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]:

    

# (Boeck et al., 2016)
#!cd ~/relmapping/wget; wget -m --no-parent http://genome.cshlp.org/content/suppl/2016/09/20/gr.202663.115.DC1/Supplemental_Table_S13.gz
fp_ = 'wget/genome.cshlp.org/content/suppl/2016/09/20/gr.202663.115.DC1/Supplemental_Table_S13.txt'
df_expr = pd.read_csv(fp_, delim_whitespace=True)#, index_col='WormbaseName')
len(df_expr)


    

    
Out[2]:





20391

In [3]:

    

#!cd ~/relmapping/wget; wget -m --no-parent http://genome.cshlp.org/content/suppl/2016/09/20/gr.202663.115.DC1/Supplemental_Fig_S4.docx
print(len(df_expr.query('L1 > 0.02'))) # eyeballed from fig4: 13.5K for L1
print(len(df_expr.query('DE > 0.02'))) # eyeballed from fig5: 15K for DE


    

    




13316
15028

In [4]:

    

# Select time points roughly matched with wt LE to YA
df_expr[df_expr.columns[16:24]].head()


    

    
Out[4]:







  

    

      

      
587min
      
626min
      
665min
      
L1
      
L2
      
L3
      
L4
      
YA
    
  
  

    

      
0
      
0.3078
      
0.3364
      
0.3074
      
0.113352
      
0.079734
      
0.025379
      
0.050510
      
0.045095
    
    

      
1
      
2.8029
      
3.1333
      
2.8126
      
0.896642
      
0.611569
      
0.415548
      
0.387748
      
0.299345
    
    

      
2
      
1.4648
      
1.2548
      
1.1278
      
0.217031
      
0.269412
      
0.165271
      
0.116517
      
0.041802
    
    

      
3
      
0.0832
      
0.0676
      
0.0682
      
0.108792
      
0.111028
      
0.152491
      
0.252174
      
0.475804
    
    

      
4
      
0.5604
      
0.5636
      
0.5500
      
0.012563
      
0.532903
      
0.052147
      
0.254605
      
0.016723
    
  

In [6]:

    

# Calculate numnber of genes with dcpm > 0.02 (as used in Boeck et al., 2016) in any stage
n_ = sum((df_expr[df_expr.columns[16:24]] > 0.02).any(axis=1))
print("%d of %d genes with dcpm > 0.02 in development (Fig S4 threshold)" % (n_, len(df_expr)))
n_ = sum((df_expr[df_expr.columns[16:24]] > 0.07).any(axis=1))
print("%d of %d genes with dcpm > 0.07 in development (Fig 1 & DE analyses' threshold)" % (n_, len(df_expr)))


    

    




18173 of 20391 genes with dcpm > 0.02 in development (Fig S4 threshold)
15746 of 20391 genes with dcpm > 0.07 in development (Fig 1 & DE analyses' threshold)

In [ ]: