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

You might also read

Related Articles

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

Sort by
Same author

Ultrasonography for suspected mild-to-moderate acute left colonic diverticulitis: a prospective head-to-head study with computed tomography.

Frontiers in radiology·2026
Same author

SUCNR1 coordinates metabolic flux, mitochondrial function, and nutrient-dependent adaptation in hepatocytes.

Science advances·2026
Same author

Dry Deposition Strategies for MALDI-MS Imaging: Principles, Advances and Emerging Applications.

Analytical science advances·2026
Same author

Validation of ChatGPT-4o for detecting surgical site infections after colorectal surgery from electronic health records: A large-scale diagnostic accuracy study.

International journal of infectious diseases : IJID : official publication of the International Society for Infectious Diseases·2026
Same author

Hydroxytyrosol Modulates Arachidonic Acid Metabolism and Purine Catabolism in Individuals with Prediabetes: An Untargeted Metabolomics Study in a Randomized Controlled Trial.

Antioxidants (Basel, Switzerland)·2026
Same author

A targeted metabolomic method to detect epigenetically relevant metabolites.

Molecular metabolism·2026
Same journal

Screen for Tissue-Specific Markers of Drug-Induced Phospholipidosis Using Mass Spectrometry Imaging.

Journal of the American Society for Mass Spectrometry·2026
Same journal

Molecular Framework Modification in Mass Spectrometry: Atom Exchange, Insertion, and Deletion.

Journal of the American Society for Mass Spectrometry·2026
Same journal

Interlaboratory Comparison of Orbitrap Analyzers in OrbiSIMS: Noise Parameters, Intensity Scaling, and Detection Limits.

Journal of the American Society for Mass Spectrometry·2026
Same journal

Isotope-Coded Derivatization Enables Accurate LC-MS/MS Quantification of Urinary THC-COOH without Isotope-Labeled Cannabinoid Standards.

Journal of the American Society for Mass Spectrometry·2026
Same journal

Characterization of Disulfide Bonds in Cyclic Peptides Using Electron Transfer-Ultraviolet Photodissociation Mass Spectrometry.

Journal of the American Society for Mass Spectrometry·2026
Same journal

Unveiling Ciprofloxacin Protonation Isomers: an Integrated Approach with Mass Spectrometry, Ion Mobility Spectrometry and Infrared Ion Spectroscopy.

Journal of the American Society for Mass Spectrometry·2026
See all related articles
  1. Home
  3. Benchmarking Ms/ms Featurization Strategies For Machine Learning-driven Metabolite Structure Annotation.
  1. Home
  3. Benchmarking Ms/ms Featurization Strategies For Machine Learning-driven Metabolite Structure Annotation.

Related Experiment Video

An Integrated Workflow of Identification and Quantification on FDR Control-Based Untargeted Metabolome
05:35

An Integrated Workflow of Identification and Quantification on FDR Control-Based Untargeted Metabolome

Published on: September 20, 2022

Benchmarking MS/MS Featurization Strategies for Machine Learning-Driven Metabolite Structure Annotation.

Roger Giné1,2, Ivan Pérez-López1, Josep M Badia1

  • 1Universitat Rovira i Virgili, Department of Electronic Engineering, 43007 Tarragona, Spain.

Journal of the American Society for Mass Spectrometry
|June 15, 2026

View abstract on PubMed

Summary
This summary is machine-generated.

This study benchmarks spectral featurization methods for metabolomics, finding adaptive binning, frequent-peaks, and DreaMS excel. Accurate metabolite annotation relies heavily on precise mass matching for reliable structure retrieval.

Keywords:
machine learningmetabolite annotationspectral featurizationstructure retrievaltandem mass spectrometryuntargeted metabolomics

More Related Videos

Large Scale Non-targeted Metabolomic Profiling of Serum by Ultra Performance Liquid Chromatography-Mass Spectrometry (UPLC-MS)
07:34

Large Scale Non-targeted Metabolomic Profiling of Serum by Ultra Performance Liquid Chromatography-Mass Spectrometry (UPLC-MS)

Published on: March 14, 2013

Multi-step Preparation Technique to Recover Multiple Metabolite Compound Classes for In-depth and Informative Metabolomic Analysis
11:25

Multi-step Preparation Technique to Recover Multiple Metabolite Compound Classes for In-depth and Informative Metabolomic Analysis

Published on: July 11, 2014

Related Experiment Videos

An Integrated Workflow of Identification and Quantification on FDR Control-Based Untargeted Metabolome
05:35

An Integrated Workflow of Identification and Quantification on FDR Control-Based Untargeted Metabolome

Published on: September 20, 2022

Large Scale Non-targeted Metabolomic Profiling of Serum by Ultra Performance Liquid Chromatography-Mass Spectrometry (UPLC-MS)
07:34

Large Scale Non-targeted Metabolomic Profiling of Serum by Ultra Performance Liquid Chromatography-Mass Spectrometry (UPLC-MS)

Published on: March 14, 2013

Multi-step Preparation Technique to Recover Multiple Metabolite Compound Classes for In-depth and Informative Metabolomic Analysis
11:25

Multi-step Preparation Technique to Recover Multiple Metabolite Compound Classes for In-depth and Informative Metabolomic Analysis

Published on: July 11, 2014

Area of Science:

  • Metabolomics
  • Computational Chemistry
  • Bioinformatics

Background:

  • Untargeted metabolomics experiments generate vast amounts of MS/MS spectra, often unannotated due to incomplete spectral libraries.
  • Machine learning offers a path to annotate metabolites beyond direct library matches, but requires effective numerical representations of MS/MS spectra.
  • Existing spectral featurization methods lack systematic comparison, hindering optimal metabolite annotation.

Purpose of the Study:

  • To systematically benchmark various spectral featurization methods for MS/MS data.
  • To evaluate the impact of vector dimensionality on performance.
  • To assess the accuracy of different featurization strategies in retrieving correct metabolite structures from large databases.

Main Methods:

  • Over 71,000 unique compounds with merged-energy MS/MS spectra were used.
  • Benchmarked methods included fixed/adaptive binning, frequent-peaks, spectrum hashing, and learned embeddings (Spec2Vec, MS2DeepScore, DreaMS, SpecEmbedding).
  • 105 neural network models were trained to predict Mol2Vec embeddings and retrieve structures, with retrieval assessed at 0.1, 3, and 10 ppm mass tolerances.

    • Main Results:

    • Adaptive binning, frequent-peaks, and DreaMS demonstrated the most accurate embedding predictions.
    • Top-1 retrieval accuracy reached 46% at 0.1 ppm, 44% at 3 ppm, and 38% at 10 ppm on the test dataset.
    • Top-5 accuracies reached up to 77%, with performance varying significantly based on mass tolerance and featurization strategy.

    Conclusions:

    • Clear performance differences exist among spectral featurization strategies.
    • Metabolite structure retrieval accuracy is strongly dependent on mass precision.
    • There is a need for evaluation metrics that align with structure-level annotation tasks in metabolomics.