CPHmodels 1.0 Server

Please note that this is an old version of CPHmodels. The current version can be found at:


Prediction of protein structure

CPHmodels is a collection of databases and methods developed to predict protein structure. The main server, CPHmodels, can be accessed from this page. It performs prediction of protein structure using comparative (homology) modelling.

The other tools are as follows:

A neural network based method to predict contacts between C-alpha atoms from the amino acid sequence (formerly SoWhat).
RedHom A tool to find a subset with low sequence similarity in a database.

Output format Article abstract Databases


Sequence name

Sequence  (only one, in one-letter code)

Not more than 900 amino acids in the input sequence.

The sequences are kept confidential and will be deleted after processing.


For publication of results, please cite:

Protein distance constraints predicted by neural networks and probability density functions.
O. Lund, K. Frimand, J. Gorodkin, H. Bohr, J. Bohr, J. Hansen and S. Brunak.
Protein Engineering: 10:1241-1248, 1997.

View the abstract.

O. Lund et al., unpublished results.


Scientific problems:        Technical problems: