rewire.it
model · family

DreaMS

DreaMS learns molecular representations from tandem mass spectra for downstream interpretation tasks.

0 evaluations · 0 metric rows

At a glance

Explanatory profile: source reviewed · Automated source review, 2026-09-16. This does not change the review status of its results.

Inputs, outputs and configuration
PropertyDescription and evidence
Training resourceGeMS unannotated MS/MS spectrapluskal-lab/DreaMS official source · README.md: introduction and What can I do with DreaMS?
Model typeNot extracted or verified for this record.
Known versionsNot extracted or verified for this record.
Context limitsNot extracted or verified for this record.
AccessNot extracted or verified for this record.
Code licenceNot extracted or verified for this record.
Weights licenceNot extracted or verified for this record.

How it works

Conceptual procedure

Schematic of the documented input, computation and output; not an executable configuration.

Conceptual procedureMS/MS spectrum. Then: Spectral preprocessing. Then: DreaMS transformer. Then: Spectrum embedding. Then: Task head or similarityMS/MS spectrumSpectral preprocessingDreaMS transformerSpectrum embeddingTask head or similarity
Read the diagram as text
  1. MS/MS spectrum
  2. Spectral preprocessing
  3. DreaMS transformer
  4. Spectrum embedding
  5. Task head or similarity
pluskal-lab/DreaMS official source · README.md: introduction and What can I do with DreaMS?

A transformer is pretrained on unannotated spectra using masked spectral peaks and chromatographic retention ordering. Representations feed task-specific prediction or similarity workflows.

pluskal-lab/DreaMS official source · README.md: introduction and What can I do with DreaMS?

Benchmarks and results

Release 2026-09-16-d74d282221a9 · 0 evaluations · 0 metric rows. Different protocols are not a single leaderboard.

No evaluations linked in this release.

Strengths and limitations

Strengths supported by sources

  • The project provides representations, spectra resources and downstream analysis workflows.pluskal-lab/DreaMS official source · README.md: introduction and What can I do with DreaMS?

Limitations and conditions

  • An embedding or similarity score is not a definitive chemical identification; the candidate set and evaluation split remain essential.pluskal-lab/DreaMS official source · README.md: introduction and What can I do with DreaMS?
Profile review details

Primary project documentation or paper inspected for the explanatory claims and cited locations. Reviewed coverage concerns this narrative, not complete metadata, independent reproduction or a performance ranking.

Stable record: discovery-model-dreams

Applicable tests and references

Applicability is distinct from a completed evaluation.

Sources and history

Release 2026-09-16-d74d282221a9 · Record review: discovered

Download this release
Technical metadata and extraction receipts

Stable ID: discovery-model-dreams

areas
metabolomics
access
official_source_linked
benchmark applicability
candidate; not evidence of a reported evaluation
candidate benchmark ids
discovery-benchmark-massspecgym
entity level
family
missing metadata
checkpoint: unextracted; code licence: unextracted; parameters: unextracted; training cutoff: unextracted; training data: unextracted; version: unextracted; weights licence: unextracted
reported name
DreaMS
version
Not reported
Related records

Suggest a correction