Protein-protein interaction site detection software tools | Structure data analysis
The identification of protein-protein interaction sites is an essential intermediate step for mutant design and the prediction of protein networks. In recent years a significant number of methods have been developed to predict these interface residues and here we review the current status of the field.
Provides a suite of methods important for the prediction of protein structural and functional features. predictProtein is a web server that incorporates over 30 tools. This software searches up-to-date public sequence databases, creates alignments, and predicts aspects of protein structure and function. It can help when little is known about the protein in question. For medium-to-high throughput analyses, downloadable software packages and the PredictProtein Machine Image (PPMI) are available.
The server is designed for protein Molecular Recognition Feature (MoRF) prediction. MoRFpred utilizes a novel design in which annotations generated by sequence alignment are fused with predictions generated by a Support Vector Machine (SVM), which uses a custom designed set of sequence-derived features. The features provide information about evolutionary profiles, selected physiochemical properties of amino acids, and predicted disorder, solvent accessibility and B-factors.
Allows users to score protein-protein docking model. iScore furnishes solution for categorizing protein-protein interfaces using a support vector machine approach on graph kernels. This program includes two binaries that (1) train a model using a training set and (2) use this model to determine the near-native character of unknown conformations.
Enables accurate identification of binding Hot-Spots in protein-protein complexes with minimal input requirements. SpotOn is an easy to use and publicly accessible web server that helps to classify interfacial residues as Hot-Spots (HS) and Null-Spots (NS). This online method is useful to experts in the feld of computational structural biology as well as less computationally trained researchers.
Identifies RNA binding sites and characterizes DNA-binding protein specificity. DeepBind utilizes a set of sequences and an experimentally determined binding score for each sequence. This software is built on deep learning, a scalable and modular pattern discovery method and doesn’t need common application-specific heuristics like seed finding. It can discover new patterns even when the locations of patterns within sequences are not known.
An algorithm for the prediction of protein-protein interface residues. CPORT combines six interface prediction methods into a consensus predictor. CPORT predictions can be used as active and passive residues in HADDOCK, using the prediction interface.
A consensus neural network method for predicting protein-protein interaction sites. Given the structure of a protein, cons-PPISP will predict the residues that will likely form the binding site for another protein. The inputs to the neural network include position-specific sequence profiles and solvent accessibilities of each residue and its spatial neighbors. The neural network is trained on known structures of protein-protein complexes.