The Protein Continuum Secondary Structure Predictor accepts amino acid sequences, presented in the FASTA format, and predicts the continuum secondary structure of each residue in the sequence.

The continuum secondary structure of a residue is a probability distribution over the possible secondary structure classes. The predicted continuum secondary structure is based on high-quality NMR structures, reflecting a variance of structural assignment.

Paste or upload your sequence below.

 Upload FASTA file:

 

OR

  
 Paste FASTA sequence here:
 Email address:

DATA

The protein continuum secondary structure predictor is trained on high-quality NMR structures, inspired by DSSPcont.

The training data set consists of 174 structures taken from the data set published by Andersen et al (Structure, 10:175-185, 2002). The 174-sequence set is made available with

secondary structure probabilities.

The test data consists of another 286 structures added to PDB post-2002. The 286-sequence set is made available with

secondary structure probabilities.

Structures in the 174-set and the 286-set share no more than 20% sequence similarity.

The predictor also calculates the entropy of the predicted continuum secondary structure to indicate regions prone to undergo conformational change.

A 171-sequence conformational variability data set was extracted using the Database of Macromolecular Movements and used to evaluate on how well the entropy identifies sequence regions undergoing conformational change. Each of the 171 sequences has at least two different observed 8-class secondary structures. All homologues were removed (no pairs within the 171-set and between the 171- and 174-set described above had more than 20% sequence identity). PDB identifiers, sequence data (with flexible residues noted with '1') for the 171 sequences can be found here.

REFERENCES

Predictor development and evaluation is reported in

Bodén, M. Yuan, Z. and Bailey, T. L. Prediction of protein continuum secondary structure with probabilistic models based on NMR solved structures. BMC Bioinformatics. 7:68, 2006.

Bodén, M. and Bailey, T. L. Identifying sequence regions undergoing conformational change via predicted continuum secondary structure. Bioinformatics. In press. doi:10.1093/bioinformatics/btl198. Supplementary analysis.

The web service was implemented by Johnson Shih and Mikael Bodén

Contact: mikael@itee.uq.edu.au