Overview
This research implementation pretrains a graph neural network and adapts it for retention-time prediction with a smaller target dataset. It provides preprocessing, training and transfer/evaluation scripts rather than a turnkey chromatography-independent predictor.
What can this tool do?
Common uses
- A research implementation of transfer-learning graph neural networks for chromatographic retention-time prediction from molecular structure using small target training datasets.
Scientific fit
Primary function
Machine learning and prediction
Other functions
Metabolite annotation and identification
Data compatibility
Inputs
Molecular structures
Outputs
Statistical results
Input formats
Prepared molecular-structure and measured retention-time datasets
Output formats
Trained/transfer models, predicted retention times and evaluation results
Scope and considerations
Designed for
- A research implementation of transfer-learning graph neural networks for chromatographic retention-time prediction from molecular structure using small target training datasets.
Not designed for
- A universal retention-time scale, raw chromatographic alignment or compound identification based only on predicted time.
Important requirements
- Python, PyTorch, DGL and RDKit with appropriately prepared molecular structures and retention-time training/target data; configure the selected target dataset before transfer learning.
Considerations
- Retention depends on the chromatographic method. Avoid structural or sample leakage between training and test sets, and assess applicability to the target LC conditions.
Access and documentation
Public research code; no explicit repository-wide license was identified. Dataset and model availability must be checked separately before reuse.
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-batch2.md.
Core publications
Resource papers, direct updates and tool-specific methods. Selection policy.
- Retention Time Prediction through Learning from a Small Training Data Set with a Pretrained Graph Neural Network. Analytical Chemistry (2023). doi:10.1021/acs.analchem.3c03177
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 24 reviewed Enveda tools in a separate second batch
View change · Entry at this revision