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]:
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)