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

added active site indication for merged_dfs in count_vars_ML.R and also added 'gene_name' in combining_dfs.py

Browse source
This commit is contained in:
Tanushree Tunstall 2022-06-15 18:36:28 +01:00
parent 1204f1faba
commit f355846dae
3 changed files with 59 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

46
scripts/combining_dfs.py
View file

@ -124,7 +124,7 @@ if gene.lower() == "embb":
print("\nReading mCSM file for gene:", gene)
#in_filename_mcsm = gene.lower() + '_complex_mcsm_norm1.csv' #798
#in_filename_mcsm = gene.lower() + '_complex_mcsm_norm2.csv' #844
in_filename_mcsm = gene.lower() + '_complex_mcsm_norm3.csv' #851
in_filename_mcsm = gene.lower() + '_complex_mcsm_norm3.csv' #858 [got all muts on 15/05/2022]
if gene.lower() in gene_list_normal:
print("\nReading mCSM file for gene:", gene)
@ -1081,21 +1081,35 @@ combined_df = pd.merge(combined_7dfs
combined_df_expected_cols = len(combined_7dfs.columns) + len(snap2_df_f.columns) - len(merging_cols_m4_v2)
#%% Dimension checks for combined_df:
#%% Dimension checks for combined_df: specially because embB didn't have mCSM
# values for all muts. This was fixed in UQ, and this rerun on 15/05/2022
#------------------------------------------------------------------------------
# No longer required since mCSM values for fetched for all muts!
# CHECK whether logic effects anything else!
if not gene == "embB":
print("\nGene is:", gene)
if len(combined_df) == len(mcsm_df) and len(combined_df.columns) == combined_df_expected_cols:
print('PASS: successfully combined 8 dfs'
, '\nNo. of rows combined_df:', len(combined_df)
, '\nNo. of cols combined_df:', len(combined_df.columns))
elif len(combined_df) == len(foldx_df) and len(combined_df.columns) == combined_df_expected_cols:
# if not gene == "embB":
# print("\nGene is:", gene)
# if len(combined_df) == len(mcsm_df) and len(combined_df.columns) == combined_df_expected_cols:
# print('PASS: successfully combined 8 dfs'
# , '\nNo. of rows combined_df:', len(combined_df)
# , '\nNo. of cols combined_df:', len(combined_df.columns))
# elif len(combined_df) == len(foldx_df) and len(combined_df.columns) == combined_df_expected_cols:
# print('PASS: successfully combined 8 dfs'
# , '\nNo. of rows combined_df:', len(combined_df)
# , '\nNo. of cols combined_df:', len(combined_df.columns))
# else:
# sys.exit('FAIL: check individual merges for seventh merge')
#------------------------------------------------------------------------------
print("\nRunning Dimension check for combined_df for gene:", gene)
if len(combined_df) == len(mcsm_df) and len(combined_df.columns) == combined_df_expected_cols:
print('PASS: successfully combined 8 dfs'
, '\nNo. of rows combined_df:', len(combined_df)
, '\nNo. of cols combined_df:', len(combined_df.columns))
, '\nNo. of rows combined_df:', len(combined_df)
, '\nNo. of cols combined_df:', len(combined_df.columns))
else:
sys.exit('FAIL: check individual merges for seventh merge')
sys.exit('FAIL: check individual merges for seventh merge')
print('\n====================================================')
print('\nResult of Seventh merge:', combined_df.shape
, '\n===================================================================')
@ -1361,6 +1375,12 @@ else:
, '\nGot:', len(combined_all_params_f2.columns)
, '\nExpected nrows:', expected_nrows
, '\nGot:', len(combined_all_params_f2) )
#---------------------------------------
# Add gene name
#---------------------------------------
combined_all_params_f2['gene_name'] = gene.lower()
#---------------------------------------
# Add pdb_file name at the end
#---------------------------------------