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

sorted combining_dfs.py with all other data files and tidied up get_plotting_dfs.R

Browse source
This commit is contained in:
Tanushree Tunstall 2021-09-10 18:16:41 +01:00
parent 4339976002
commit e28be8bf0d
3 changed files with 111 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

71
scripts/combining_dfs.py
View file

@ -169,25 +169,31 @@ i_join = 'inner'
#=====================
# some preprocessing
#=====================
#-------------
#===========
# FoldX
#-------------
#===========
foldx_df.shape
#=======================
#----------------------
# scale foldx values
#=======================
#----------------------
# rename ddg column to ddg_foldx
foldx_df['ddg']
foldx_df = foldx_df.rename(columns = {'ddg':'ddg_foldx'})
foldx_df['ddg_foldx']
# Rescale values in Foldx_change col b/w -1 and 1 so negative numbers
# stay neg and pos numbers stay positive
foldx_min = foldx_df['ddg'].min()
foldx_max = foldx_df['ddg'].max()
foldx_min = foldx_df['ddg_foldx'].min()
foldx_max = foldx_df['ddg_foldx'].max()
foldx_min
foldx_max
foldx_scale = lambda x : x/abs(foldx_min) if x < 0 else (x/foldx_max if x >= 0 else 'failed')
foldx_df['foldx_scaled'] = foldx_df['ddg'].apply(foldx_scale)
print('Raw foldx scores:\n', foldx_df['ddg']
foldx_df['foldx_scaled'] = foldx_df['ddg_foldx'].apply(foldx_scale)
print('Raw foldx scores:\n', foldx_df['ddg_foldx']
, '\n---------------------------------------------------------------'
, '\nScaled foldx scores:\n', foldx_df['foldx_scaled'])
@ -195,8 +201,8 @@ print('Raw foldx scores:\n', foldx_df['ddg']
fsmi = foldx_df['foldx_scaled'].min()
fsma = foldx_df['foldx_scaled'].max()
c = foldx_df[foldx_df['ddg']>=0].count()
foldx_pos = c.get(key = 'ddg')
c = foldx_df[foldx_df['ddg_foldx']>=0].count()
foldx_pos = c.get(key = 'ddg_foldx')
c2 = foldx_df[foldx_df['foldx_scaled']>=0].count()
foldx_pos2 = c2.get(key = 'foldx_scaled')
@ -209,20 +215,30 @@ else:
, '\nGot:', foldx_pos2
, '\n======================================================')
# rename ddg column to ddg_foldx
foldx_df['ddg']
foldx_df = foldx_df.rename(columns = {'ddg':'ddg_foldx'})
foldx_df['ddg_foldx']
#-------------------------
# foldx outcome category
#--------------------------
foldx_df['foldx_outcome'] = foldx_df['ddg_foldx'].apply(lambda x: 'Stabilising' if x >= 0 else 'Destabilising')
foldx_df[foldx_df['ddg_foldx']>=0].count()
foc = foldx_df['foldx_outcome'].value_counts()
#-------------
if foc['Stabilising'] == foldx_pos and foc['Stabilising'] == foldx_pos2:
print('\nPASS: Foldx outcome category created')
else:
print('\nFAIL: Foldx outcome category could NOT be created'
, '\nExpected number:', foldx_pos
, '\nGot:', foc[0]
, '\n======================================================')
sys.exit()
#=======================
# Deepddg
#-------------
#=======================
deepddg_df.shape
#=======================
#-------------------------
# scale Deepddg values
#=======================
#-------------------------
# Rescale values in deepddg_change col b/w -1 and 1 so negative numbers
# stay neg and pos numbers stay positive
deepddg_min = deepddg_df['deepddg'].min()
@ -252,6 +268,23 @@ else:
, '\nExpected number:', deepddg_pos
, '\nGot:', deepddg_pos2
, '\n======================================================')
#--------------------------
# Deepddg outcome category
#--------------------------
deepddg_df['deepddg_outcome'] = deepddg_df['deepddg'].apply(lambda x: 'Stabilising' if x >= 0 else 'Destabilising')
deepddg_df[deepddg_df['deepddg']>=0].count()
doc = deepddg_df['deepddg_outcome'].value_counts()
if doc['Stabilising'] == deepddg_pos and doc['Stabilising'] == deepddg_pos2:
print('\nPASS: Deepddg outcome category created')
else:
print('\nFAIL: Deepddg outcome category could NOT be created'
, '\nExpected number:', deepddg_pos
, '\nGot:', doc[0]
, '\n======================================================')
sys.exit()
#%%=============================================================================
# Now merges begin
#%%=============================================================================