model are optimized, and the recognition accuracies are tested by simulation experiments. It is demonstrated that the accuracy rates of qualitative and quantitative analysis can reach up to 99.0% and 98.4%, respectively. Moreover, the practical feasibility of this multi-tasks model is demonstrated by using it to achieve qualitative and quantitative analysis of PHE and ROS in complex serum matrix. Overall, this single-model multi-tasks deep learning network shows significant potential for the recognition and quantitation of SERS spectroscopy, which provides the algorithmic and experimental basis for large-scale and multiple substances SERS spectra analysis.

Deep Learning for Raman Spectroscopy: A Review

Raman spectroscopy (RS) is a spectroscopic method which indirectly measures the vibrational states within samples. This information on vibrational states can be utilized as spectroscopic fingerprints of the sample, which, subsequently, can be used in a wide range of application scenarios to determine the chemical composition of the sample without altering it, or to predict a sample property, such as the disease state of patients. These two examples are only a small portion of the application scenarios, which range from biomedical diagnostics to material science questions. However, the Raman signal is weak and due to the label-free character of RS, the Raman data is untargeted. Therefore, the analysis of Raman spectra is challenging and machine learning based chemometric models are needed. As a subset of representation learning algorithms, deep learning (DL) has had great success in data science for the analysis of Raman spectra and photonic data in general. In this review, recent developments of DL algorithms for Raman spectroscopy and the current challenges in the application of these algorithms will be discussed.

Discriminating cell line specific features of antibiotic-resistant strains of Escherichia coli from Raman spectra via machine learning analysis

While Raman spectroscopy can provide label-free discrimination between highly similar biological species, the discrimination is often marginal, and optimal use of spectral information is imperative. Here, we compare two machine learning models, an artificial neural network and a support vector machine, for discriminating between Raman spectra of 11 bacterial mutants of Escherichia coli MDS42. While we find that both models discriminate the 11 bacterial strains with similarly high accuracy, sensitivity and specificity, it is clear that the models form different class boundaries. By extracting strain-specific (and function-specific) spectral features utilized by the models, we find that both models utilize a small subset of high intensity peaks while separate subsets of lower intensity peaks are utilized by only one method or the other. This analysis highlights the need for methods to use the complete spectral information more effectively, beginning with a better understanding of the distinct information gained from each model.

Deep Learning-Based Method for Compound Identification in NMR Spectra of Mixtures

Nuclear magnetic resonance (NMR) spectroscopy is highly unbiased and reproducible, which provides us a powerful tool to analyze mixtures consisting of small molecules. However, the compound identification in NMR spectra of mixtures is highly challenging because of chemical shift variations of the same compound in different mixtures and peak overlapping among molecules. Here, we present a pseudo-Siamese convolutional neural network method (pSCNN) to identify compounds in mixtures for NMR spectroscopy. A data augmentation method was implemented for the superposition of several NMR spectra sampled from a spectral database with random noises. The augmented dataset was split and used to train, validate and test the pSCNN model. Two experimental NMR datasets (flavor mixtures and additional flavor mixture) were acquired to benchmark its performance in real applications. The results show that the proposed method can achieve good performances in the augmented test set (ACC = 99.80%, TPR = 99.70% and FPR = 0.10%), the flavor mixtures dataset (ACC = 97.62%, TPR = 96.44% and FPR = 2.29%) and the additional flavor mixture dataset (ACC = 91.67%, TPR = 100.00% and FPR = 10.53%). We have demonstrated that the translational invariance of convolutional neural networks can solve the chemical shift variation problem in NMR spectra. In summary, pSCNN is an off-the-shelf method to identify compounds in mixtures for NMR spectroscopy because of its accuracy in compound identification and robustness to chemical shift variation.

Diagnosis of dengue virus infection using spectroscopic images and deep learning

Dengue virus (DENV) infection is one of the major health issues and a substantial epidemic infectious human disease. More than two billion humans are living in dengue susceptible regions with annual infection mortality rate is about 5%-20%. At initial stages, it is difficult to differentiate dengue virus symptoms with other similar diseases. The main objective of this research is to diagnose dengue virus infection in human blood sera for better treatment and rehabilitation process. A novel and robust approach is proposed based on Raman spectroscopy and deep learning. In this regard, the ResNet101 deep learning model is modified by exploiting transfer learning (TL) concept on Raman spectroscopic data of human blood sera. Sample size was selected using standard statistical tests. The proposed model is evaluated on 2,000 Raman spectra images in which 1,200 are DENV-infected of human blood sera samples, and 800 are healthy ones. It offers 96.0% accuracy on testing data for DENV infection diagnosis. Moreover, the developed approach demonstrated minimum improvement of 6.0% and 7.0% in terms of AUC and Kappa index respectively over the other state-of-the-art techniques. The developed model offers superior performance to capture minute Raman spectral variations due to the better residual learning capability and generalization ability compared to others deep learning models. The developed model revealed that it might be applied for diagnosis of DENV infection to save precious human lives.

