added deepddg data to combining_df.py

scripts/combining_dfs.py

@@ -131,7 +131,7 @@ in_filename_foldx = gene.lower() + '_foldx.csv'
 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_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'
@@ -143,7 +143,7 @@ infile_foldx = outdir + in_filename_foldx
 infile_dssp = outdir + in_filename_dssp
 infile_kd = outdir + in_filename_kd
 infile_rd = outdir + in_filename_rd
-#infile_deepddg = outdir + in_filename_deepddg
+infile_deepddg = outdir + 'deep_ddg/' + in_filename_deepddg
 
 infile_snpinfo = outdir + '/' + in_filename_snpinfo 
 infile_afor = outdir + '/' + in_filename_afor
@@ -203,6 +203,37 @@ print('\n\nResult of first merge:', mcsm_foldx_dfs.shape
       , '\n===================================================================')
 mcsm_foldx_dfs[merging_cols_m1].apply(len)
 mcsm_foldx_dfs[merging_cols_m1].apply(len) == len(mcsm_foldx_dfs)
+#%%
+print('==================================='
+      , '\nSecond merge: mcsm_foldx_dfs + deepddg'
+      , '\n===================================')
+
+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)
+mcsm_foldx_deepddg_dfs['deepddg_outcome'].value_counts()
+
+ncols_deepddg_merge = len(mcsm_foldx_deepddg_dfs.columns)
 #%%============================================================================
 print('==================================='
       , '\nSecond merge: dssp + kd'
@@ -240,10 +271,15 @@ print('======================================='
       , '\nmcsm_foldx_dfs + dssp_kd_rd_dfs'
       , '\n=======================================')
 #combined_df = combine_dfs_with_checks(mcsm_foldx_dfs, dssp_kd_rd_dfs, my_join = i_join)
-merging_cols_m4 = detect_common_cols(mcsm_foldx_dfs, dssp_kd_rd_dfs)
+#merging_cols_m4 = detect_common_cols(mcsm_foldx_dfs, dssp_kd_rd_dfs)
-combined_df = pd.merge(mcsm_foldx_dfs, dssp_kd_rd_dfs, on = merging_cols_m4, how  = i_join)
+#combined_df = pd.merge(mcsm_foldx_dfs, dssp_kd_rd_dfs, on = merging_cols_m4, how  = i_join)
+#combined_df_expected_cols = ncols_m1 + ncols_m3 - len(merging_cols_m4)
 
-combined_df_expected_cols = ncols_m1 + ncols_m3 - len(merging_cols_m4)
+# with deepddg values
+merging_cols_m4 = detect_common_cols(mcsm_foldx_deepddg_dfs, dssp_kd_rd_dfs)
+combined_df = pd.merge(mcsm_foldx_deepddg_dfs, dssp_kd_rd_dfs, on = merging_cols_m4, how  = i_join)
+
+combined_df_expected_cols = ncols_deepddg_merge + ncols_m3 - len(merging_cols_m4)
 
 if len(combined_df) == len(mcsm_df) and len(combined_df.columns) == combined_df_expected_cols:
     print('PASS: successfully combined 5 dfs'
@@ -256,15 +292,24 @@ print('\nResult of Fourth merge:', combined_df.shape
       , '\n===================================================================')
 combined_df[merging_cols_m4].apply(len)
 combined_df[merging_cols_m4].apply(len) == len(combined_df)
-
 #%%============================================================================
+# Format the combined df columns
+combined_df_colnames = combined_df.columns
 
-#deepddg_df =  pd.read_csv(infile_deepddg, sep = ' ')
+# check redundant columns
+combined_df['chain'].equals(combined_df['chain_id'])
+combined_df['wild_type'].equals(combined_df['wild_type_kd']) # has nan
+combined_df['wild_type'].equals(combined_df['wild_type_dssp'])
+#sanity check
+foo = combined_df[['wild_type', 'wild_type_kd', 'wt_3letter_caps', 'wt_aa_3lower', 'mut_aa_3lower']] 
 
+# Drop cols
+cols_to_drop = ['chain_id', 'wild_type_kd', 'wild_type_dssp', 'wt_3letter_caps' ]
+combined_df_clean = combined_df.drop(cols_to_drop, axis = 1)
 
+del(foo)
 #%%============================================================================
 # Output columns
-
 out_filename_stab_struc = gene.lower() + '_comb_stab_struc_params.csv'
 outfile_stab_struc =  outdir + '/' + out_filename_stab_struc
 print('Output filename:', outfile_stab_struc