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]:

    

# Ni: ForJulie/20180223_modERN_modENCODE_peak_assignment
fp_ = 'annot/Fig2S3_overlaps/20180223_modERN_modENCODE_peak_assignment/ce10.summits.combined.txt'
names_ = ['summit_chrom', 'summit_start', 'summit_end', 'factor_name', 'stage', 'file_accession', 'peak_iv']

def chrom_(s): return s.split(':')[0]
def start_(s): return s.split(':')[1].split('-')[0]
def end_(s): return s.split(':')[1].split('-')[1]

df_ = pd.read_csv(fp_, sep='\t', names=names_)
df_['peak_chrom'] = df_['peak_iv'].map(chrom_)
df_['peak_start'] = df_['peak_iv'].map(start_)
df_['peak_end'] = df_['peak_iv'].map(end_)
df_.head()


    

    
Out[2]:







  

    

      

      
summit_chrom
      
summit_start
      
summit_end
      
factor_name
      
stage
      
file_accession
      
peak_iv
      
peak_chrom
      
peak_start
      
peak_end
    
  
  

    

      
0
      
chrI
      
3769
      
3770
      
elt-3-GFP
      
L3
      
ENCFF724CLW
      
chrI:3600-3940
      
chrI
      
3600
      
3940
    
    

      
1
      
chrI
      
3812
      
3813
      
blmp-1-GFP
      
L2
      
ENCFF697TST
      
chrI:3645-3981
      
chrI
      
3645
      
3981
    
    

      
2
      
chrI
      
3820
      
3821
      
ZK546.5-GFP
      
L4
      
ENCFF905WSC
      
chrI:3669-3973
      
chrI
      
3669
      
3973
    
    

      
3
      
chrI
      
3821
      
3822
      
efl-1-GFP
      
YA
      
ENCFF456YBJ
      
chrI:3701-3893
      
chrI
      
3701
      
3893
    
    

      
4
      
chrI
      
3828
      
3829
      
rec-8-GFP
      
YA
      
ENCFF721FFG
      
chrI:3614-4044
      
chrI
      
3614
      
4044
    
  

In [3]:

    

# Calculate peak call coverage of all factors
col_ = ['peak_chrom', 'peak_start', 'peak_end']
bg = BedTool.from_dataframe(df_[col_]).genome_coverage(bg=True, g='shared/ce10.chroms').to_dataframe()
fp_bg = 'annot/Fig2S3_overlaps/modERN_modENCODE/modERN_modENCODE_peak_pileup.bedGraph'
fp_bw = 'annot/Fig2S3_overlaps/modERN_modENCODE/modERN_modENCODE_peak_pileup.bw'
bg.to_csv(fp_bg, header=False, index=False, sep='\t')

# convert track to bigWig
!bedGraphToBigWig {fp_bg} shared/ce10.chroms {fp_bw}
!rm {fp_bg}


    

In [4]:

    

# modENCODE/modERN TFBS
df_ext200_ = pd.DataFrame()
df_ext200_['chrom'] = df_['summit_chrom']
df_ext200_['start'] = df_['summit_start'] - 200
df_ext200_['end'] = df_['summit_end'] + 200
df_ext200_['name'] = df_['file_accession']
df_ext200_merge_ = BedTool.from_dataframe(df_ext200_.query('chrom != "chrM"')).merge(c='4', o='count').to_dataframe()
fp_ = 'annot/Fig2S3_overlaps/modERN_modENCODE/modERN_modENCODE_ext200_merge.bed'
df_ext200_merge_.to_csv(fp_, sep='\t', index=False, header=False)
!wc -l {fp_}


    

    




36389 annot/Fig2S3_overlaps/modERN_modENCODE/modERN_modENCODE_ext200_merge.bed