Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

High-Resolution Mass Spectrometry (HRMS)

High-Resolution Mass Spectrometry (HRMS)

The resolution of a mass spectrometer depends on the efficiency of separating ions with different ion masses. The mass of an atom is approximated to the sum of the masses of protons and neutrons inside, considering the masses of protons and neutrons as equal. However, the masses of the proton (1.6726 × 10−24 g) and neutron (1.6749 × 10−24 g) are not truly equal. There is a minor error in the expression of atomic masses relative to the simplest atom of hydrogen. For...

You might also read

Related Articles

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

Sort by

Same author

Primary Care Integrated Management of chronic obstructive pulmonary disease (PRIM-COPD): study protocol for a cluster-randomised controlled trial.

BMJ open respiratory research·2026

Same author

The mTOR/Akt pathway is involved in regulating astrocyte growth and GLT-1 expression during cerebral ischemia-reperfusion.

PloS one·2026

Same author

Microbial production of xanthohumol driven by synthetic biology approaches.

World journal of microbiology & biotechnology·2026

Same author

Benchmarking computational methods for identifying and quantifying polyadenylation sites from 3' tag-based single-cell RNA-seq data.

Nucleic acids research·2026

Same author

Single-Cell Gene Module Inference Reveals Alternative Polyadenylation Dynamics Associated with Autism.

International journal of molecular sciences·2026

Same author

[Eurycomanone inhibits renal ischemia/reperfusion-induced mitochondrial dysfunction and inflammation in mice by binding to STAT3 to inhibit its phosphorylation].

Nan fang yi ke da xue xue bao = Journal of Southern Medical University·2026

Search research articles

Related Experiment Video

Updated: Jan 11, 2026

Navigating the Mass Spectrometry-Based Proteomic Data Using Free Computational Tools

Navigating the Mass Spectrometry-Based Proteomic Data Using Free Computational Tools

Published on: August 19, 2025

Disc-Hub: a python package for benchmarking machine learning strategies in DIA-MS identification.

Yiwen Yu¹, Xiaohui Wu¹, Jian Song¹

¹Cancer Institute, Suzhou Medical College, Soochow University, Jiangsu 215123, China.

Bioinformatics Advances

|November 12, 2025

Summary

This summary is machine-generated.

Machine learning is crucial for analyzing data-independent acquisition (DIA) mass spectrometry. A K-fold training strategy with a multilayer perceptron best balances peptide identification depth and false discovery rate (FDR) control in DIA analysis.

More Related Videos

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Mapping Dysfunctional Protein-Protein Interactions in Disease

Mapping Dysfunctional Protein-Protein Interactions in Disease

Published on: October 24, 2025

Related Experiment Videos

Last Updated: Jan 11, 2026

Navigating the Mass Spectrometry-Based Proteomic Data Using Free Computational Tools

Navigating the Mass Spectrometry-Based Proteomic Data Using Free Computational Tools

Published on: August 19, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Mapping Dysfunctional Protein-Protein Interactions in Disease

Mapping Dysfunctional Protein-Protein Interactions in Disease

Published on: October 24, 2025

Area of Science:

Proteomics
Computational Biology
Mass Spectrometry

Background:

Accurate analysis of data-independent acquisition (DIA) mass spectrometry data requires machine learning to differentiate target peptides from decoy peptides.
Various DIA identification engines employ different binary classifiers and training workflows for this task.
A lack of systematic comparison regarding machine learning strategies' impact on identification performance hinders optimal strategy selection and can lead to underfitting or overfitting, compromising false discovery rate (FDR) control.

Purpose of the Study:

To systematically benchmark different machine learning strategies for DIA mass spectrometry data analysis.
To identify the optimal combination of training strategies and classifiers for robust peptide identification and FDR control.
To provide a resource for researchers to select appropriate machine learning configurations for DIA identification algorithms.

Main Methods:

Benchmarking of three distinct training strategies and four different classifiers.
Evaluation performed on representative DIA datasets.
Utilized K-fold training combined with a multilayer perceptron as a key machine learning approach.

Main Results:

The combination of K-fold training and a multilayer perceptron demonstrated the best performance.
This optimal strategy achieved a superior balance between peptide identification depth and effective FDR control.
The study identified specific machine learning configurations that enhance DIA data analysis.

Conclusions:

The optimal machine learning strategy for DIA mass spectrometry involves K-fold training with a multilayer perceptron.
This approach significantly improves the balance between identification depth and FDR control.
The findings guide the development of more effective DIA identification algorithms and reliable FDR control mechanisms.