Related Experiment Video
Updated: Jan 12, 2026

Resolving Water, Proteins, and Lipids from In Vivo Confocal Raman Spectra of Stratum Corneum through a Chemometric Approach
Published on: September 26, 2019
Automated identification of class-separating principal component subspaces in biomedical Raman and Fourier Transform
Dorota Jakubczyk1, Jan Jakub Kęsik2, Piotr Terlecki2
1Department of Physics and Medical Engineering, Rzeszow University of Technology, Rzeszów, Poland.
PCA AutoExplorer automates the identification of key spectral features for disease diagnosis using Principal Component Analysis (PCA) triplets. This tool enhances biomarker discovery in clinical vibrational spectroscopy by rigorously ranking spectral data.
Area of Science:
- Biomedical Engineering
- Spectroscopy
- Data Science
Background:
- Clinical vibrational spectroscopy offers powerful biomarker discovery potential.
- Automated analysis is crucial for handling complex spectral datasets and improving diagnostic accuracy.
Purpose of the Study:
- To introduce PCA AutoExplorer, an open-source tool for automated identification of Principal Component (PC) triplets that maximize class separation in clinical vibrational spectroscopy.
- To develop a statistically rigorous framework for prioritizing spectral biomarkers and enhancing diagnostic reliability.
Main Methods:
- Exhaustive evaluation of all PC triplets using Mahalanobis distance and Linear Discriminant Analysis (LDA) accuracy.
- Development of marker strength plots and PC loading heatmaps for prioritizing diagnostic bands.
- Validation using Fourier Transform Infrared Spectroscopy (FTIR) and Raman Spectroscopy data from acute coronary syndrome patients and controls.
Main Results:
- PCA AutoExplorer successfully identified PC triplets yielding high class separation (Mahalanobis distance up to ~2.03, LDA accuracy 96%-100%).
- Raman spectroscopy (second derivative) and FTIR (intensity/first derivative) showed optimal performance depending on spectral range.
- Key diagnostic bands were highlighted, including specific wavenumbers for FTIR and Raman Spectroscopy.
Conclusions:
- PCA AutoExplorer provides a reproducible and statistically sound method for biomarker discovery in clinical vibrational spectroscopy.
- The tool enhances the reliability of spectral analysis and is adaptable to other omics-related spectral data.
Related Concept Videos
Raman Spectroscopy Instrumentation: Overview
The monochromatic laser source, typically using visible or near-infrared radiation, generates a highly focused beam of light. This light interacts with the molecules of the sample, scattering some of the light. Liquid and gaseous samples are usually tested in ordinary glass capillaries, while solids can be analyzed as powders packed in capillaries or as potassium...
Raman Spectroscopy: Overview
However, a small fraction of the scattered light exhibits a frequency shift due to the exchange of energy between the incident photons and...
IR Frequency Region: Fingerprint Region
MALDI-TOF Mass Spectrometry
Infrared (IR) Spectroscopy: Overview
Different compounds display unique properties due to their...
IR Spectrum Peak Splitting: Symmetric vs Asymmetric Vibrations

