ElliPro is a web-based tool for predicting antibody epitopes in protein antigens. It implements a method based on the geometrical properties of protein structure, using an ellipsoid approximation to determine protrusion indices for residues. The tool allows prediction and visualization of both continuous and discontinuous epitopes. ElliPro was tested on a benchmark dataset of discontinuous epitopes inferred from 3D structures of antibody-protein complexes. It performed the best among six other structure-based methods, achieving an AUC value of 0.732 when the most significant prediction was considered for each protein. The tool is available at http://tools.immuneepitope.org/tools/ElliPro. ElliPro is considered a useful research tool for identifying antibody epitopes in protein antigens. It is based on simple concepts, such as regions protruding from the globular surface of the protein being more available for interaction with an antibody. The tool does not require training and may be applicable for predicting different types of protein-protein interactions. The results suggest that further research on antibody epitopes considering more features that discriminate epitopes from non-epitopes may improve predictions. The tool is available for use and is platform-independent, written in Java. It does not require any additional software or licenses. The authors contributed to the design, programming, and writing of the manuscript. The tool is supported by the National Institutes of Health.ElliPro is a web-based tool for predicting antibody epitopes in protein antigens. It implements a method based on the geometrical properties of protein structure, using an ellipsoid approximation to determine protrusion indices for residues. The tool allows prediction and visualization of both continuous and discontinuous epitopes. ElliPro was tested on a benchmark dataset of discontinuous epitopes inferred from 3D structures of antibody-protein complexes. It performed the best among six other structure-based methods, achieving an AUC value of 0.732 when the most significant prediction was considered for each protein. The tool is available at http://tools.immuneepitope.org/tools/ElliPro. ElliPro is considered a useful research tool for identifying antibody epitopes in protein antigens. It is based on simple concepts, such as regions protruding from the globular surface of the protein being more available for interaction with an antibody. The tool does not require training and may be applicable for predicting different types of protein-protein interactions. The results suggest that further research on antibody epitopes considering more features that discriminate epitopes from non-epitopes may improve predictions. The tool is available for use and is platform-independent, written in Java. It does not require any additional software or licenses. The authors contributed to the design, programming, and writing of the manuscript. The tool is supported by the National Institutes of Health.