Metabolomics Navigator Tools, strategies & workflow guidance for metabolomics

Metabolite annotation and identification

PeakDecoder

Use machine learning to support metabolite identification and error-rate estimation in multidimensional LC-IM-MS-DIA data.

LC-MSUntargeted metabolomicsMetabolite profilingCommand lineOpen source
Access toolSuggest an update

Overview

PeakDecoder is a workflow for metabolite annotation and profiling in liquid-chromatography, ion-mobility and data-independent-acquisition mass spectrometry. It uses precursor and fragment-ion co-elution and co-mobility information together with machine learning to score candidate metabolite assignments and estimate false-discovery rates.

What can this tool do?

Identification-confidence assessmentMS/MS processing

Common uses

  • Score metabolite identifications in LC-IM-MS-DIA datasets using co-elution and co-mobility information.
  • Estimate false-discovery-rate thresholds for candidate metabolite identifications.

Scientific fit

Primary function

Metabolite annotation and identification

Other functions

Machine learning and prediction, Quality control and filtering

Analysis types

Untargeted metabolomics, Metabolite profiling

MS level

MS1, MS/MS

Acquisition

Data-independent acquisition (DIA)

Ion mobility

Ion mobility required

Data compatibility

Inputs

Feature or peak table, Mass spectra

Outputs

Compound list or annotations, Statistical results

Input formats

CSV or TSV, MSP, Other, MS-DIAL peak lists and Skyline reports

Output formats

CSV or TSV, Other, PeakDecoder scores and FDR thresholds

Scope and considerations

Designed for

  • Multidimensional LC-IM-MS-DIA metabolite-identification workflows with precursor and fragment-ion traces.

Not designed for

  • General-purpose preprocessing of arbitrary LC-MS datasets or de novo structure elucidation.

Important requirements

  • Upstream feature and fragment-ion processing plus targeted extraction of precursor and fragment traces.

Considerations

  • Model performance depends on the training data and the quality of chromatographic and ion-mobility measurements.

Access and documentation

Primary access

Source code, example data and workflow instructions are publicly available in the project repository.

License: BSD-2-Clause

Evidence and review

Added from the 2026 computational-metabolomics review population and Springer methods coverage; checked against the official PeakDecoder repository and primary publication on 10 September 2026.

Core publications

Resource papers, direct updates and tool-specific methods. Selection policy.

  1. Bilbao A, et al. PeakDecoder enables machine learning-based metabolite annotation and accurate profiling in multidimensional mass spectrometry measurements. Nature Communications (2023). doi:10.1038/s41467-023-37031-9

Related tools

BAMSimilar function · BAM generates and ranks structural candidates for suspect metabolites by applying biotransformation rules to known anchor structures.BUDDY / msbuddySimilar function · Generate and rank molecular formula annotations for small-molecule mass-spectrometry queries.CANOPUSSimilar function · A SIRIUS-integrated machine-learning method and webservice for predicting compound classes directly from high-resolution MS/MS data without requiring an exact database structure match.CFM-IDSimilar function · Predict tandem mass spectra, annotate fragments and rank candidate structures for small molecules.

Entry history

Changes to this catalogue entry, not the tool's software release history. Acceptance and editorial review are separate.

  1. 2026-09-10 · Entry update

    Complete PeakDecoder editorial fields

    View change · Entry at this revision
  2. 2026-09-10 · First committed entry

    Add PeakDecoder annotation entry

    View change · Entry at this revision

Full GitHub history