Diagnosis of a model of Duchenne muscular dystrophy in blood serum of mdx mice using Raman hyperspectroscopy

Machine Learning for Prediction, Classification, and Identification of Immobilized Enzymes for Biocatalysis

BACKGROUND

Enzyme immobilization is a beneficial component involved in biocatalytic strategies. Understanding and evaluating the enzyme immobilization system plays an important role in the successful development and implementation of the biocatalysis route. Ensuring the implementation of a successful enzyme immobilization process is vital for realizing a highly functioning and well suited biocatalytic process within pharmaceutical development.

AIM

To develop a method which can accurately and objectively identify and classify differences within enzyme immobilization systems, sample preparation methods, and data collection parameters.

METHODS

Raman hyperspectral imaging was used to obtain a total of eight spectral data sets from enzyme immobilization samples. Partial least squares discriminant analysis (PLS-DA) was used to classify and identify the samples based on their differences.

RESULTS

Several two-class, four-class, and eight-class PLS-DA models were built to classify the different sample data sets. All models reached between 92-100% accuracy after cross-validation and external validation, illustrating great success of the models for identifying differences between the samples.

CONCLUSION

Raman hyperspectral imaging with machine learning can be used to investigate, interpret, and classify different data collection parameters, sample preparation methods, and enzyme immobilization supports, providing crucial insight into enzyme immobilization process development.

Label-free laser spectroscopy for respiratory virus detection: A review

Infectious diseases are among the most severe threats to modern society. Current methods of virus infection detection based on genome tests need reagents and specialized laboratories. The desired characteristics of new virus detection methods are noninvasiveness, simplicity of implementation, real-time, low cost and label-free detection. There are two groups of methods for molecular biomarkers' detection and analysis: (i) a sample physical separation into individual molecular components and their identification, and (ii) sample content analysis by laser spectroscopy. Variations in the spectral data are typically minor. It requires the use of sophisticated analytical methods like machine learning. This review examines the current technological level of laser spectroscopy and machine learning methods in applications for virus infection detection.

A Novel Method for Detecting Duchenne Muscular Dystrophy in Blood Serum of mdx Mice

Duchenne muscular dystrophy (DMD) is the most common form of muscular dystrophy, typically affecting males in infancy. The disease causes progressive weakness and atrophy of skeletal muscles, with approximately 20,000 new cases diagnosed yearly. Currently, methods for diagnosing DMD are invasive, laborious, and unable to make accurate early detections. While there is no cure for DMD, there are limited treatments available for managing symptoms. As such, there is a crucial unmet need to develop a simple and non-invasive method for accurately detecting DMD as early as possible. Raman spectroscopy with chemometric analysis is shown to have the potential to fill this diagnostic need.

Trabecular Bone Volume Is Reduced, With Deteriorated Microstructure, With Aging in a Rat Model of Duchenne Muscular Dystrophy

We aimed to clarify the effect of aging on trabecular bone volume and trabecular bone microstructure in a rat model of Duchenne muscular dystrophy (DMD). Six rats each of wild type (WT) and DMD model at 15 weeks of age, and 4 rats each at 30 weeks of age, were analyzed by dual energy X-ray absorptiometry and by micro-CT for analysis of trabecular and cortical bone of the femur. Bone mineral density was significantly lower in the DMD group than in the WT group at both 15 and 30 weeks of age. Micro-CT showed that trabecular bone volume and number were not significantly different between the two groups at 15 weeks, but at 30 weeks both were significantly lower in the DMD group than in the WT group. Connectivity density and structure model index were not significantly different between the two groups at 15 weeks, but at 30 weeks they differed significantly. No significant differences between the WT and DMD groups in cortical thickness and cortical area were evident at both 15 and 30 weeks. In conclusion, trabecular bone volume is significantly reduced, with deteriorated microstructure, with aging in a rat model of DMD.

Towards development of a novel screening method for identifying Alzheimer's disease risk: Raman spectroscopy of blood serum and machine learning

There is an urgent clinical need for a fast and effective method for diagnosing Alzheimer's disease (AD). The identification of AD in its most initial stages, at which point treatment could provide maximum therapeutic benefits, is not only likely to slow down disease progression but to also potentially provide a cure. However, current clinical detection is complicated and requires a combination of several methods based on significant clinical manifestations due to widespread neurodegeneration. As such, Raman spectroscopy with machine learning is investigated as a novel alternative method for detecting AD in its earliest stages. Here, blood serum obtained from rats fed either a standard diet or a high-fat diet was analyzed. The high-fat diet has been shown to initiate a pre-AD state. Partial least squares discriminant analysis combined with receiver operating characteristic curve analysis was able to separate the two rat groups with 100% accuracy at the donor level during external validation. Although further work is necessary, this research suggests there is a potential for Raman spectroscopy to be used in the future as a successful method for identifying AD early on in its progression, which is essential for effective treatment of the disease.

Raman spectroscopy and machine learning for biomedical applications: Alzheimer's disease diagnosis based on the analysis of cerebrospinal fluid

Current Alzheimer's disease (AD) diagnostics is based on clinical assessments, imaging and neuropsychological tests that are efficient only at advanced stages of the disease. Early diagnosis of AD will provide decisive opportunities for preventive treatment and development of disease-modifying drugs. Cerebrospinal fluid (CSF) is in direct contact with the human brain, where the deadly pathological process of the disease occurs. As such, the CSF biochemical composition reflects specific changes associated with the disease and is therefore the most promising body fluid for AD diagnostic test development. Here, we describe a new method to diagnose AD based on CSF via near infrared (NIR) Raman spectroscopy in combination with machine learning analysis. Raman spectroscopy is capable of probing the entire biochemical composition of a biological fluid at once. It has great potential to detect small changes specific to AD, even at the earliest stages of pathogenesis. NIR Raman spectra were measured of CSF samples acquired from 21 patients diagnosed with AD and 16 healthy control (HC) subjects. Artificial neural networks (ANN) and support vector machine discriminant analysis (SVM-DA) statistical methods were used for differentiation purposes, with the most successful results allowing for the differentiation of AD and HC subjects with 84% sensitivity and specificity. Our classification models show high discriminative power, suggesting the method has a great potential for AD diagnostics. The reported Raman spectroscopic examination of CSF can complement current clinical tests, making early AD detection fast, accurate, and inexpensive. While this study shows promise using a small sample set, further method validation on a larger scale is required to indicate the true strength of the approach.