The Antibody Prediction Toolbox

Welcome to SAbPred

SAbPred is a collection of computational tools that make predictions about the properties of antibodies, focusing on their structures. Antibody informatics tools can help improve our understanding of immune responses to disease and aid in the design and engineering of therapeutic molecules.

Our tools can be used to perform a variety of tasks:

The SAbPred tools were developed by the Oxford Protein Informatics Group (OPIG).

Our structural antibody database, which collates and consistently annotates all antibody structures found in the PDB, can be found at our SAbDab site.

Modelling Tools


Generate Fv homology models annotated with their estimated accuracy and sequence liabilities.


Antibody-specific prediction of side chain conformations.


Hybrid knowledge-based/ab initio prediction of loop structures, with a version parameterised for H3 modelling.


Knowledge-based loop prediction software (software download only)

Other Tools


Classify and number antibody and T-cell receptor amino-acid variable domain sequences.

Antibody i-Patch

Paratope prediction - annotate the antibody residues most likely to be in contact with the antigen.


Identify the epitope region on the antigen, given the structures of the antibody and the antigen.


Sequence-based antibody canonical loop structure annotation.


The Therapeutic Antibody Profiler - compare your antibody to known therapeutics to predict its developability.


Calculate the VH-VL orientation angles for an antibody structure (software download only).

SAbPred paper: Dunbar, J. et al (2016). Nucleic Acids Res. 44. W474-W478 [link]