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

tidy code and saving work for the day

Browse source
This commit is contained in:
Tanushree Tunstall 2020-03-26 17:58:39 +00:00
parent 69e2567ffc
commit afd6ca8881
6 changed files with 307 additions and 284 deletions
Download patch file Download diff file Expand all files Collapse all files

28
meta_data_analysis/mut_electrostatic_changes.py
View file

@ -46,7 +46,8 @@ indir = datadir + '/' + drug + '/' + 'input'
in_filename = 'merged_df3.csv'
infile = outdir + '/' + in_filename
print('Input filename: ', in_filename
, '\nInput path: ', indir)
, '\nInput path: ', indir
, '\n============================================================')
#=======
# output
@ -56,7 +57,8 @@ outdir = datadir + '/' + drug + '/' + 'output'
out_filename = 'mut_elec_changes.txt'
outfile = outdir + '/' + out_filename
print('Output filename: ', out_filename
, '\nOutput path: ', outdir)
, '\nOutput path: ', outdir
, '\n============================================================')
#%% end of variable assignment for input and output files
#=======================================================================
@ -65,10 +67,11 @@ print('Reading input file (merged file):', infile)
comb_df = pd.read_csv(infile, sep = ',')
print('Input filename: ', in_filename,
'\nPath :', outdir,
'\nNo. of rows: ', len(comb_df),
'\nNo. of cols: ', infile)
print('Input filename: ', in_filename
, '\nPath :', outdir
, '\nNo. of rows: ', len(comb_df)
, '\nNo. of cols: ', infile
, '\n============================================================')
# column names
list(comb_df.columns)
@ -81,15 +84,18 @@ df = comb_df.drop_duplicates(['Mutationinformation'], keep = 'first')
total_muts = df.Mutationinformation.nunique()
#df.Mutationinformation.count()
print('Total mutations associated with structure: ', total_muts)
print('Total mutations associated with structure: ', total_muts
, '\n===============================================================')
#%% combine aa_calcprop cols so that you can count the changes as value_counts
# check if all muts have been categorised
print('Checking if all muts have been categorised: ')
if df['wt_calcprop'].isna().sum() == 0 & df['mut_calcprop'].isna().sum():
print('PASS: No. NA detected i.e all muts have aa prop associated')
print('PASS: No. NA detected i.e all muts have aa prop associated'
, '\n===============================================================')
else:
print('FAIL: NAs detected i.e some muts remain unclassified')
print('FAIL: NAs detected i.e some muts remain unclassified'
, '\n===============================================================')
df['wt_calcprop'].head()
df['mut_calcprop'].head()
@ -151,11 +157,11 @@ print('======================\n'
, '\n============================\n'
, all_prop_change)
print('========================================================================'
print('================================================================='
, '\nTotal number of electrostatic changes resulting from Mtation is (%):', elec_changes
, '\nTotal no. of muts: ', total_muts
, '\nTotal no. of changed muts: ', all_prop_change.mut_count.sum()
, '\nTotal no. of unchanged muts: ', no_change_muts.mut_count.sum()
, '\n=========================================================================')
, '\n===================================================================')
#%% end of script
#=======================================================================