From: Antibody-protein interactions: benchmark datasets and prediction tools evaluation
Server name | Method type | Training dataset | Reference |
---|---|---|---|
CEP (Conformational Epitope Prediction) | Discontinuous epitope prediction based on residue solvent accessibility and spatial distribution. | No training set. | [48] |
DiscoTope | Discontinuous epitope prediction based on amino acid statistics, residue solvent accessibility and spatial distribution. | 75 structures of antibody-antigen complexes. | [49] |
ProMate | Protein-protein binding interface prediction based on significant structural and sequence interface properties. | Manually curated; 57 protein involved in heterodimeric transient interactions (excluding antigen-antibody complexes). | [55] |
PIER (Protein IntErface Recognition) | Protein-protein binding interface prediction based on local statistical properties of the protein surface derived at the level of atomic groups. | 490 homodimeric, 62 heterodimeric and 196 transient interfaces (excluding antigen-antibody complexes). | [54] |
PPI-PRED (Protein-Protein Interface Prediction) | Protein-protein binding interface prediction based on significant structural and sequence interface properties. | Manually curated; 180 proteins from 149 complexes both obligate (114) and transient (66). | [53] |
ConSurf | Mapping of phylogenetic information (sequence conservation grades) on to the surface of proteins with known 3D structure. | No training set. | [56] |
ClusPro (DOT program) | Rigid-body protein-protein docking based on the Fast-Fourier Transform correlation approach. | No training set. | [50] [51] |
PatchDock | Rigid-body protein-protein docking based on local shape feature matching. | No training set. | [52] |