Input mode
Automatic, VHH, or VH/VL
Detect paired chains or require one structure mode for every row.
Predict antibody and VHH structures
Predict antibody or VHH coordinates and review residue-level uncertainty across the structural ensemble.
Prepare
Antibody or VHH sequences
Use a protein, annotated-sequence, or comparison Dataset with a heavy/VHH column and an optional paired light-chain column.
- Heavy/VHH sequence for every selected row
- Paired light chain for VH/VL mode
- Up to 100 rows and 500 residues per sequence
Heavy or VHH column
sequencePaired light column
light_chainHow the analysis starts
Choose a Project, open a compatible Dataset, then select the rows you want to analyze. Ubi will open this method with the compatible controls and column mappings ready to review.
Configure the scientific method
These controls appear in the Dataset analysis panel, where values can be checked against the actual input before the run starts.
Numbering
IMGT
Use a consistent coordinate convention for residue uncertainty.
Refinement
OpenMM
Refine predicted coordinates before structure review.
Review results as scientific outputs
Results open with the figures, structures, sequences, and metrics needed to answer the scientific question. Downloadable files remain available for downstream analysis.
How to interpret the result
- Lower predicted coordinate error indicates greater model agreement, not experimental validation.
- Review CDR loops and unusual regions alongside ensemble uncertainty before structure-guided decisions.
- Confirm chain sequences and numbering in the published artifact before downstream modeling.
1
Predicted structures
Open or download PDB coordinates for each successful prediction.
2
Residue predicted error
Review ensemble coordinate-error evidence across each chain.
3
Sequence conservation
Verify that published structures preserve the submitted chains.
Continue your analysis
Use a complementary method on the same Project data.
Method scope and limitations
- This method supports antibody VH/VL and VHH structures, not TCR prediction.
- Predicted coordinates should be interpreted with experimental or higher-confidence structural evidence.
