Difference between revisions of "SEA"

From DISI
Jump to: navigation, search
m (1 revision)
Line 3: Line 3:
  
 
[[Install SEA]]
 
[[Install SEA]]
 +
 +
[[Generate model]]
  
 
[[Basic Tutorial]]
 
[[Basic Tutorial]]
  
 
[[Chembl processing protocol]]
 
[[Chembl processing protocol]]
 
 
== How to generate a model to run SEA ==
 
 
We need the files: reference.smi ; reference.set ; reference.fp
 
 
First we need to generate the background Z-score distribution:
 
 
[prompt]$ sea-background reference.set.gz
 
 
This generated the file model.out
 
 
Then we need to fit data the data from this background model and build a fit parameter file:
 
 
[prompt]$ sea-fit model.out
 
 
This generates the file model.out.distfit, containing the values for the best fit of the background distribution to a normal and an extreme value distribution. From this distribution, we need to select the optimal cutoff (in general we look for the similarity value that better fits to EVD) and then use it to get the fit file.
 
 
[prompt]$ sea-fit -c cutoff model.out
 
  
  

Revision as of 16:14, 11 October 2012

SEA, the similarity ensemble approach. sea.docking.org

Install SEA

Generate model

Basic Tutorial

Chembl processing protocol