This server offers a protein secondary structure prediction from its primary sequence and a three dimensional model. An neural network was trained with low resolution tertiary structure, an amino acid property profile, and the position based scoring matrix of a blast run (as used by David Jones, J. Biol. Mol., 1999, 292(2) 195-202). It achieves a three state prediction accuracy between 75% and 95% depending on the quality of the structural model.

Files are limited to 4MB in size; if you are a Meiler-Lab member, please login to upload files up to 16MB