Overview
FIDDLE predicts and rescores molecular-formula candidates from tandem mass spectra using deep learning. Its command-line and Python workflows provide instrument-specific inference and ranked formula outputs, with research training/evaluation scripts separately available.
What can this tool do?
Common uses
- FIDDLE predicts and rescores molecular-formula candidates from tandem mass spectra using deep learning.
Scientific fit
Primary function
Metabolite annotation and identification
Other functions
Machine learning and prediction
Data compatibility
Inputs
Mass spectra
Outputs
Compound list or annotations
Input formats
MGF spectra with required precursor and collision-energy metadata
Output formats
CSV ranked formula candidates and scores, plus optional evaluation
Scope and considerations
Designed for
- FIDDLE predicts and rescores molecular-formula candidates from tandem mass spectra using deep learning.
Not designed for
- Full molecular-structure identification or guaranteed formula recovery outside the supported instrument and chemical domains.
Important requirements
- The inference package and downloaded models, plus MGF spectra containing the required title, precursor mass/type and collision-energy metadata; select the appropriate instrument model.
Considerations
- Formula ranking and rescoring depend on spectral metadata and model selection. Optional BUDDY/SIRIUS comparisons add separate software and account requirements.
Access and documentation
Apache-2.0 source distribution. External datasets, dependent packages and any hosted routes retain their own terms; software operation was not tested.
License: Apache-2.0
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.
- FIDDLE: a deep learning method for chemical formulas prediction from tandem mass spectra. Nature Communications (2025). doi:10.1038/s41467-025-66060-9
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