tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

updating ambiguous muts manipulation section in data_extraction_v2

Browse source
This commit is contained in:
Tanushree Tunstall 2022-04-14 10:36:08 +01:00
parent 6330a2e716
commit e6faf80c20
1 changed files with 12 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

12
scripts/data_extraction_v2.py
View file

@ -959,6 +959,18 @@ foo = bar.iloc[ambig_muts_rev_df.index]
foo[['mutation', 'mutation_info', 'mutation_info_old']]
# CHECK if there are still any ambiguous muts
muts_split_rev = list(bar.groupby('mutation_info'))
dr_muts_rev = muts_split_rev[0][1].mutation
other_muts_rev = muts_split_rev[1][1].mutation
print('splitting muts by mut_info:', muts_split_rev)
print('no.of dr_muts samples:', len(dr_muts_rev))
print('no. of other_muts samples', len(other_muts_rev))
if not dr_muts_rev.isin(other_muts_rev).sum() & other_muts_rev.isin(dr_muts_rev).sum() > 0:
print('\nAmbiguous muts corrected. Proceeding with downstream analysis')
else:
print('\nAmbiguous muts corrected. Quitting!')
sys.exit()
#%% ROUND THE HOUSES: DELETE
foo = ambig_muts_rev_df[['mutation', 'mutation_info_REV']]