CRNPRED: a software for accurate prediction of 1D protein structures.
CRNPRED is a program that predicts secondary structures (SS), contact numbers (CN), and residue-wise contact orders (RWCO) of a native protein structure from its amino acid sequence.
The prediction scheme uses an output of PSI-BLAST (sequence profile), and is based on
a novel machine learning technique called Critical Random Networks.
For the methodology, refer to the following paper:
- A.R. Kinjo and K. Nishikawa, Predicting secondary structures, contact numbers, and residue-wise contact orders of native protein structure from amino acid sequence using critical random networks BIOPHYSICS, 1:67-74 (2005) doi:10.2142/biophysics.1.67
The paper describing the software has been published as:
- A.R. Kinjo and K. Nishikawa, CRNPRED: Highly accurate prediction of one-dimensional protein structures by large-scale critical random networks BMC Bioinformatics 7:401 (2006) doi:10.1186/1471-2105-7-401
CRNPRED predicts 3 types of 1D structures: SS, CN, and RWCO. To find out why these 3 types are of interest, refer to
- A.R. Kinjo and K. Nishikawa, Recoverable one-dimensional encoding of three-dimensional protein structures Bioinformatics, 21:2167-2170 (2005) doi:10.1093/bioinformatics/bti330
Prediction Web Server
The web-based prediction service is available at