Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Raman Spectroscopy: Overview01:20

Raman Spectroscopy: Overview

380
The underlying principle of Raman spectroscopy is based on the interaction between light and matter, specifically molecules' inelastic scattering of photons. When a monochromatic beam of light, typically from a laser source, interacts with a sample, most scattered light has the same frequency as the incident light. This is known as Rayleigh scattering.
However, a small fraction of the scattered light exhibits a frequency shift due to the exchange of energy between the incident photons and...
380
Raman Spectroscopy Instrumentation: Overview01:26

Raman Spectroscopy Instrumentation: Overview

332
A conventional Raman spectrophotometer includes a laser source, a sample holding system, a wavelength selector, and a detector.
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...
332
IR Spectrum Peak Splitting: Symmetric vs Asymmetric Vibrations01:08

IR Spectrum Peak Splitting: Symmetric vs Asymmetric Vibrations

1.0K
Identical bonds within a polyatomic group can stretch symmetrically (in-phase) or asymmetrically (out-of-phase). Similar to hydrogen bonding, these vibrations also influence the shape of the IR peak. Generally, asymmetric stretching frequencies are higher than symmetric stretching frequencies. For example, primary amines exhibit two distinct IR peaks between 3300–3500 cm−1 corresponding to the symmetric and asymmetric N-H stretching, while secondary amines exhibit a single...
1.0K
MALDI-TOF Mass Spectrometry01:19

MALDI-TOF Mass Spectrometry

4.8K
Mass spectrometry is a powerful characterization technique that can identify and separate a wide variety of compounds ranging from chemical to biological entities, based on their mass-to-charge ratio (m/z). The instruments that allow this detection, known as mass spectrometers, have three components: an ion source, a mass analyzer, and a detector. These spectrometers differ based on the nature of their ion source and analyzers.
Matrix-assisted laser desorption ionization (MALDI) is a commonly...
4.8K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

On-Chip Raman Spectroscopy for Rapid Antimicrobial Susceptibility Testing from Blood Cultures.

Analytical chemistry·2026
Same author

Current trends in machine learning for surface-enhanced Raman spectroscopy.

The Analyst·2026
Same author

Lightweight CycleGAN models for cross-modality image transformation and experimental quality assessment in fluorescence microscopy.

Biomedical optics express·2026
Same author

Denoising and Baseline Correction of Low-Scan FTIR Spectra: A Benchmark of Deep Learning Models Against Traditional Signal Processing.

Bioengineering (Basel, Switzerland)·2026
Same author

Label-Free Differentiation of Antimicrobial Resistance Groups Using Raman Spectroscopy.

Analytical chemistry·2026
Same author

Automatic optimization of flat-field corrections by evaluation and enhancement (EVEN) in multimodal optical microscopy.

Nature communications·2026

Related Experiment Video

Updated: Jul 1, 2025

Rapid Antimicrobial Susceptibility Testing by Stimulated Raman Scattering Imaging of Deuterium Incorporation in a Single Bacterium
12:08

Rapid Antimicrobial Susceptibility Testing by Stimulated Raman Scattering Imaging of Deuterium Incorporation in a Single Bacterium

Published on: February 14, 2022

2.7K

Siamese Networks for Clinically Relevant Bacteria Classification Based on Raman Spectroscopy.

Jhonatan Contreras1,2, Sara Mostafapour1, Jürgen Popp1,2

  • 1Institute of Physical Chemistry (IPC) and Abbe Center of Photonics (ACP), Friedrich Schiller University Jena, Member of the Leibniz Centre for Photonics in Infection Research (LPI), Helmholtzweg 4, 07743 Jena, Germany.

Molecules (Basel, Switzerland)
|March 13, 2024
PubMed
Summary

Siamese networks offer a promising solution for bacterial strain identification using Raman spectra, especially with limited data. Siamese-model2 achieved high sensitivity, outperforming other methods in challenging scenarios.

Keywords:
Raman spectroscopySiamese networksbacteria classificationmachine learning

More Related Videos

Identification of Rare Bacterial Pathogens by 16S rRNA Gene Sequencing and MALDI-TOF MS
06:34

Identification of Rare Bacterial Pathogens by 16S rRNA Gene Sequencing and MALDI-TOF MS

Published on: July 11, 2016

18.2K
Use of MALDI-TOF Mass Spectrometry and a Custom Database to Characterize Bacteria Indigenous to a Unique Cave Environment Kartchner Caverns, AZ, USA
11:09

Use of MALDI-TOF Mass Spectrometry and a Custom Database to Characterize Bacteria Indigenous to a Unique Cave Environment Kartchner Caverns, AZ, USA

Published on: January 2, 2015

14.0K

Related Experiment Videos

Last Updated: Jul 1, 2025

Rapid Antimicrobial Susceptibility Testing by Stimulated Raman Scattering Imaging of Deuterium Incorporation in a Single Bacterium
12:08

Rapid Antimicrobial Susceptibility Testing by Stimulated Raman Scattering Imaging of Deuterium Incorporation in a Single Bacterium

Published on: February 14, 2022

2.7K
Identification of Rare Bacterial Pathogens by 16S rRNA Gene Sequencing and MALDI-TOF MS
06:34

Identification of Rare Bacterial Pathogens by 16S rRNA Gene Sequencing and MALDI-TOF MS

Published on: July 11, 2016

18.2K
Use of MALDI-TOF Mass Spectrometry and a Custom Database to Characterize Bacteria Indigenous to a Unique Cave Environment Kartchner Caverns, AZ, USA
11:09

Use of MALDI-TOF Mass Spectrometry and a Custom Database to Characterize Bacteria Indigenous to a Unique Cave Environment Kartchner Caverns, AZ, USA

Published on: January 2, 2015

14.0K

Area of Science:

  • Microbiology
  • Spectroscopy
  • Machine Learning

Background:

  • Bacterial strain identification is crucial for diagnostics and quality control.
  • Classical machine learning and Convolutional Neural Networks (CNNs) are used for Raman spectra-based identification.
  • CNNs require large datasets and can be costly to retrain for new bacterial targets.

Purpose of the Study:

  • To compare the performance of classical machine learning, CNNs, and Siamese networks for bacterial identification using Raman spectra.
  • To evaluate models based on sensitivity, training time, prediction time, and parameter count.
  • To determine the most effective model for handling limited and unbalanced bacterial spectral datasets.

Main Methods:

  • Developed and tested classical machine learning, shallow and deep CNNs, and two Siamese network variants.
  • Utilized Raman spectral datasets of bacteria for model training and evaluation.
  • Assessed models using metrics including mean sensitivity, training time, prediction time, and number of parameters.

Main Results:

  • Siamese-model2 achieved the highest mean sensitivity (83.61 ± 4.73%).
  • Siamese networks demonstrated strong performance in unbalanced and limited data scenarios, reaching 73% prediction accuracy.
  • Classical machine learning and shallow CNNs showed suitability when time and resources are limited.

Conclusions:

  • The optimal model choice for bacterial identification depends on the specific application's trade-offs between accuracy, time, and resources.
  • Siamese networks are advantageous for small datasets, while CNNs are better suited for extensive data.
  • Model selection should align with the balance between performance requirements and available computational resources.