Introducing GGBweb

In [3]:

    

from query.egrin2_query import *

# connect to the egrin 2.0 database
host = "primordial"
port = 27017
db = "eco_db"
client = MongoClient( 'mongodb://'+ host +':'+ str( port )+'/' )


    

In [3]:

    

# get nucleotide gene info
gene_info = pd.DataFrame( list( client[ db ].row_info.find( { "$or": [ { "GO": { "$regex" : "GO:0009117" } }, { "TIGRRoles": { "$regex" : "nucleotide" } }, { "ECDesc": { "$regex" : "nucleotide" } } ] } ) ) )
gene_info.loc[ :,[ "name","ECDesc","TIGRRoles" ] ]
# get egrin2 gene names only
genes = gene_info.egrin2_row_name.tolist()


    

In [4]:

    

# name chromosome-:1823979-1824947 
ggbwebModule( genes, outfile = "nucleotide_module.txt", host = host, port = port, db = db )


    

    




Module written to: /Users/abrooks/Documents/git/GGBWeb/docs/nucleotide_module.txt

In [5]:

    

# find GREs discovered upstream of these genes
gre_candidates = agglom( genes, x_type="gene", y_type="gre", host=host, db=db, logic="or", x_input_type = "egrin2_row_name").sort(["counts","pval"],ascending=False)

gre_candidates.head()


    

    




Using or logic






    
Out[5]:






  

    

      

      
counts
      
all_counts
      
pval
      
qval_BH
      
qval_bonferroni
    
  
  

    

      
2 
      
 262
      
 417
      
 1.225490e-15
      
 8.741826e-14
      
 5.245096e-13
    
    

      
11
      
 227
      
 231
      
 2.100609e-77
      
 2.247651e-75
      
 8.990605e-75
    
    

      
7 
      
 157
      
 272
      
 1.333561e-06
      
 5.188765e-05
      
 5.707641e-04
    
    

      
12
      
 147
      
 211
      
 7.512623e-15
      
 4.593432e-13
      
 3.215403e-12
    
    

      
8 
      
 138
      
 253
      
 2.201497e-04
      
 4.959161e-03
      
 9.422405e-02
    
  

In [1]:

    

gres = gre_candidates.index[0:5].tolist()


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-1-e7eca1ea4863> in <module>()
----> 1 gres = gre_candidates.index[0:5].tolist()

NameError: name 'gre_candidates' is not defined

In [7]:

    

# fimoFinder( locusId = "NC_000913", filterby = gres, filter_type = "gre", host=host, port=port, db=db, outfile = "fimo.txt")


    

    




Start not provided. Assuming beginning of chromosome
Stop not provided. Assuming end of chromosome
WARNING: Many of these filters are not supported currently. Only GREs!!!
Filtering motifs by gre_id
Writing file GRE_8_fimo.txt
Writing file GRE_12_fimo.txt
Writing file GRE_2_fimo.txt
Writing file GRE_11_fimo.txt
Writing file GRE_7_fimo.txt