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

updated count.py with indel and stop codon count

Browse source
This commit is contained in:
Tanushree Tunstall 2021-02-24 09:56:36 +00:00
parent 8975a4cedf
commit 9784bc1729
2 changed files with 28 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

30
scripts/count.py
View file

@ -276,13 +276,37 @@ foo_count = foo.loc[foo[dr_muts_col].str.contains('del', na = False, regex = Tru
bar = meta_data[other_muts_col].value_counts()
bar = bar.reset_index(name = 'values')
bar.columns = [other_muts_col, 'dr_muts_count'] #64
bar.columns = [other_muts_col, 'other_muts_count'] #64
bar_count = bar.loc[bar[other_muts_col].str.contains('del', na = False, regex = True, case = False)]
tot = len(foo_count) + len(bar_count)
n_del = tot/len(meta_data)
n_del*100
n_del*100 #0.6
#============================
foo2 = meta_data[dr_muts_col].value_counts()
foo2 = foo2.reset_index(name = 'values')
foo2.columns = [dr_muts_col, 'dr_muts_count'] #171
foo2_count = foo2.loc[foo2[dr_muts_col].str.contains('ins', na = False, regex = True, case = False) ]
baz = meta_data.loc[meta_data[dr_muts_col].str.contains(nssnp_match, na = False, regex = True, case = False) | meta_data[other_muts_col].str.contains(nssnp_match, na = False, regex = True, case = False) ]
bar2 = meta_data[other_muts_col].value_counts()
bar2 = bar2.reset_index(name = 'values')
bar2.columns = [other_muts_col, 'pther_muts_count'] #64
bar2_count = bar2.loc[bar2[other_muts_col].str.contains('ins', na = False, regex = True, case = False)]
tot2 = len(foo2_count) + len(bar2_count)
n_ins = tot2/len(meta_data)
n_ins*100 #0.5
#=========
del_ins_tot = n_del*100 + n_ins*100
#==========
# stop codons
baz_count = foo.loc[foo[dr_muts_col].str.contains('\*', na = False, regex = True, case = False) ]
baz_count2 = bar.loc[bar[other_muts_col].str.contains('\*', na = False, regex = True, case = False)]
tot3 = len(baz_count) + len(baz_count2)
n_stop = tot3/len(meta_data)
n_stop*100 #0.11
all_tot = n_del*100 + n_ins*100 + n_stop*100 #1.2