Table of Contents


In [1]:
import pandas as pd

In [2]:
quants = pd.read_csv('../output/temp_files/DE_genes.csv')
hypoxia = pd.read_csv('../output/temp_files/hypoxia_response.csv')
hifoh = pd.read_csv('../output/temp_files/hifoh_candidates.csv')
vhl = pd.read_csv('../output/temp_files/vhl_1_regulated_genes.csv')

In [3]:
hypoxia = hypoxia.target_id.unique()
hifoh = hifoh.target_id.unique()
vhl = vhl.target_id.unique()

In [4]:
pathway = {}
for gid in hypoxia:
    pathway[gid] = 'hypoxia'
for gid in vhl:
    pathway[gid] = 'vhl'

hOH = {}
for gid in hifoh:
    hOH[gid] = 'non-canonical'

In [5]:
quants['pathway'] = quants.target_id.map(pathway)

In [6]:
quants['non_canonical_epistasis'] = quants.target_id.map(hOH)

In [7]:
quants.head()


Out[7]:
ens_gene ext_gene target_id b se_b qval genotype sorter code pathway non_canonical_epistasis
0 WBGene00007064 2RSSE.1 2RSSE.1a 0.150147 0.829418 1.000000 fog-2 5 g NaN NaN
1 WBGene00007065 pot-3 3R5.1a 0.063856 1.909284 1.000000 fog-2 5 g NaN NaN
2 WBGene00007065 pot-3 3R5.1b 0.274498 1.268484 1.000000 fog-2 5 g NaN NaN
3 WBGene00004964 spe-10 AC3.10 0.197351 0.453000 0.998032 fog-2 5 g NaN NaN
4 WBGene00007070 ugt-49 AC3.2 -0.340556 0.140666 0.100833 fog-2 5 g NaN NaN

In [8]:
quants = quants[['ens_gene', 'ext_gene', 'target_id', 'b', 'se_b', 'qval', 'genotype', 'pathway', 'non_canonical_epistasis']]
quants = quants[quants.genotype != 'fog-2']
quants.to_csv('../output/supplementary_tables/supplementary_file_1.csv', index=False)