Choice nbr cores & add meta consensus in total out

msa_limit.py

@@ -16,6 +16,9 @@ def usage():
         "       IUPAC consensus sequence in the diploid case\n",
 
         "  optional:",
+        "    -c <int>",
+        "       default: 24",
+        "       number of cores",
         "    -n <string>",
         "       default: date and time of execution",
         "       name of the experiment",
@@ -53,6 +56,10 @@ def usage():
         "  run_config <string> <string> ...",
         "       Launches the pipeline from configuration file(s)",
         "        required: path to the configuration file(s).",
+        "        optional: ",
+        "         -c <int>",
+        "            default: 24",
+        "            number of cores",
         "  rulegraph",
         "       Displays a graph of the snakemake rules"
         ,sep="\n")
@@ -104,21 +111,32 @@ def summary():
             result = subprocess.Popen("ls experiments",shell=True,stdout=subprocess.PIPE)
             exp_names=result.communicate()[0].decode("utf-8")
             exp_names=re.sub('\n', r' ', exp_names)
+        result = subprocess.run("./src/total_data_format.py -m -n " + exp_names,shell=True)
         result = subprocess.run("./src/total_data_format.py -n " + exp_names,shell=True)
     else:
         print("No experiment has been launched yet")
 
 def run_config():
+    cores=""
+    try:
+        index_c=sys.argv.index("-c")
+        cores=sys.argv[index_c+1]
+        del sys.argv[index_c+1]
+        del sys.argv[index_c]
+    except:
+        pass
     try:
         path_config = sys.argv[2]
     except:
         print("ERROR: The configuration file(s) is missing.")
         print("Usage: msa_limit.py run_config <path config file>.")
         sys.exit()
+
+    cores=""
     i=2
     end_files = 0
     while ( not end_files  ):
-        result = subprocess.run(["./src/snakemake_launcher.sh",path_config])
+        result = subprocess.run(["./src/snakemake_launcher.sh",path_config,cores])
         i+=1
         try:
             path_config = sys.argv[i]
@@ -239,9 +257,13 @@ else:
             lines.append("O: [" + nb_region + "]")
         except:
             pass
+    cores=""
+    try:
+        cores = sys.argv[sys.argv.index("-c")+1]
+    except:
+        pass
 
-    print('\n'.join(lines))
-    #fichier = open(os.path.join("configuration_files",exp_name + ".yaml"), "w")
-    #fichier.write('\n'.join(lines))
-    #fichier.close()
-    #result = subprocess.run(["./src/snakemake_launcher.sh",os.path.join("configuration_files",exp_name + ".yaml")])
+    fichier = open(os.path.join("configuration_files",exp_name + ".yaml"), "w")
+    fichier.write('\n'.join(lines))
+    fichier.close()
+    result = subprocess.run(["./src/snakemake_launcher.sh",os.path.join("configuration_files",exp_name + ".yaml"),cores])

src/snakemake_launcher.sh

@@ -8,6 +8,10 @@ CURRENT_PATH=`pwd`
 conda activate $CURRENT_PATH/.conda_snakemake
 
 CONFIG_EXPERIMENT=$1
-
-echo "Launche Snakemake with $1"
-snakemake --configfile $1 -c24 --use-conda --rerun-incomplete
+if [[ $2 == "" ]]; then
+  CORES="24"
+else
+  CORES=$2
+fi
+echo "Launche Snakemake with $CONFIG_EXPERIMENT"
+snakemake --configfile $CONFIG_EXPERIMENT -c$CORES --use-conda --rerun-incomplete

src/total_data_format.py

@@ -7,6 +7,7 @@ ATTRIBUTES_TO_DISPLAY_THRESHOLD_INDEPENDANT=["time","memory"]
 PREFIX="region_"
 RESULT_FOLDER="results"
 NAME_DATA_FILE="data_align_t"
+NAME_META_CONSENSUS="consensus_consensus_"
 #Script use
 def use():
 	print("\nScript:\ttotal_data_formating.py",
@@ -38,6 +39,13 @@ else:
 			next_name = sys.argv[sys.argv.index("-n")+i]
 		except:
 			end_names = 1
+
+META_CONSENSUS=True
+try:
+    a = [sys.argv[sys.argv.index("-m")]]
+except:
+	META_CONSENSUS=False
+
 files={}
 i=0
 result = subprocess.run("if [ ! -d results_mean ]; then mkdir results_mean;fi",shell=True)
@@ -56,6 +64,9 @@ for i in range(len(exp_names)):
 					for root, dirs, current_files in os.walk(os.path.join(EXP,exp_names[i],dir,RESULT_FOLDER)):
 						for filename in current_files:
 							if re.search(NAME_DATA_FILE,filename):
+								search_meta_consensus=re.search(NAME_META_CONSENSUS,filename)
+								if ((search_meta_consensus and META_CONSENSUS) or (not search_meta_consensus and not META_CONSENSUS)):
+
 									threshold=filename.split(".")[0].split("_t")[1]
 									if (threshold not in files):
 										files[threshold]={}
@@ -123,18 +134,22 @@ for threshold in files :
 # Write to output files
 #-----------------------------------------------------------------------------
 for threshold in files :
+	add_name_file_output=""
 	attributes_to_display=ATTRIBUTES_TO_DISPLAY
+	if (not META_CONSENSUS):
 		if (threshold==last_threshold):
 			attributes_to_display+=ATTRIBUTES_TO_DISPLAY_THRESHOLD_INDEPENDANT
+	else:
+		add_name_file_output=NAME_META_CONSENSUS
 	for attribute in attributes_to_display:
 		#Header for files
 		if attribute in ATTRIBUTES_TO_DISPLAY_THRESHOLD_INDEPENDANT:
 			pass
-			output_mean=open("results_mean/data_mean_"+ attribute + ".csv","w")
-			output_all=open("results_all_regions/data_all_region_"+ attribute + ".csv","w")
+			output_mean=open("results_mean/data_" + add_name_file_output + "mean_"+ attribute + ".csv","w")
+			output_all=open("results_all_regions/data_" + add_name_file_output + "all_region_"+ attribute + ".csv","w")
 		else:
-			output_mean=open("results_mean/data_mean_"+ attribute + "_" + threshold + ".csv","w")
-			output_all=open("results_all_regions/data_all_region_"+ attribute + "_" + threshold + ".csv","w")
+			output_mean=open("results_mean/data_" + add_name_file_output + "mean_"+ attribute + "_" + threshold + ".csv","w")
+			output_all=open("results_all_regions/data_" + add_name_file_output + "all_region_"+ attribute + "_" + threshold + ".csv","w")
 		output_mean.write(",,")
 		output_all.write(",,")
 		for exp_name in data["order"]: