Overview
SpecTUS translates GC-electron-ionization mass spectra into candidate SMILES structures using a transformer pretrained on synthetic spectra and fine-tuned on experimental spectra. The repository provides research code, synthetic resources and a pretraining checkpoint.
What can this tool do?
Common uses
- SpecTUS translates GC-electron-ionization mass spectra into candidate SMILES structures using a transformer pretrained on synthetic spectra and fine-tuned on experimental spectra.
Scientific fit
Primary function
Metabolite annotation and identification
Other functions
Machine learning and prediction
Data compatibility
Inputs
Mass spectra
Outputs
Molecular structures
Input formats
EI mass spectra, including documented MSP inference inputs
Output formats
Ranked candidate molecular structures as SMILES
Scope and considerations
Designed for
- SpecTUS translates GC-electron-ionization mass spectra into candidate SMILES structures using a transformer pretrained on synthetic spectra and fine-tuned on experimental spectra.
Not designed for
- ESI tandem-spectrum identification or assured identification of unknowns from a generated candidate alone.
Important requirements
- The documented conda environment and trained checkpoint; the final NIST20-trained model is not distributed, so reproducing it requires licensed NIST20 data and training.
Considerations
- Public pretraining resources and a hosted demonstration are distinct from access to the final trained model. Assess candidate ranking and domain coverage against suitable reference data.
Access and documentation
MIT source code. The final NIST20-trained model is withheld because of proprietary training data; public synthetic data/pretraining checkpoints and hosted demo have separate terms and availability.
License: MIT
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.
- SpecTUS: Spectral Translator for Unknown Structures Annotation from EI-MS Spectra. Analytical Chemistry (2026). doi:10.1021/acs.analchem.6c02423
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