Given two protein sequences, the structure-based interaction prediction technique threads these two sequences to all the protein complexes in the PDB and then chooses the best potential match. Based on this match, the method generates alignment scores, z-scores, and an interfacial energy for the sequence pair. Logistic regression is then used to evaluate whether a set of scores corresponds to an interaction or not. The algorithm is also extended to find all potential partners given a single protein sequence. Further details about the method are described here.
Pred_PPI is a web-based system that serves for predicting PPIs from different organisms. This server is freely available to any researcher wishing to use it for non-commercial purposes. Based on auto covariance (AC) and support vector machine (SVM), this tool is capable of predicting PPIs for any target protein pair only using their primary sequences, and assigning an interaction probability to each SVM prediction as well. So the user can use this tool to predict novel PPIs with high confidence.
Through the calculation of secondary structure, hydrogen bonding and van der Waals contributions, catRAPID is able predict protein-RNA interaction propensities with great accuracy (up to 89% on the ncRNA-protein interaction database, NPinter).
"For a given protein sequence or structure query, IBIS reports protein-protein, protein-small molecule, protein nucleic acids and protein-ion interactions observed in experimentally-determined structural biological assemblies. IBIS also infers/predicts interacting partners and binding sites by homology, by inspecting the protein complexes formed by close homologs of a given query. To ensure biological relevance of inferred binding sites, the IBIS algorithm clusters binding sites formed by homologs based on binding site sequence and structure conservation."