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

Peptide Identification Using Tandem Mass Spectrometry01:33

Peptide Identification Using Tandem Mass Spectrometry

6.4K
Tandem mass spectrometry, also known as MS/MS or MS2, is an analytical technique that employs two mass analyzers. Essentially it is a series of mass spectrometers that helps isolate a particular biomolecule and then helps study its chemical properties.
This technique helps gather information regarding the protein from which the peptide was obtained and to study the peptides’ amino acid sequence. Identifying peptides from a complex mixture is an important component of the growing field of...
6.4K

You might also read

Related Articles

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

Sort by
Same author

Comparative genomic analysis of clinically relevant human skin-associated fungi.

Nature communications·2026
Same author

Proteomics reveals spatial and molecular heterogeneities in advanced atherosclerotic carotid artery plaques.

Nature cardiovascular research·2026
Same author

Molecular maps of diseases from omics data and network embeddings.

NPJ systems biology and applications·2026
Same author

Author Correction: Regulatory T cells in the mouse hypothalamus control immune activation and ameliorate metabolic impairments in high-calorie environments.

Nature communications·2026
Same author

Cysteine availability tunes ubiquitin signaling via inverse stability of LRRC58 E3 ligase and its substrate CDO1.

Nature communications·2026
Same author

CCMRI: a classification and curated database of climate change-related microbiome studies.

Scientific reports·2026

Related Experiment Video

Updated: Jun 22, 2025

Deep Proteome Profiling by Isobaric Labeling, Extensive Liquid Chromatography, Mass Spectrometry, and Software-assisted Quantification
10:37

Deep Proteome Profiling by Isobaric Labeling, Extensive Liquid Chromatography, Mass Spectrometry, and Software-assisted Quantification

Published on: November 15, 2017

11.9K

Imputation of label-free quantitative mass spectrometry-based proteomics data using self-supervised deep learning.

Henry Webel1,2, Lili Niu1, Annelaura Bach Nielsen1

  • 1Novo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen N, Denmark.

Nature Communications
|June 26, 2024
PubMed
Summary
This summary is machine-generated.

Deep learning imputation methods like PIMMS-VAE enhance mass spectrometry proteomics analysis by recovering missing data. This approach identified more significant proteins in alcohol-related liver disease, aiding in disease progression prediction.

More Related Videos

High Resolution Quantitative Synaptic Proteome Profiling of Mouse Brain Regions After Auditory Discrimination Learning
10:36

High Resolution Quantitative Synaptic Proteome Profiling of Mouse Brain Regions After Auditory Discrimination Learning

Published on: December 15, 2016

10.6K
Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.5K

Related Experiment Videos

Last Updated: Jun 22, 2025

Deep Proteome Profiling by Isobaric Labeling, Extensive Liquid Chromatography, Mass Spectrometry, and Software-assisted Quantification
10:37

Deep Proteome Profiling by Isobaric Labeling, Extensive Liquid Chromatography, Mass Spectrometry, and Software-assisted Quantification

Published on: November 15, 2017

11.9K
High Resolution Quantitative Synaptic Proteome Profiling of Mouse Brain Regions After Auditory Discrimination Learning
10:36

High Resolution Quantitative Synaptic Proteome Profiling of Mouse Brain Regions After Auditory Discrimination Learning

Published on: December 15, 2016

10.6K
Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.5K

Area of Science:

  • Proteomics
  • Bioinformatics
  • Machine Learning

Background:

  • Mass spectrometry (MS)-based proteomics using label-free quantification (LFQ) relies heavily on imputation techniques to handle missing measurements.
  • Missing data is a common challenge in large-scale proteomics datasets, potentially obscuring biologically relevant findings.

Purpose of the Study:

  • To evaluate deep learning approaches, including collaborative filtering, denoising autoencoders, and variational autoencoders, for imputing missing values in LFQ proteomics data.
  • To apply and validate a novel method, Proteomics Imputation Modeling Mass Spectrometry (PIMMS), on a real-world alcohol-related liver disease (ALD) cohort.

Main Methods:

  • Implementation of collaborative filtering, denoising autoencoders (DAEs), and variational autoencoders (VAEs) for missing value imputation in LFQ proteomics.
  • Application of the PIMMS method, specifically PIMMS-VAE, to a blood plasma proteomics dataset from 358 individuals with ALD.
  • Systematic evaluation of imputation performance by removing 20% of intensity values and assessing recovery of significant protein groups.

Main Results:

  • PIMMS-VAE imputation successfully recovered 15 out of 17 significant abundant protein groups when 20% of data was removed.
  • Analysis of the full dataset with imputation identified 30 additional significantly differentially abundant proteins compared to no imputation.
  • Imputed proteins were found to be predictive of ALD progression in machine learning models, highlighting their clinical relevance.

Conclusions:

  • Deep learning-based imputation methods, such as PIMMS-VAE, are effective for handling missing data in large-scale MS-based proteomics.
  • The proposed imputation strategies can significantly increase the number of identified differentially abundant proteins and improve the biological insights derived from proteomics studies.
  • The study recommends the adoption of deep learning approaches for imputation in MS-based proteomics, particularly for larger datasets, and provides accessible workflows.