In [1]:

    

%run ~/relmapping/annot/notebooks/__init__.ipynb


    

    




/mnt/home3/jj374/anaconda36/lib/python3.6/site-packages/statsmodels/compat/pandas.py:56: FutureWarning: The pandas.core.datetools module is deprecated and will be removed in a future version. Please use the pandas.tseries module instead.
  from pandas.core import datetools






    




os.getcwd(): /mnt/b2/scratch/ahringer/jj374/lab/relmapping

In [2]:

    

# Emb DHSs
#!cd ~/relmapping/wget; wget -m --no-parent ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE97nnn/GSE97425/suppl/GSE97425_embryo.ce10.allDHS.bed.gz
# L1 DHSs
#!cd ~/relmapping/wget; wget -m --no-parent ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE97nnn/GSE97425/suppl/GSE97425_L1.ce10.allDHS.bed.gz


    

In [3]:

    

fp_ = 'wget/ftp.ncbi.nlm.nih.gov/geo/series/GSE97nnn/GSE97425/suppl/GSE97425_embryo.ce10.allDHS.bed.gz'
df_ = pd.read_csv(fp_, sep='\t', names=yp.NAMES_BED9[:4])
df_[yp.NAMES_BED3].to_csv('annot/FigA_atac_screen_shot/Ho2017_embryo.bed', header=None, index=None, sep='\t')
!wc -l annot/FigA_atac_screen_shot/Ho2017_embryo.bed
df_.head()


    

    




41825 annot/FigA_atac_screen_shot/Ho2017_embryo.bed






    
Out[3]:







  

    

      

      
chrom
      
start
      
end
      
name
    
  
  

    

      
0
      
chrI
      
3900
      
4050
      
1391.125000
    
    

      
1
      
chrI
      
9740
      
9890
      
507.437500
    
    

      
2
      
chrI
      
11380
      
11530
      
1080.578125
    
    

      
3
      
chrI
      
13820
      
13970
      
149.218750
    
    

      
4
      
chrI
      
16920
      
17070
      
164.890625
    
  

In [4]:

    

fp_ = 'wget/ftp.ncbi.nlm.nih.gov/geo/series/GSE97nnn/GSE97425/suppl/GSE97425_L1.ce10.allDHS.bed.gz'
df_ = pd.read_csv(fp_, sep='\t', names=yp.NAMES_BED9[:4])
df_[yp.NAMES_BED3].to_csv('annot/FigA_atac_screen_shot/Ho2017_L1_arrest.bed', header=None, index=None, sep='\t')
!wc -l annot/FigA_atac_screen_shot/Ho2017_L1_arrest.bed
df_.head()


    

    




23670 annot/FigA_atac_screen_shot/Ho2017_L1_arrest.bed






    
Out[4]:







  

    

      

      
chrom
      
start
      
end
      
name
    
  
  

    

      
0
      
chrI
      
3880
      
4030
      
927.546875
    
    

      
1
      
chrI
      
9740
      
9890
      
173.281250
    
    

      
2
      
chrI
      
11380
      
11530
      
589.343750
    
    

      
3
      
chrI
      
13840
      
13990
      
254.109375
    
    

      
4
      
chrI
      
22880
      
23030
      
534.062500
    
  

In [5]:

    

fp_ = 'annot/FigA_overlaps/bed_files/Daugherty2017_consensus_ATAC.bed'
df_ = pd.read_csv(fp_, sep='\t', comment='#', names=yp.NAMES_BED9)[yp.NAMES_BED3]
df_.to_csv('annot/FigA_atac_screen_shot/Daugherty2017_consensus_ATAC_bed3.bed', header=None, index=None, sep='\t')


    

In [ ]: