Aims to improve the accuracy of transmembrane helices (TMH) prediction. MemBrain is a prediction method to derive transmembrane inter-helix contacts from amino acid sequences by combining correlated mutations and multiple machine learning classifiers. This method is able to predict residue contacts for the entire transmembrane (TM) protein sequence. It was trained with inter-helix residue pairs and long-range residue pairs of type II and III.
Predicts the exposure or burial of transmembrane residues incorporating the structural specificities of channels. RHYTHM is a web application in which the position-specific matrices were updated using an enlarged data set of input structures. It also integrates the secondary structure prediction tool HMMTOP. After the upload of a single sequence file and the specification of the position specific matrix type, the prediction for tertiary structure contacts is started.
Predicts residue-residue contacts in alpha-helix transmembrane (TM) proteins. TMhhcp is a random forest (RF) algorithm that can be used as a valuable tool for predicting the structural properties of TM proteins and can help to gain useful insights into their structure and function. It also uses the machine learning method, which integrates Position-Specific Scoring Matrix (PSSM), sequence distance, residue covariance, residue conservation, relative residue distance of two helices and helix number to predict helix-helix contacts.
A contact prediction method for α-helical transmembrane proteins, in which evolutionary couplings are combined with a machine learning approach. MemConP achieves a substantially improved accuracy (precision: 56.0%, recall: 17.5%, MCC: 0.288) compared to the use of either machine learning or co-evolution methods alone. The method also achieves 91.4% precision, 42.1% recall and a MCC of 0.490 in predicting helix-helix interactions based on predicted contacts. The approach was trained and rigorously benchmarked by cross-validation and independent testing on up-to-date non-redundant datasets of 90 and 30 experimental three dimensional structures, respectively.
Predicts helix-helix contacts specifically within the transmembrane parts of membrane proteins. TMHcon is a neural-network based approach. It integrates sequence profiles, correlated mutations, protein topology, sequence separation, and predicted scores for lipid-exposure. It also includes predictions by two neural networks, one developed for helix-helix contacts on all transmembrane helix pairs, and the second specifically tailored for the prediction of helix-helix contacts lying on non-neighboring transmembrane helices.
Identifies interactions from predicted residue contact maps. HHConPred is a method that permits a reliable prediction of helix-helix interactions in both soluble and membrane proteins given the noisy 2D contact maps generated from correlated mutations. This application was developed using the contact maps predicted from CCMpred. It also could be extended to membrane proteins with at least comparable performance.
Predicts transmembrane (TM) interhelical residue contacts. TMhit is a method based on a hierarchical architecture with two levels via support vector machines (SVMs) classifiers. It estimates the propensities of residues or pairs in contact and incorporates them as input features for prediction. It could also be applied to select potentially interacting peptides and key residues for improving the binding specificity by protein engineering.
0 - 0 of 0
0 - 0 of 0