Difference between revisions of "Jpred"

From Bioinformatikpedia
(Jnet)
Line 21: Line 21:
 
|}
 
|}
   
  +
Jnet uses two neural networks for its prediction.
<<under construction>>
 
  +
The first network is feeded with a window of 17 residues over each amino acid in the alignment plus a conservation number.
  +
It uses a hidden layer of nine nodes and has three output nodes, one for each secondary structure element.
   
  +
The second network is feeded with a window of 19 residues (the result of first network) plus the conservation number.
Jnet uses neural networks for its prediction.
 
  +
It has a hidden layer with nine nodes and has three output nodes.
first, input: window of 17 residues over each amino acid in the alignment plus the
 
addition of a conservation number; nine hidden nodes; three output nodes
 
 
second, input: window of 19 residues (result of first network) plus the conservation
 
number; nine hidden nodes; three output nodes
 
 
input: multiple sequence alignment
 
output: for each amino-acid three scores for three secondary structure elements
 
(Helix, Sheet, Coil)
 

Revision as of 21:21, 6 June 2011

Jpred

Basic Information

Jpred itself is just a Protein Secondary Structure Prediction server, which exists since 1998 in different versions. JPred predicts Solvent Accessibility and Coiled-coil regions with the Lupas method and the secondary structure with the Jnet algorithm.

Jnet

Jnet
Author James A. Cuff, Geoffrey J. Barton
Year 2000
Reference PubMed 10861942
ML Method Neural Network

Jnet uses two neural networks for its prediction. The first network is feeded with a window of 17 residues over each amino acid in the alignment plus a conservation number. It uses a hidden layer of nine nodes and has three output nodes, one for each secondary structure element.

The second network is feeded with a window of 19 residues (the result of first network) plus the conservation number. It has a hidden layer with nine nodes and has three output nodes.