Related Experiment Video
Updated: Jan 29, 2026
09:26
Identification of Antibacterial Immunity Proteins in Escherichia coli using MALDI-TOF-TOF-MS/MS and Top-Down Proteomic Analysis
Published on: May 23, 2021
3.7K
ReShuffle-MS: Region-Guided Data Augmentation Improves Artificial Intelligence-Based Resistance Prediction in
Dongbo Dai1, Chenyang Huang1, Junjie Li1
1School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China.
Microorganisms
|January 28, 2026
Summary
ReShuffle-MS enhances artificial intelligence (AI) models for predicting antimicrobial resistance (AMR) from mass spectrometry (MS) data, even with limited samples. This method improves prediction accuracy and clinical utility for rapid diagnostics.
Area of Science:
- Microbiology
- Analytical Chemistry
- Bioinformatics
Background:
- Rapid antimicrobial resistance (AMR) prediction using artificial intelligence (AI) and mass spectrometry (MS) is crucial but challenged by small sample sizes and high-dimensional spectral data.
- Existing methods struggle with overfitting to noise or discarding important low-intensity signals, hindering accurate AMR detection.
Purpose of the Study:
- To introduce ReShuffle-MS, a novel region-guided data augmentation framework designed to improve AI model performance for AMR prediction from MALDI-TOF MS data.
- To address the limitations of small-sample constraints and high-dimensional spectral data in AMR prediction.
Main Methods:
- ReShuffle-MS partitions mass spectra into a Main Discriminative Region (MDR) and a Peripheral Peak Region (PPR).
- It augments data by recombining signals within the PPR across samples of the same class, preserving the MDR.
- The framework was tested on clinical data for *Escherichia coli* levofloxacin resistance and validated on the DRIAMS-C dataset for ceftriaxone resistance.
Main Results:
- ReShuffle-MS significantly improved the average accuracy of classical machine learning models by 3.7% for *E. coli* levofloxacin resistance prediction.
- A one-dimensional convolutional neural network (CNN) achieved 83.25% accuracy and 97.28% recall using ReShuffle-MS.
- Grad-CAM visualization indicated a shift towards broader, more meaningful spectral pattern attention, and the method generalized to an external dataset and different antibiotic targets.
Conclusions:
- ReShuffle-MS enhances the robustness and clinical utility of AI-based AMR prediction from MALDI-TOF MS spectra.
- The region-guided augmentation approach effectively handles small-sample constraints and improves model generalization.
- This framework offers a promising strategy for advancing rapid AMR diagnostics in clinical settings.
Related Concept Videos
01:19MALDI-TOF Mass Spectrometry
6.8K
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...
6.8K
01:19Mass Spectrometry: Overview
8.6K
Mass spectrometry is an analytical technique used to determine the molecular mass and molecular formula of a compound. The basic principle of mass spectrometry is to generate ions from the analyte molecule and measure these ion abundances against their molecular mass. One common type of ionization, known as electron ionization or EI, bombards the analyte molecules in the gas phase with high-energy electron beams. The electron beams displace an electron from the molecule and leave behind a...
8.6K
01:21Tandem Mass Spectrometry
2.5K
Tandem mass spectrometry is a technique that uses multiple mass analyzers in series to obtain a higher selectivity and reduce chemical noise during analyte detection. Instruments with multiple analyzers separated by an interaction cell enable secondary fragmentation and selected study of the fragment ions.Secondary fragmentations occur in the interaction cell and can be induced by various factors. Fragmentation induced by collision with inert gases, such as N2, Ar, He, etc., is called...
2.5K
01:15Mass Spectrometry of Amines
5.4K
In mass spectroscopy, amines undergo fragmentation to give parent ions with odd molecule weights. This observed mass spectrum follows the nitrogen rule; a molecule with an odd number of nitrogen atoms produces a molecular ion with an odd molecular weight. Amines undergo fragmentation through α cleavage, producing nitrogen-containing cations—iminium ions—and alkyl radicals. Mass spectra of aromatic and cyclic aliphatic amines exhibit strong molecular ion peaks, but acyclic...
5.4K
01:13Mass Spectrometry: Isotope Effect
4.1K
Most elements exist in nature as a mixture of isotopes. The isotopes differ in weight due to their respective number of neutrons. The molecular weight of a molecule is different depending on the specific isotope of its elements involved. As a result, the mass spectrum of the molecule exhibits peaks from the same fragment at multiple positions. The positions of these mass signals depend on the mass differences between isotopes. Furthermore, the intensity of these signals is dependent on the...
4.1K
01:21Chemical Ionization (CI) Mass Spectrometry
1.5K
The molecular ion peak of a molecule in the mass spectrum provides vital information for molecular identification. However, conventional electron impact ionization can lead to the rapid dissociation of some molecular ions before they reach the detector. A milder ionization method is required to increase the lifetime of such ionized analyte molecules. Chemical ionization (CI) is a gas-phase protonation reaction useful for mass-analyzing analyte molecules that are easily protonated to yield the...
1.5K