Overfitting One-Dimensional convolutional neural networks for Raman spectra identification

Dedicated handheld spectrometers have been adopted by first responders and law enforcement agencies for in situ identification of unknown substances. Real-time spectral matching process is a pixel-by-pixel comparing of the unknown spectra with reference data. In fact, the success rate of this process using a miniaturized portable Raman spectrometer relies mainly on the variety of reference data carried on the memory. This is a hurdle in miniaturizing and affordability of the current handheld spectrometers due to limited memory and computational power. In this study, we aim to mitigate this issue by utilizing the power of one-dimensional Convolutional Neural Networks (1DCNN) trained on millions of Raman spectra augmented from standard available reference databases. Specifically, an intentionally overfitted 1DCNN model can be substituted with the reference database of handheld spectrometers to alleviate the memory size and increase the identification process speed and accuracy. Our experimental results revealed that 1DCNN could identify one pure unknown Raman instance from thousands of classes with a high accuracy.

Pushing the Limits of Surface-Enhanced Raman Spectroscopy (SERS) with Deep Learning: Identification of Multiple Species with Closely Related Molecular Structures

Raman spectroscopy is a non-destructive and label-free molecular identification technique capable of producing highly specific spectra with various bands correlated to molecular structure. Moreover, the enhanced detection sensitivity offered by surface-enhanced Raman spectroscopy (SERS) allows analyzing mixtures of related chemical species in a relatively short measurement time. Combining SERS with deep learning algorithms allows in some cases to increase detection and classification capabilities even further. The present study evaluates the potential of applying deep learning algorithms to SERS spectroscopy to differentiate and classify different species of bile acids, a large family of molecules with low Raman cross sections and molecular structures that often differ by a single hydroxyl group. Moreover, the study of these molecules is of interest for the medical community since they have distinct pathological roles and are currently viewed as potential markers of gut microbiome imbalances. A convolutional neural network model was developed and used to classify SERS spectra from five bile acid species. The model succeeded in identifying the five analytes despite very similar molecular structures and was found to be reliable even at low analyte concentrations.

Performance Improvement of Handheld Raman Spectrometer for Mixture Components Identification Using Fuzzy Membership and Sparse Non-Negative Least Squares

Due to the advantages of low price and convenience for end-users to conduct field-based, in-situ analysis, handheld Raman spectrometers are widely used in the identification of mixture components. However, the spectra collected by handheld Raman spectrometer usually have serious peak overlapping and spectral distortion, resulting in difficulties in component identification in the mixture. A novel method for mixture components identification based on the handheld Raman spectrometer was proposed in this study. The wavelet transform and Voight curve fitting method were used to extract the feature parameters from each Raman spectral peak, including Raman shift, maximum intensity, and full width at half-maximum (FWHM), and the similarities between the mixture and each substance in the database were calculated by fuzzy membership function based on extracted feature parameters. Then, the possible substances in the mixture were preliminarily screened out as candidates according to the similarity. Finally, the Raman spectra of these candidates were used to fit the spectra of the mixture, and the fitting coefficients obtained by sparse non-negative least squares algorithm were employed to further determine the suspected substance in the mixture. The Raman spectra of 190 liquid mixture samples and 158 powder mixture samples were collected using a handheld Raman spectrometer and these spectra were used to validate the identification performance of the proposed method. The proposed method could achieve good identification accuracy for different mixture samples. It shows that the proposed method is an effective way for the component identification in mixture by using a handheld Raman spectrometer.

Deep Learning for Type 1 Diabetes Mellitus Diagnosis Using Infrared Quantum Cascade Laser Spectroscopy

An estimated 10.5% of the world’s population aged 20–79 years are currently living with diabetes in 2021. An urgent task is to develop a non-invasive express-diagnostics of diabetes with high accuracy. Type 1 diabetes mellitus (T1DM) diagnostic method based on infrared laser spectroscopy of human exhaled breath is described. A quantum cascade laser emitting in a pulsed mode with a peak power of up to 150 mW in the spectral range of 5.3–12.8 μm and Herriot multipass gas cell with an optical path length of 76 m were used. We propose a method for collecting and drying an exhaled human air sample and have measured 1200 infrared exhaled breath spectra from 60 healthy volunteers (the control group) and 60 volunteers with confirmed T1DM (the target group). A 1-D convolutional neural network for the classification of healthy and T1DM volunteers with an accuracy of 99.7%, recall 99.6% and AUC score 99.9% was used. The demonstrated results require clarification on a larger dataset and series of clinical studies and, further, the method can be implemented in routine medical practice.

