Send to

Choose Destination
Bioinformatics. 2019 May 1;35(9):1591-1593. doi: 10.1093/bioinformatics/bty822.

AbPredict 2: a server for accurate and unstrained structure prediction of antibody variable domains.

Author information

Department of Biomolecular Sciences, Weizmann Institute of Science, Rehovot, Israel.
Institute for Molecular Bioscience, The University of Queensland, St. Lucia, Australia.
CSIRO Synthetic Biology Future Science Platform, Weizmann Institute of Science, Rehovot, Israel.
Bioinformatics & Biological Computing Unit, Weizmann Institute of Science, Rehovot, Israel.



Methods for antibody structure prediction rely on sequence homology to experimentally determined structures. Resulting models may be accurate but are often stereochemically strained, limiting their usefulness in modeling and design workflows. We present the AbPredict 2 web-server, which instead of using sequence homology, conducts a Monte Carlo-based search for low-energy combinations of backbone conformations to yield accurate and unstrained antibody structures.


We introduce several important improvements over the previous AbPredict implementation: (i) backbones and sidechains are now modeled using ideal bond lengths and angles, substantially reducing stereochemical strain, (ii) sampling of the rigid-body orientation at the light-heavy chain interface is improved, increasing model accuracy and (iii) runtime is reduced 20-fold without compromising accuracy, enabling the implementation of AbPredict 2 as a fully automated web-server ( Accurate and unstrained antibody model structures may in some cases obviate the need for experimental structures in antibody optimization workflows.

Supplemental Content

Full text links

Icon for Silverchair Information Systems Icon for PubMed Central
Loading ...
Support Center