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.
A computational approach for fast and accurate prediction of MoRFs in protein sequences. MoRFCHiBi combines the outcomes of two SVM models that take advantage of two different kernels with high noise tolerance. The first, SVMS, is designed to extract maximal information from the general contrast in amino acid compositions between MoRFs, their surrounding regions (Flanks), and the remainders of the sequences. The second, SVMT, is used to identify similarities between regions in a query sequence and MoRFs of the training set.
A method for identifying Molecular Recognition Features (MoRFs). Firstly, a masking method is used to calculate the average local conservation scores of residues within a masking-window length in the position-specific scoring matrix (PSSM). Then, the scores below the average are filtered out. Finally, a smoothing method is used to incorporate the features of flanking regions for each residue to prepare the feature sets for prediction.
Predicts linear motifs in a protein sequence based on our neural network which was trained on Short Linear Motif containing proteins. Information about the relative local conservation and the disorder context of the peptide are included in the results.
Predicts the RNA-, DNA-, and protein-binding residues located in the intrinsically disordered regions. DisoRDPbind is implemented using a runtime-efficient multi-layered design that utilizes information extracted from physiochemical properties of amino acids, sequence complexity, putative secondary structure and disorder, and sequence alignment. Its outputs complement predictions of representative methods that were built using structured DNA- and RNA-binding residues. Predictions of disordered protein-binding residues generated by DisoRDPbind are characterized by strong correlations, better predictive performance and higher runtime when compared with the closest ANCHOR method.
Predicts the likelihood of a residue to undergo disorder-to-order transition upon binding to a partner protein. Proteus uses random-forest-based protean predictor. The prediction is based on features that can be calculated using the amino acid sequence alone. This tool compares favourably with existing methods predicting twice as many true positives as the second best method (55% vs. 27%) at a much higher precision on an independent data set. Proteus also shades some light on a possible 'disorder-to-order' transitioning consensus, untangled, yet embedded in the amino acid sequence of IDP, and on a real-life structural modelling of an IDPR (intrinsically disordered proteins containing regions of disorder).