Raman spectroscopy and PCA-SVM as a non-invasive diagnostic tool to identify and classify qualitatively glycated hemoglobin levels <i>in vivo</i>

Villa-Manríquez, J. F.; Castro‐Ramos, J.; Gutiérrez-Delgado, F.; Lopéz-Pacheco, M. A.; Villanueva-Luna, A. E.

doi:10.1002/jbio.201600169

Cited by 27 publications

(21 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is highlighted by recent applications of Raman spectroscopy and PCA in disease diagnostics. [106][107][108][109][110] Nevertheless, the initial characterisation of pure samples is essential for the development of chemical fingerprints that can be applied to such classification models in complex systems in order to develop an understanding of any differences that are observed.…”

Section: Discussionmentioning

confidence: 99%

Conformational Evolution of Molecular Signatures during Amyloidogenic Protein Aggregation

Devitt

Rice

Crisford

et al. 2019

ACS Chem. Neurosci.

View full text Add to dashboard Cite

Aggregation is a pathological hallmark of proteinopathies such as Alzheimer's disease and results in the deposition of β-sheet-rich amyloidogenic protein aggregates. Such proteinopathies can be classified by the identity of one or more aggregated protein, with recent evidence also suggesting that distinct molecular conformers (strains) of the same protein can be observed in different diseases, as well is in sub-types of the same disease. Therefore, methods for the quantification of pathological changes in protein conformation are central to understanding and treating proteinopathies. In this work the evolution of Raman spectroscopic molecular signatures of three conformationally distinct proteins, Bovine Serum Albumin (α-helical-rich), β2-microglobulin (β-sheetrich) and tau (natively disordered), was assessed during aggregation into oligomers and fibrils. The morphological evolution was tracked using Atomic Force Microscopy and corresponding conformational changes were assessed by their Raman signatures acquired in both wet and dried conditions. A deconvolution model was developed which allowed us to quantify the conformation of the non-regular protein tau, as well as for the oligomeric and fibrillar species of each of the proteins. Principle component analysis of the fingerprint region allowed further identification of the distinguishing spectral features and unsupervised distinction. While an increase in β-sheet is seen on aggregation, crucially, however, each protein also retains a significant proportion of its native monomeric structure after aggregation. Thus, spectral analysis of each aggregated species, oligomeric, as well as fibrillar, for each protein resulted in a unique and quantitative 'conformational fingerprint'. This approach allowed us to provide the first differential detection of both oligomers and fibrils of the three different amyloidogenic proteins, including tau, whose aggregates have never before been interrogated using spontaneous Raman spectroscopy. Quantitative 'conformational fingerprinting' by Raman spectroscopy thus demonstrates its huge potential and utility in understanding proteinopathic disease mechanisms and for providing strain-specific early diagnostic markers and targets for disease-modifying therapies.

show abstract

Section: Discussionmentioning

confidence: 99%

Conformational Evolution of Molecular Signatures during Amyloidogenic Protein Aggregation

Devitt

Rice

Crisford

et al. 2019

ACS Chem. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Among multivariate analysis methods, those based on the principal component analysis (PCA) proved to be particularly suitable for analyzing the complex spectra resulting when Raman spectroscopy is used in biomedical applications. 46,47 The PCA method performs a mathematical decomposition of the spectral data, which reduces the data dimensions to a smaller number of scores and principal components (PCs) or loadings that effectively carry most of the important information of the spectra. 48 Classification of spectral data can be easily done by choosing different combinations of PCs to build a new coordinate system.…”

Section: Multivariate Analysis (I-pca)mentioning

confidence: 99%

Monitoring early phases of orthodontic treatment by means of Raman spectroscopies

et al. 2017

View full text Add to dashboard Cite

Gingival crevicular fluid (GCF) is a site-specific exudate in the gingival sulcus. GCF composition changes in response to diseases or mechanical stimuli, such as those occurring during orthodontic treatments. Raman microspectroscopy (μ-RS) and surface-enhanced Raman spectroscopy (SERS) were adopted for a GCF analysis during different initial phases of orthodontic force application. GCF samples were pooled from informed patients using paper cones. SERS spectra were obtained from GCF extracted from these cones, whereas μ-RS spectra were directly acquired on paper cones without any manipulation. The spectral characteristics of the main functional groups and the changes in cytochrome, amide III, and amide I contributions were highlighted in the different phases of orthodontic treatment with both SERS and μ-RS analysis. μ-RS directly performed on the paper cones together with proper statistical methods can offer an effective approach for the development of a tool for monitoring the processes occurring during orthodontic treatments, which may help the clinician in the choice of type of treatment individually for each patient and accelerate and improve the orthodontic therapy.

show abstract

“…We reason that accurate discrimination of such glycemic states, based on the spectral profiles recorded from the whole blood and hemolysate specimen, would offer value in aiding treatment decisions. A recent study using spontaneous Raman spectroscopy adopts a similar approach, namely categorical classification of glycated hemoglobin levels between healthy volunteers, well‐controlled diabetic patients and not controlled diabetic patients .…”

Section: Resultsmentioning

confidence: 99%

“…In this pilot study, we seek to couple the measurements of RR profiles with support vector machines (SVMs) in order to map the subtle differences in the spectra to prediction of class label (low, mid and high). Segmentation into these categories by sampling small volumes of the specimen offers the requisite clinical information to inform therapeutic decision‐making, as espoused in a recent report on differentiation of diabetic and nondiabetic populations by Villa‐Manríquez et al …”

Section: Introductionmentioning

confidence: 99%

Label‐free spectrochemical probe for determination of hemoglobin glycation in clinical blood samples

Pandey

Singh

Zhang

et al. 2018

Journal of Biophotonics

View full text Add to dashboard Cite

Glycated hemoglobin, HbA1c, is an important biomarker that reveals the average value of blood glucose over the preceding 3 months. While significant recent attention has been focused on the use of optical and direct molecular spectroscopic methods for determination of HbA1c, a facile test that minimizes sample preparation needs and turnaround time still remains elusive. Here, we report a label-free approach for identifying low, mid and high-HbA1c groups in hemolysate and in whole blood samples featuring resonance Raman (RR) spectroscopy and support vector machine (SVM)-based classification of spectral patterns. The diagnostic power of RR measurements stems from its selective enhancement of hemoglobin-specific features, which simultaneously minimizes the blood matrix spectral interference and permits detection in the native solution. In this pilot study, our spectroscopic observations reveal that glycation of hemoglobin results in subtle but reproducible changes even when detected in the whole blood matrix. Leveraging SVM analysis of the principal component scores determined from the RR spectra, we show high degree of accuracy in classifying clinical specimen. We envisage that the promising findings will pave the way for more extensive clinical specimen investigations with the ultimate goal of translating molecular spectroscopy for routine point-of-care testing.

show abstract

Raman spectroscopy and PCA-SVM as a non-invasive diagnostic tool to identify and classify qualitatively glycated hemoglobin levels in vivo

Cited by 27 publications

References 16 publications

Conformational Evolution of Molecular Signatures during Amyloidogenic Protein Aggregation

Conformational Evolution of Molecular Signatures during Amyloidogenic Protein Aggregation

Monitoring early phases of orthodontic treatment by means of Raman spectroscopies

Label‐free spectrochemical probe for determination of hemoglobin glycation in clinical blood samples

Contact Info

Product

Resources

About