added cmd option for dynamut2 formatting results

dynamut/run_format_results_dynamut.py

@@ -20,8 +20,45 @@ from format_results_dynamut2 import *
 # variables
 # TODO: add cmd line args
 
-gene = 'gid'
-drug = 'streptomycin'
+#gene = 
+#drug = 
+
+#%% command line args
+arg_parser = argparse.ArgumentParser()
+arg_parser.add_argument('-d', '--drug', help='drug name (case sensitive)', default = None)
+arg_parser.add_argument('-g', '--gene', help='gene name (case sensitive)', default = None)
+arg_parser.add_argument('--datadir', help = 'Data Directory. By default, it assmumes homedir + git/Data')
+arg_parser.add_argument('-i', '--input_dir', help = 'Input dir containing pdb files. By default, it assmumes homedir + <drug> + input')
+arg_parser.add_argument('-o', '--output_dir', help = 'Output dir for results. By default, it assmes homedir + <drug> + output')
+#arg_parser.add_argument('-m', '--make_dirs', help = 'Make dir for input and output', action='store_true') # should be handled elsewhere!
+
+arg_parser.add_argument('--debug', action ='store_true', help = 'Debug Mode')
+
+args = arg_parser.parse_args()
+#=======================================================================
+#%% variable assignment: input and output paths & filenames
+drug = args.drug
+gene = args.gene
+datadir = args.datadir
+indir   = args.input_dir
+outdir  = args.output_dir
+#make_dirs  = args.make_dirs
+
+#%% input and output dirs and files
+#=======
+# dirs
+#=======
+if not datadir:
+    datadir = homedir + '/' + 'git/Data'
+    
+if not indir:
+    indir = datadir + '/' + drug + '/input'
+    
+if not outdir:
+    outdir = datadir + '/' + drug + '/output'
+
+#%%=====================================================================
+
 datadir = homedir + '/git/Data'
 indir = datadir + '/' + drug + '/input'
 outdir = datadir + '/' + drug + '/output'
@@ -29,12 +66,12 @@ outdir_dynamut = outdir + '/dynamut_results/'
 outdir_dynamut2 = outdir + '/dynamut_results/dynamut2/'
 
 # Input file
-infile_dynamut =  outdir_dynamut + gene + '_dynamut_all_output_clean.csv'
+#infile_dynamut =  outdir_dynamut + gene + '_dynamut_all_output_clean.csv'
 infile_dynamut2 =  outdir_dynamut2 + gene + '_dynamut2_output_combined_clean.csv'
 
 # Formatted output filename
-outfile_dynamut_f = outdir_dynamut2 + gene + '_complex_dynamut_norm.csv'
-outfile_dynamut2_f = outdir_dynamut2 + gene + '_complex_dynamut2_norm.csv'
+#outfile_dynamut_f = outdir_dynamut2 + gene + '_dynamut_norm.csv'
+outfile_dynamut2_f = outdir_dynamut2 + gene + '_dynamut2_norm.csv'
 
 #===============================
 # CALL: format_results_dynamut
@@ -69,4 +106,4 @@ print('Finished writing file:'
        , '\nExpected no. of cols:', len(dynamut2_df_f.columns)
        , '\n=============================================================')
 
-#%%#####################################################################
+#%%#####################################################################

dynamut/run_get_results_dynamut.py

@@ -17,8 +17,8 @@ my_host = 'http://biosig.unimelb.edu.au'
 #headers = {"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"}
 
 # TODO: add cmd line args
-#gene = 'gid'
-drug = 'streptomycin'
+# gene = 
+# drug = 
 datadir = homedir + '/git/Data/'
 indir = datadir + drug + '/input/'
 outdir = datadir + drug + '/output/'
@@ -41,4 +41,4 @@ get_results(url_file  = my_url_file
             , output_dir = outdir
             , outfile_suffix = my_suffix)
            
-########################################################################
+########################################################################

dynamut/split_csv_chain.sh

@@ -13,10 +13,25 @@ CHUNK=$3
 mkdir -p ${OUTDIR}/${CHUNK}/chain_added
 cd ${OUTDIR}/${CHUNK}/chain_added
 
-# makes the 2 dirs, hence ../..
+# makes the 3 dirs, hence ../..
 split ../../../${INFILE} -l ${CHUNK} -d snp_batch_
 
-# use case
-#~/git/LSHTM_analysis/dynamut/split_csv_chain.sh katg_mcsm_formatted_snps.csv snp_batches 50     #Date: 20/09/2021
+########################################################################
+# use cases
+# Date: 20/09/2021
+# sed -e 's/^/A /g' katg_mcsm_formatted_snps.csv > katg_mcsm_formatted_snps_chain.csv
+#~/git/LSHTM_analysis/dynamut/split_csv_chain.sh katg_mcsm_formatted_snps_chain.csv snp_batches 50
 
+# Date: 01/10/2021
+# sed -e 's/^/A /g' rpob_mcsm_formatted_snps.csv > rpob_mcsm_formatted_snps_chain.csv
+#~/git/LSHTM_analysis/dynamut/split_csv_chain.sh rpob_mcsm_formatted_snps_chain.csv snp_batches 50     
+
+# Date: 02/10/2021
+# sed -e 's/^/A /g' alr_mcsm_formatted_snps.csv > alr_mcsm_formatted_snps_chain.csv
+#~/git/LSHTM_analysis/dynamut/split_csv_chain.sh alr_mcsm_formatted_snps_chain.csv snp_batches 50  
+
+# Date: 05/10/2021
+#~/git/LSHTM_analysis/dynamut/split_csv_chain.sh alr_mcsm_formatted_snps_chain.csv snp_batches 20    
+  
 # add .txt to the files
+########################################################################

scripts/data_extraction.py

@@ -81,9 +81,6 @@ indir   = args.input_dir
 outdir  = args.output_dir
 make_dirs  = args.make_dirs
 
-#drug = 'streptomycin'
-#gene = 'gid'
-
 #%% input and output dirs and files
 #=======
 # dirs
@@ -1373,4 +1370,4 @@ if dr_muts.isin(other_muts).sum() & other_muts.isin(dr_muts).sum() > 0:
 print(u'\u2698' * 50,
       '\nEnd of script: Data extraction and writing files'
       '\n' + u'\u2698' * 50 )
-#%% end of script
+#%% end of script