From 69b8ba9d0803917ee1744b6d4a44b5f8249d4927 Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Sat, 13 Nov 2021 09:43:56 +0000
Subject: [PATCH] ran mcsm format for embb

---
 mcsm/mcsm.py             |  2 +-
 mcsm/run_mcsm.py         | 16 ++++++++--------
 scripts/combining_dfs.py |  4 +++-
 3 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/mcsm/mcsm.py b/mcsm/mcsm.py
index 817089c..f992c04 100644
--- a/mcsm/mcsm.py
+++ b/mcsm/mcsm.py
@@ -243,7 +243,7 @@ def format_mcsm_output(mcsm_outputcsv):
         mcsm_data = mcsm_data.drop_duplicates(['mutationinformation'])
         print('Dim of data after removing duplicate muts:', mcsm_data.shape
         , '\n===========================================================')
-#%%===================================================================== 
+#%%=====================================================================
     #############
     # Create col: duet_outcome
     #############
diff --git a/mcsm/run_mcsm.py b/mcsm/run_mcsm.py
index dd0e150..dbb7076 100755
--- a/mcsm/run_mcsm.py
+++ b/mcsm/run_mcsm.py
@@ -79,13 +79,13 @@ gene_match = gene + '_p.'
 # directories
 #============
 if not datadir:
-    datadir = homedir + '/' + 'git/Data'
+    datadir = homedir + '/git/Data/'
     
 if not indir:
-    indir = datadir + '/' + drug + '/input'
+    indir = datadir + drug + 'input/'
     
 if not outdir:
-    outdir = datadir + '/' + drug + '/output'
+    outdir = datadir + drug + 'output/'
 
 #=======
 # input
@@ -95,7 +95,7 @@ if pdb_filename:
 else:
     in_filename_pdb = gene.lower() + '_complex.pdb'
     
-infile_pdb = indir + '/' + in_filename_pdb
+infile_pdb = indir + in_filename_pdb
 
 #in_filename_snps = gene.lower() + '_mcsm_snps.csv' #(outfile_mcsm_snps, from data_extraction.py)
 #infile_snps = outdir + '/' + in_filename_snps
@@ -105,7 +105,7 @@ if mutation_filename:
 else:
     in_filename_snps = gene.lower() + '_mcsm_formatted_snps.csv'
     
-infile_snps = outdir + '/' + in_filename_snps
+infile_snps = outdir + in_filename_snps
 
 #=======
 # output
@@ -113,13 +113,13 @@ infile_snps = outdir + '/' + in_filename_snps
 # mcsm_results globals
 if not result_urls:
     result_urls_filename = gene.lower() + '_result_urls.txt'
-    result_urls =  outdir + '/' + result_urls_filename
+    result_urls =  outdir + result_urls_filename
     if DEBUG:
         print('DEBUG: Result URLs:', result_urls)
 
 if not mcsm_output:
     mcsm_output_filename = gene.lower() + '_mcsm_output.csv'
-    mcsm_output =  outdir + '/' + mcsm_output_filename
+    mcsm_output =  outdir + mcsm_output_filename
     if DEBUG:
         print('DEBUG: mCSM output CSV file:', mcsm_output)
 
@@ -127,7 +127,7 @@ if not mcsm_output:
 #out_filename_format = gene.lower() + '_mcsm_processed.csv'
 if not outfile_format:
     out_filename_format = gene.lower() + '_complex_mcsm_norm.csv'
-    outfile_format =  outdir + '/' + out_filename_format
+    outfile_format =  outdir + out_filename_format
     if DEBUG:
         print('DEBUG: formatted CSV output:', outfile_format)
 #%%=====================================================================
diff --git a/scripts/combining_dfs.py b/scripts/combining_dfs.py
index cb47d50..a0c570b 100755
--- a/scripts/combining_dfs.py
+++ b/scripts/combining_dfs.py
@@ -122,7 +122,9 @@ if gene.lower() == "gid":
     in_filename_mcsm = gene.lower() + '_complex_mcsm_norm_SRY.csv' # was incorrectly SAM previously
 if gene.lower() == "embb":
     print("\nReading mCSM file for gene:", gene)
-    in_filename_mcsm = gene.lower() + '_complex_mcsm_norm1.csv'
+    #in_filename_mcsm = gene.lower() + '_complex_mcsm_norm1.csv'
+    in_filename_mcsm = gene.lower() + '_complex_mcsm_norm2.csv'
+
 if gene.lower() in gene_list_normal:
    print("\nReading mCSM file for gene:", gene)
    in_filename_mcsm = gene.lower() + '_complex_mcsm_norm.csv'