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

changed outcols in dssp and kd outputs

Browse source
This commit is contained in:
Tanushree Tunstall 2020-03-26 17:12:59 +00:00
parent 5bab99c15f
commit c0bac6fd7b
3 changed files with 14 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

7
meta_data_analysis/dssp_df.py
View file

@ -60,16 +60,19 @@ print('Input filename:', in_filename
# specify PDB chain # specify PDB chain
my_chain = 'A' my_chain = 'A'
print('======================================================================')
#======= #=======
# output # output
#======= #=======
outdir = datadir + '/' + drug + '/' + 'output' outdir = datadir + '/' + drug + '/' + 'output'
out_filename = gene.lower() + '_dssp_df' out_filename = gene.lower() + '_dssp.csv'
outfile = outdir + '/' + out_filename outfile = outdir + '/' + out_filename
print('Output filename:', out_filename print('Output filename:', out_filename
, '\nOutput path:', outdir , '\nOutput path:', outdir
,'\nOutfile: ', outfile) ,'\nOutfile: ', outfile)
print('======================================================================')
#%% end of variable assignment for input and output files #%% end of variable assignment for input and output files
#======================================================================= #=======================================================================
# Process dssp output and extract into df # Process dssp output and extract into df
@ -87,7 +90,7 @@ pp.pprint(dssp_df)
# Rename column (amino acid) as 'wild_type' and (site} as 'position' # Rename column (amino acid) as 'wild_type' and (site} as 'position'
# to be the same names as used in the file required for merging later. # to be the same names as used in the file required for merging later.
dssp_df.columns dssp_df.columns
dssp_df.rename(columns = {'site':'position', 'amino_acid':'wild_type'}, inplace = True) dssp_df.rename(columns = {'site':'position', 'amino_acid':'wild_type_dssp'}, inplace = True)
dssp_df.columns dssp_df.columns
#%% Write ouput csv file #%% Write ouput csv file

11
meta_data_analysis/kd_df.py
View file

@ -59,6 +59,7 @@ print('Input filename:', in_filename
, '\nInput path:', indir) , '\nInput path:', indir)
print('======================================================================') print('======================================================================')
#======= #=======
# output # output
#======= #=======
@ -111,7 +112,7 @@ print('======================================================================')
# df1: df of aa seq with index reset to start from 1 (reflective of the actual aa position in a sequence) # df1: df of aa seq with index reset to start from 1 (reflective of the actual aa position in a sequence)
# Name column of wt as 'wild_type' to be the same name used in the file required for merging later. # Name column of wt as 'wild_type' to be the same name used in the file required for merging later.
dfSeq = pd.DataFrame({'wild_type':list(sequence)}) dfSeq = pd.DataFrame({'wild_type_kd':list(sequence)})
dfSeq.index = np.arange(1, len(dfSeq) + 1) # python is not inclusive dfSeq.index = np.arange(1, len(dfSeq) + 1) # python is not inclusive
# df2: df of kd_values with index reset to start from offset + 1 and subsequent matched length of the kd_values # df2: df of kd_values with index reset to start from offset + 1 and subsequent matched length of the kd_values
@ -122,9 +123,9 @@ dfVals.index = np.arange(offset + 1, len(dfVals) + 1 + offset)
max(dfVals['kd_values']) max(dfVals['kd_values'])
min(dfVals['kd_values']) min(dfVals['kd_values'])
#============ #===================
# merging dfs # concatenating dfs
#============ #===================
# Merge the two on index (as these are now reflective of the aa position numbers): df1 and df2 # Merge the two on index (as these are now reflective of the aa position numbers): df1 and df2
# This will introduce NaN where there is missing values. In our case this will be 2 (first and last ones) # This will introduce NaN where there is missing values. In our case this will be 2 (first and last ones)
# Conveniently, the last position in this case is not part of the struc, so not much loss of info # Conveniently, the last position in this case is not part of the struc, so not much loss of info
@ -133,7 +134,7 @@ min(dfVals['kd_values'])
kd_df = pd.concat([dfSeq, dfVals], axis = 1) kd_df = pd.concat([dfSeq, dfVals], axis = 1)
#============================ #============================
# Renaming index to position # renaming index to position
#============================ #============================
kd_df = kd_df.rename_axis('position') kd_df = kd_df.rename_axis('position')
kd_df.head kd_df.head

1
meta_data_analysis/rd_df.py
View file

@ -50,6 +50,7 @@ infile = indir + '/' + in_filename
print('Input filename:', in_filename print('Input filename:', in_filename
, '\nInput path:', indir) , '\nInput path:', indir)
print('======================================================================')
#======= #=======
# output # output
#======= #=======