The Rametrix™ PRO Toolbox v1.0 for MATLAB®

Background Existing tools for chemometric analysis of vibrational spectroscopy data have enabled characterization of materials and biologicals by their broad molecular composition. The Rametrix™ LITE Toolbox v1.0 for MATLAB® is one such tool available publicly. It applies discriminant analysis of pr...

Full description

Bibliographic Details
Main Authors: Ryan S. Senger, John L. Robertson
Format: Article
Language:English
Published: PeerJ Inc. 2020-01-01
Series:PeerJ
Subjects:
Online Access:https://peerj.com/articles/8179.pdf
_version_ 1827607306245767168
author Ryan S. Senger
John L. Robertson
author_facet Ryan S. Senger
John L. Robertson
author_sort Ryan S. Senger
collection DOAJ
description Background Existing tools for chemometric analysis of vibrational spectroscopy data have enabled characterization of materials and biologicals by their broad molecular composition. The Rametrix™ LITE Toolbox v1.0 for MATLAB® is one such tool available publicly. It applies discriminant analysis of principal components (DAPC) to spectral data to classify spectra into user-defined groups. However, additional functionality is needed to better evaluate the predictive capabilities of these models when “unknown” samples are introduced. Here, the Rametrix™ PRO Toolbox v1.0 is introduced to provide this capability. Methods The Rametrix™ PRO Toolbox v1.0 was constructed for MATLAB® and works with the Rametrix™ LITE Toolbox v1.0. It performs leave-one-out analysis of chemometric DAPC models and reports predictive capabilities in terms of accuracy, sensitivity (true-positives), and specificity (true-negatives). Rametrix™PRO is available publicly through GitHub under license agreement at: https://github.com/SengerLab/RametrixPROToolbox. Rametrix™ PRO was used to validate Rametrix™ LITE models used to detect chronic kidney disease (CKD) in spectra of urine obtained by Raman spectroscopy. The dataset included Raman spectra of urine from 20 healthy individuals and 31 patients undergoing peritoneal dialysis treatment for CKD. Results The number of spectral principal components (PCs) used in building the DAPC model impacted the model accuracy, sensitivity, and specificity in leave-one-out analyses. For the dataset in this study, using 35 PCs in the DAPC model resulted in 100% accuracy, sensitivity, and specificity in classifying an unknown Raman spectrum of urine as belonging to a CKD patient or a healthy volunteer. Models built with fewer or greater number of PCs showed inferior performance, which demonstrated the value of Rametrix™ PRO in evaluating chemometric models constructed with Rametrix™ LITE.
first_indexed 2024-03-09T06:52:35Z
format Article
id doaj.art-d6e7eaee87744e3ea58d2c5839805b2e
institution Directory Open Access Journal
issn 2167-8359
language English
last_indexed 2024-03-09T06:52:35Z
publishDate 2020-01-01
publisher PeerJ Inc.
record_format Article
series PeerJ
spelling doaj.art-d6e7eaee87744e3ea58d2c5839805b2e2023-12-03T10:25:16ZengPeerJ Inc.PeerJ2167-83592020-01-018e817910.7717/peerj.8179The Rametrix™ PRO Toolbox v1.0 for MATLAB®Ryan S. Senger0John L. Robertson1Department of Biological Systems Engineering, Virginia Polytechnic Institute and State University (Virginia Tech), Blacksburg, VA, United States of AmericaDialySensors, Inc., Blacksburg, VA, United States of AmericaBackground Existing tools for chemometric analysis of vibrational spectroscopy data have enabled characterization of materials and biologicals by their broad molecular composition. The Rametrix™ LITE Toolbox v1.0 for MATLAB® is one such tool available publicly. It applies discriminant analysis of principal components (DAPC) to spectral data to classify spectra into user-defined groups. However, additional functionality is needed to better evaluate the predictive capabilities of these models when “unknown” samples are introduced. Here, the Rametrix™ PRO Toolbox v1.0 is introduced to provide this capability. Methods The Rametrix™ PRO Toolbox v1.0 was constructed for MATLAB® and works with the Rametrix™ LITE Toolbox v1.0. It performs leave-one-out analysis of chemometric DAPC models and reports predictive capabilities in terms of accuracy, sensitivity (true-positives), and specificity (true-negatives). Rametrix™PRO is available publicly through GitHub under license agreement at: https://github.com/SengerLab/RametrixPROToolbox. Rametrix™ PRO was used to validate Rametrix™ LITE models used to detect chronic kidney disease (CKD) in spectra of urine obtained by Raman spectroscopy. The dataset included Raman spectra of urine from 20 healthy individuals and 31 patients undergoing peritoneal dialysis treatment for CKD. Results The number of spectral principal components (PCs) used in building the DAPC model impacted the model accuracy, sensitivity, and specificity in leave-one-out analyses. For the dataset in this study, using 35 PCs in the DAPC model resulted in 100% accuracy, sensitivity, and specificity in classifying an unknown Raman spectrum of urine as belonging to a CKD patient or a healthy volunteer. Models built with fewer or greater number of PCs showed inferior performance, which demonstrated the value of Rametrix™ PRO in evaluating chemometric models constructed with Rametrix™ LITE.https://peerj.com/articles/8179.pdfRaman spectroscopyMATLABPrincipal component analysisDiscriminant analysisSpectral data analysisPrediction
spellingShingle Ryan S. Senger
John L. Robertson
The Rametrix™ PRO Toolbox v1.0 for MATLAB®
PeerJ
Raman spectroscopy
MATLAB
Principal component analysis
Discriminant analysis
Spectral data analysis
Prediction
title The Rametrix™ PRO Toolbox v1.0 for MATLAB®
title_full The Rametrix™ PRO Toolbox v1.0 for MATLAB®
title_fullStr The Rametrix™ PRO Toolbox v1.0 for MATLAB®
title_full_unstemmed The Rametrix™ PRO Toolbox v1.0 for MATLAB®
title_short The Rametrix™ PRO Toolbox v1.0 for MATLAB®
title_sort rametrix™ pro toolbox v1 0 for matlab r
topic Raman spectroscopy
MATLAB
Principal component analysis
Discriminant analysis
Spectral data analysis
Prediction
url https://peerj.com/articles/8179.pdf
work_keys_str_mv AT ryanssenger therametrixprotoolboxv10formatlab
AT johnlrobertson therametrixprotoolboxv10formatlab
AT ryanssenger rametrixprotoolboxv10formatlab
AT johnlrobertson rametrixprotoolboxv10formatlab