Overview
MS-BART models molecular representations and mass-spectral information with a unified language-model workflow for structure elucidation. Its research pipeline includes molecular pretraining, spectral fine-tuning, chemical-feedback alignment and candidate generation.
What can this tool do?
Common uses
- MS-BART models molecular representations and mass-spectral information with a unified language-model workflow for structure elucidation.
Scientific fit
Primary function
Metabolite annotation and identification
Other functions
Machine learning and prediction
Data compatibility
Inputs
Mass spectra
Outputs
Molecular structures
Input formats
Prepared spectral/fingerprint TSV data and module-specific MGF inputs
Output formats
Generated molecular candidates and training/evaluation artifacts
Scope and considerations
Designed for
- MS-BART models molecular representations and mass-spectral information with a unified language-model workflow for structure elucidation.
Not designed for
- A turnkey raw-MS identification application or guaranteed correct structures for spectra outside the model domain.
Important requirements
- The documented Python 3.9 environment, downloaded checkpoints/data and fingerprint preprocessing resources; review configuration paths and evaluation-script settings before use.
Considerations
- README documents path and beam-variable issues in evaluation scripts. Preserve evaluation splits and distinguish predicted fingerprints and generated structures from experimental confirmation.
Access and documentation
Public research code and separately hosted weights/data; no repository-wide license grant was established from reviewed metadata. Consult artifact and dependency terms separately.
Evidence and review
Enveda intake rechecked against official repository documentation, package/license metadata and primary publication identity on 2026-10-27. Editorial source review only; no software execution or independent benchmark. See docs/enveda-expansion-review-2026-10-27-batch3.md.
Core publications
Resource papers, direct updates and tool-specific methods. Selection policy.
- Han et al. MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation. arXiv:2510.20615 (2025). Authors identify the associated conference as NeurIPS 2025. doi:10.48550/arXiv.2510.20615
Related tools
Entry history
Changes to this catalogue entry, not the tool's software release history. Acceptance and editorial review are separate.
- 2026-10-27 · First committed entry
Add 45 source-reviewed Enveda tool entries in third expansion batch
View change · Entry at this revision