SPRING is a template-base algorithm for protein-protein complex structure prediction. The pipeline first threads one chain of the protein complex through the PDB library with the binding parters retrieved from the original oligomer entries. The complex models for the query are then deduced from the template binding partner associations through a pre-calculated look-up table. The model of the best orientation is finally selected by the SPRING-score that is a combination of threading Z-score, interface contacts, and TM-align match between monomer-to-dimer templates.
The output of the SPRING server include (An example of the SPRING output):