Image Title 2

Propensity-based Prediction

One of the major advatages of propensity based models over models based on machine learning techniques that their output is easy to understand. These methods provide propensity at residue and at turn level. In this study, propensity score of residues, dipeptides etc. calculated on large dataset contain ~18000 PDB chains. Click here to »Submit »

Image Title 1

Beta Turn in proteins

Beta-turns are the most common type of non-repetitive structures, and constitute on average 25% of the residues in all protein chains. In a beta turn, a tight loop is formed when the carbonyl oxygen of one residue forms a hydrogen bond with the amide proton of an amino acid three residues down the chain. This hydrogen bond stabilizes the beta bend structure. A beta turn can reverse the direction of its peptide chain.

Image Title 2

Prediction of Beta Turn

In the past numerous methods were developed to predict the beta turns. But all of this method were trained to predict residue level prediction instead of four residue level. Since, a beta turn is composed of four consecutive amno acids. Using this simple approach we have achieved good prediction accuracy and realistic prediction of beta turns. To predict beta turns in your protein click »Submit »

Image Title 2

Designing of Beta Turn

For the first time, we have developed a module thats helps user in understanding the positional preference of pairs of amino acids. First, user sequence is mapped and various propensity score are shown for all possible tetrapeptide. Second, the module performs all possible mutation in a tetrapeptide, either to increase or decrease its beta turn formation probability. Click here to »Submit »

Image Title 2

Prediction of Beta Turn Type

In the past numerous methods were developed to predict the beta turn types. Using the turn level approach we have significantly improved the prediction accuracy of beta turn types. To predict beta turns types in your protein click »Submit »

Image Title 3

Algorithm

We have developed a algorithm that predcit complete beta turn, earlier algorithm predict the residue that are present in beta turn. They can predict a residue to be beta turn residue, even its neighbouring residue are non beta turn. Our algorithm has overcome all these limitation and can predict only four consecutive beta turn residues.

More »

Propensity-based Beta Turn Prediction
(Sequence Submission Form)


This page allow users to predict beta turns in their protein sequences using propensity based model/score. User can upload multiple protein sequence in FASTA format. The server predict whole beta turn in a protein sequence. Click here for help

Paste protein sequences in Fasta format       []         
OR Upload protein sequence file in fasta format :

Select prediction model Threshold (scale = 1-9)
 Residue propensity (position-wise)1    
 Propensity of pair of residues2    
 Tri-peptide propensity3    
 Propensity of Tetra-peptides4    
 Hybrid (combination of propensities)5    

   


EXPLAINATION:

1. Position wise residue propensity: Position wise (at position P1, P2, P3, P4) propensity values of all the four residues of a pattern is averaged. If this value is above the threshold, it is predicted as betaturn, else non-turn.

2. Pair wise residue propensity: Pair wise (at position P1-2, P1-3, P1-4, P2-3, P2-4, P3-4) propensity values of all the residue pairs of a pattern is averaged. If this value is above the threshold, it is predicted as betaturn else non-turn.

3. Tri-peptide propensity: In this method, tri-peptide (at position P1-2-3 and P2-3-4) propensity values are averaged and used for predicting betaturns and non-turns.

4. Tetra-peptide propensity: In this method, tetra-peptide propensity score is used for predicting betaturns and non-turns based on its value above or below threshold.

5. Hybrid Score: In this method, all the propensity scores are added (Position wise + Pair wise + Tri-peptide + Tetra-peptide) and used for predicting betaturns and non-turns.