Version 1.0
Updated on 5/25/2007
Contact:
George Karypis
karypis@cs.umn.edu
You may want to try our new
MONSTER
server that besides YASSPP-based secondary structure prediction also provides predictions for other structural and functional properties of a protein's residues.
Name:
A name by which you can easily identify this sequence.
Sequence:
The amino acid sequence whose secondary structure will like to predict.
Valid amino acid codes:
ARNDCQEGHILKMFPSTWYVBZX
.
Spaces in the sequence are not significant.
Email:
A valid email address to email back the prediction results.
Advanced
Settings:
Training Set
Input Coding Scheme
PSI-Blast DB
Astral25 Family
Astral25 Superfamily
PB396
PB513
PSSM+BLOSUM62
PSSM
NCBI nr
Swissprot
Selects among the different pre-trained YASSPP models. Reasonable defaults have already being selected, but you can always experiment with the different choices.
Reference:
Karypis G. "YASSPP: Better kernels and coding schemes lead to improvements in SVM-based secondary structure prediction".
Proteins: Structure, Function, and Bioinformatics, Vol 64, Issue 3, pp. 575-586, 2006.