added deep ddg formatted data to combinig_dfs.py

scripts/combining_dfs.py

@@ -84,9 +84,6 @@ arg_parser.add_argument('--debug', action ='store_true', help = 'Debug Mode')
 args = arg_parser.parse_args()
 #=======================================================================
 #%% variable assignment: input and output 
-#drug = 'pyrazinamide'
-#gene = 'pncA'
-
 drug    = args.drug
 gene    = args.gene
 datadir = args.datadir
@@ -128,39 +125,40 @@ if not outdir:
 #in_filename_mcsm = gene.lower() + '_complex_mcsm_norm.csv' 
 in_filename_mcsm = gene.lower() + '_complex_mcsm_norm_SAM.csv' # gidb
 in_filename_foldx = gene.lower() + '_foldx.csv'
+in_filename_deepddg = gene.lower() + '_ni_deepddg.csv' # change to decent filename and put it in the correct dir
+
 in_filename_dssp = gene.lower() + '_dssp.csv'
 in_filename_kd = gene.lower() + '_kd.csv'
 in_filename_rd = gene.lower() + '_rd.csv'
-in_filename_deepddg = gene.lower() + '_complex_ddg_results.txt' # change to decent filename and put it in the correct dir
-
-in_filename_snpinfo = 'ns' + gene.lower() + '_snp_info_f.csv' # gwas f info
-in_filename_afor = gene.lower() + '_af_or.csv'
-in_filename_afor_kin = gene.lower() + '_af_or_kinship.csv'
 
+#in_filename_snpinfo = 'ns' + gene.lower() + '_snp_info_f.csv' # gwas f info
+#in_filename_afor = gene.lower() + '_af_or.csv'
+#in_filename_afor_kin = gene.lower() + '_af_or_kinship.csv'
 
 infile_mcsm = outdir + in_filename_mcsm
 infile_foldx = outdir + in_filename_foldx
+infile_deepddg = outdir + in_filename_deepddg
+
 infile_dssp = outdir + in_filename_dssp
 infile_kd = outdir + in_filename_kd
 infile_rd = outdir + in_filename_rd
-infile_deepddg = outdir + 'deep_ddg/' + in_filename_deepddg
 
-infile_snpinfo = outdir + '/' + in_filename_snpinfo 
-infile_afor = outdir + '/' + in_filename_afor
-infile_afor_kin = outdir + '/' + in_filename_afor_kin
+#infile_snpinfo = outdir + '/' + in_filename_snpinfo 
+#infile_afor = outdir + '/' + in_filename_afor
+#infile_afor_kin = outdir + '/' + in_filename_afor_kin
 
 print('\nInput path:', indir
       , '\nOutput path:', outdir, '\n'
       , '\nInput filename mcsm:', infile_mcsm
       , '\nInput filename foldx:', infile_foldx, '\n'
+      , '\nInput filename deepddg', infile_deepddg , '\n'
       , '\nInput filename dssp:', infile_dssp
       , '\nInput filename kd:', infile_kd 
       , '\nInput filename rd', infile_rd
-#     , '\nInput filename rd', infile_deepddg , '\n'
      
-      , '\nInput filename snp info:', infile_snpinfo, '\n'
-      , '\nInput filename af or:', infile_afor
-      , '\nInput filename afor kinship:', infile_afor_kin
+      #, '\nInput filename snp info:', infile_snpinfo, '\n'
+      #, '\nInput filename af or:', infile_afor
+      #, '\nInput filename afor kinship:', infile_afor_kin
       , '\n============================================================')
 
 #=======
@@ -208,29 +206,11 @@ print('==================================='
       , '\nSecond merge: mcsm_foldx_dfs + deepddg'
       , '\n===================================')
 
-deepddg_df =  pd.read_csv(infile_deepddg, sep = ' ')
+deepddg_df =  pd.read_csv(infile_deepddg, sep = ',')
 deepddg_df.columns
 
-deepddg_df.rename(columns = {'#chain'  : 'chain_id'
-                             , 'WT'    : 'wild_type_deepddg'
-                             , 'ResID' : 'position'
-                             , 'Mut'   : 'mutant_type_deepddg'}
-                             , inplace = True)
-
-deepddg_df['mutationinformation'] = deepddg_df['wild_type_deepddg'] + deepddg_df['position'].map(str) + deepddg_df['mutant_type_deepddg']
-
-# add deepddg outcome column: <0--> Destabilising, >0 --> Stabilising
-deepddg_df['deepddg_outcome'] = np.where(deepddg_df['deepddg'] < 0, 'Destabilising', 'Stabilising')
-deepddg_df['deepddg_outcome'].value_counts()
-
-# drop extra columns to allow clean merging
-deepddg_short_df = deepddg_df.drop(['chain_id', 'wild_type_deepddg', 'position', 'mutant_type_deepddg'], axis = 1)
-
-# rearrange columns
-deepddg_short_df.columns
-deepddg_short_df = deepddg_short_df[["mutationinformation", "deepddg", "deepddg_outcome"]]
-
-mcsm_foldx_deepddg_dfs = pd.merge(mcsm_foldx_dfs, deepddg_short_df, on = 'mutationinformation',  how = l_join)
+# merge with mcsm_foldx_dfs and deepddg_df
+mcsm_foldx_deepddg_dfs = pd.merge(mcsm_foldx_dfs, deepddg_df, on = 'mutationinformation',  how = l_join)
 mcsm_foldx_deepddg_dfs['deepddg_outcome'].value_counts()
 
 ncols_deepddg_merge = len(mcsm_foldx_deepddg_dfs.columns)
@@ -317,10 +297,10 @@ print('Output filename:', outfile_stab_struc
 
 # write csv
 print('Writing file: combined stability and structural parameters')
-combined_df.to_csv(outfile_stab_struc, index = False)
+combined_df_clean.to_csv(outfile_stab_struc, index = False)
 print('\nFinished writing file:'
-      , '\nNo. of rows:', combined_df.shape[0]
-      , '\nNo. of cols:', combined_df.shape[1])
+      , '\nNo. of rows:', combined_df_clean.shape[0]
+      , '\nNo. of cols:', combined_df_clean.shape[1])
 
 
 #%% end of script