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.

Extreme Point Sort Transformation Combined With a Long Short-Term Memory Network Algorithm for the Raman-Based Identification of Therapeutic Monoclonal Antibodies

Therapeutic monoclonal antibodies (mAbs) are a new generation of protein-based medicines that are usually expensive and thus represent a target for counterfeiters. In the present study, a method based on Raman spectroscopy that combined extreme point sort transformation with a long short-term memory (LSTM) network algorithm was presented for the identification of therapeutic mAbs. A total of 15 therapeutic mAbs were used in this study. An in-house Raman spectrum dataset for model training was created with 1,350 spectra. The characteristic region of the Raman spectrum was reduced in dimension and then transformed through an extreme point sort transformation into a sequence array, which was fitted for the LSTM network. The characteristic array was extracted from the sequence array using a well-trained LSTM network and then compared with standard spectra for identification. To demonstrate whether the present algorithm was better, ThermoFisher OMNIC 8.3 software (Thermo Fisher Scientific Inc., U.S.) with two matching modes was selected for comparison. Finally, the present method was successfully applied to identify 30 samples, including 15 therapeutic mAbs and 15 other injections. The characteristic region was selected from 100 to 1800 cm⁻¹ of the full spectrum. The optimized dimensional values were set from 35 to 53, and the threshold value range was from 0.97 to 0.99 for 15 therapeutic mAbs. The results of the robustness test indicated that the present method had good robustness against spectral peak drift, random noise and fluorescence interference from the measurement. The areas under the curve (AUC) values of the present method that were analysed on the full spectrum and analysed on the characteristic region by the OMNIC 8.3 software’s built-in method were 1.000, 0.678, and 0.613, respectively. The similarity scores for 15 therapeutic mAbs using OMNIC 8.3 software in all groups compared with that of the relative present algorithm group had extremely remarkable differences (p < 0.001). The results suggested that the extreme point sort transformation combined with the LSTM network algorithm enabled the characteristic extraction of the therapeutic mAb Raman spectrum. The present method is a proposed solution to rapidly identify therapeutic mAbs.

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.

High-Speed Diagnosis of Bacterial Pathogens at the Single Cell Level by Raman Microspectroscopy with Machine Learning Filters and Denoising Autoencoders

Accurate and rapid identification of infectious bacteria is important in medicine. Raman microspectroscopy holds great promise in performing label-free identification at the single-cell level. However, due to the naturally weak Raman signal, it is a challenge to build extensive databases and achieve both accurate and fast identification. Here, we used signal-to-noise ratio (SNR) as a standard indicator for Raman data quality and performed bacterial identification using 11, 141 single-cell Raman spectra from nine bacterial strains. Subsequently, using two machine learning methods, a simple filter, and a neural network-based denoising autoencoder (DAE), we demonstrated 92% (simple filter using 1 s/cell spectra) and 84% (DAE using 0.1 s/cell spectra) identification accuracy. Our machine learning-aided Raman analysis paves the way for high-speed Raman microspectroscopic clinical diagnostics.

Multicomponent Raman spectral regression using complete and incomplete models and convolutional neural networks

A critical study of CNN networks for Raman regression problems is presented. In evaluating performance on models where spectral information is missing, CNN performs as well as state-of-the-art methods, without the need for spectral pre-processing.

Identifying the charge density and dielectric environment of graphene using Raman spectroscopy and deep learning

We built a CNN model to classify graphene Raman spectra. Compared to other deep learning models and machine learning algorithms studied in this work, the CNN model achieves a high accuracy of 99% and is less sensitive to the SNR of Raman spectra.

Deeply-recursive convolutional neural network for Raman spectra identification

Raman spectroscopy has been widely used in various fields due to its unique and superior properties. For achieving high spectral identification speeds and high accuracy, machine learning methods have found many applications in this area, with convolutional neural network-based methods showing great advantages. In this study, we propose a Raman spectral identification method using a deeply-recursive convolutional neural network (DRCNN). It has a very deep network structure (up to 16 layers) for improving performance without introducing more parameters for recursive layers, which eases the difficulty of training. We also propose a recursive-supervision extension to ease the difficulty of training. By testing several different open-source spectral databases, DRCNN has achieved higher prediction accuracies and better performance in transfer learning compared with other CNN-based methods. Superior identification performance is demonstrated, especially by identification, for characteristically similar and indistinguishable spectra.

Raman spectroscopy has been widely used in various fields due to its unique and superior properties.