Help Getting Started

APPTEST is a neural network model trained using experimentally obtained peptide structures. The peptide sequences that the model was trained and validated on are available for download here.

Predicting Peptide Tertiary Structure

To predict the tertiary structure of a peptide, enter its sequence in the text box on the main page in 1-letter format.

1-letter peptide amino acid sequence, in single letter format, is accepted. Only the canonical 20 amino acids are supported, non-natural amino acids are not currently supported. Then press "Run Prediction"

The following is an example of a valid input for the prediction of a single peptide:

FLPILASLAAKFGPKLFCLVTKKC

Simulated Annealing and Molecular Dynamics

If you wish to use the webserver to create a model structure, you must select a simulated annealing and molecular dynamics method. Currently, only XPLOR-NIH is available due to licensing.

You may run the prediction without conducting simulated annealing and molecular dynamics if you wish to do so later using your locally installed copy of CYANA or XPLOR-NIH. Simply leave the simulated annealing and molecular dynamics option as none.

Predicting tertiary structure of cyclic peptides

If your peptide has disulfide bonds, you should specify those under Disulfide Bonds. Indicate the positions of the cysteine residues involved in bonds, separated by a hyphen. Multiple disulfide bond definitions can be separated by a comma. See below for example of valid disulfide bond definition.

1-7,18-24