Overview
SigmaCCS uses molecular graphs with three-dimensional conformations and adduct information to predict CCS for candidate annotation filtering.
What can this tool do?
Common uses
- Predict collision cross sections from molecular structures and ion adducts.
Scientific fit
Primary function
Metabolite annotation and identification
Data compatibility
Inputs
Molecular structures
Outputs
Human-readable report
Input formats
SMILES and adduct records plus model parameters and trained weights
Output formats
Predicted CCS values for candidate ions
Scope and considerations
Designed for
- SigmaCCS uses molecular graphs with three-dimensional conformations and adduct information to predict CCS for candidate annotation filtering.
Not designed for
- Instrument CCS calibration or confirmation of a molecular identity from CCS alone.
Important requirements
- Python, RDKit, TensorFlow and Spektral; molecular conformer generation and the supplied model/parameter files.
Considerations
- The documented large predicted collection covers [M+H]+, [M+Na]+ and [M-H]-; do not assume support for arbitrary adducts.
- Check applicability to the candidate chemistry and measurement conditions before using predicted CCS as a filter.
Access and documentation
MIT code license checked. Separately distributed predicted datasets and model resources may carry their own terms; no execution test.
License: MIT
Evidence and review
Enveda intake checked against official documentation, license information and primary DOI/title/year on 2026-10-22. Editorial review only; no execution or independent benchmark.
Core publications
Resource papers, direct updates and tool-specific methods. Selection policy.
- Highly accurate and large-scale collision cross sections prediction with graph neural networks. Communications Chemistry (2023). doi:10.1038/s42004-023-00939-w
Related tools
Entry history
Changes to this catalogue entry, not the tool's software release history. Acceptance and editorial review are separate.
- 2026-10-23 · First committed entry
Add ten reviewed Enveda tools with input and applicability limits
View change · Entry at this revision