Structure prediction · Antibody design

ImmuneBuilder

(Work in Progress)

Deep-Learning models for predicting the structures of immune proteins.

A set of deep learning models trained to accurately predict the structure of antibodies (ABodyBuilder2), nanobodies (NanoBodyBuilder2) and T-Cell receptors (TCRBuilder2). By predicting an ensemble of structures, ImmuneBuilder also gives an error estimate for every residue in its final prediction.

Home page ↗ Paper ↗ Source code ↗ License ↗

No jobs before this; it will run immediately.

Not logged in. Register an account to keep track of your jobs and results, and add presets and bookmarks. Email results to this address when complete:

Ready

Job name

Heavy-chain sequence Variable domain only; constant domains are not modelled.

Light-chain sequence

VHH sequence

TCR alpha-chain sequence

TCR beta-chain sequence

Numbering scheme How the residues of the returned structure are numbered.

CPU threads for refinement 0 refines on the GPU; any other value forces OpenMM onto that many CPU threads.

Skip the strained-bond check Slightly faster, at the risk of an occasional unphysical side chain.

Use the original TCRBuilder2 weights Off by default, which uses the newer TCRBuilder2+ weights.

Ready