Antibody & Biologics · Oxford Protein Informatics Group
ImmuneBuilder
Fast structure prediction for antibodies, nanobodies, and T-cell receptors across full repertoires.
What ImmuneBuilder is
ImmuneBuilder is a computational suite developed by the Oxford Protein Informatics Group for predicting the three-dimensional structures of immune molecules from their protein sequences. It provides sub-second predictions for antibodies, nanobodies, and T-cell receptors (TCRs).
The tool comprises three dedicated modules: ABodyBuilder2, NanoBodyBuilder2, and TCRBuilder2. Its execution speed enables structural analysis across entire immune repertoires rather than restricting investigations to small selections of candidate leads.
Key facts
- Version
- 1.0
- Domain
- Antibody
- Task
- Structure prediction
- Input modality
- Protein sequence
- GPU memory
- 8 GB
What you can use it for
- Repertoire-Scale Antibody Modelling
- Generate all-atom coordinates across full antibody repertoires at sub-second speeds per sequence.
- Nanobody Structure Prediction
- Model the three-dimensional structures of single-domain antibodies using the NanoBodyBuilder2 component.
- T-Cell Receptor Modelling
- Predict all-atom coordinates for T-cell receptor sequences using TCRBuilder2.
- Residue Confidence Estimation
- Assess local model reliability across predicted structures using per-residue pLDDT scores.
Run it here
No installation and no GPU of your own: fill in the inputs and it runs on our servers. Results stay in your browser unless you sign in.
Runs on On-demand GPU
Runs on our servers with on-demand compute. A first run needs time to load the model; active capacity can be reused and scales down when idle.Run this model
ImmuneBuilder
Strengths and limits
Good at
- Completes all-atom structure predictions in sub-second runtimes.
- Scales sufficiently to process entire immune repertoires rather than a small number of candidate sequences.
- Provides calibrated per-residue confidence scores to evaluate structural reliability.
- Covers antibodies, nanobodies, and TCRs within a single integrated framework.
Watch out for
- Model regions scoring 70 or lower on the pLDDT metric are generally not reliable.
- Requires hardware with at least 8 GB of GPU memory.
Inputs and outputs
You provide
Heavy chain / nanobody
Single-letter amino acid code. Whitespace and FASTA headers are stripped automatically.
Light chainoptional
Single-letter amino acid code. Whitespace and FASTA headers are stripped automatically.
Builderoptional
You get back
All-atom coordinates in PDB format, viewable and downloadable.
pLDDT score per residue (0–100). Above 70 is generally reliable.
Licence
Commercial use permitted · BSD-3-Clause
The BSD-3-Clause licence allows use in commercial research and products.
Questions
Can I use ImmuneBuilder commercially?
Commercial use permitted. The BSD-3-Clause licence allows use in commercial research and products.
How do I run ImmuneBuilder without installing anything?
Use the form under “Run it here” on this page: fill in the inputs and press Run model. It runs on our servers on 1× A100 16GB, typically in 900ms, and a run costs about 14 credits. Visitors without an account get 1,000 credits a month.
Which specific models are included in the ImmuneBuilder suite?
The suite contains three models: ABodyBuilder2 for antibodies, NanoBodyBuilder2 for nanobodies, and TCRBuilder2 for T-cell receptors.
What inputs does the suite require?
It requires the heavy chain or nanobody amino acid sequence, the light chain sequence where applicable, and the selection of the appropriate builder.
What outputs are provided after prediction?
ImmuneBuilder returns all-atom structural coordinates in PDB format along with a per-residue pLDDT confidence vector.
How are the pLDDT confidence scores interpreted?
The pLDDT score ranges from 0 to 100, where scores above 70 are considered generally reliable.
Written from ImmuneBuilder's own documentation. Statements citing a figure that does not appear there are removed before publication. Licence and running details come from our registry.