renaming frame -> start_position

Snakefile

@@ -3,7 +3,7 @@ import os
 configfile: "config.yaml"
 
 EXP = "experiments"
-PREFIX_FRAME="frame_"
+PREFIX_START_POSITION="start_position_"
 #Script usage
 def usage():
     print("\nScript:\tsnakemake",
@@ -13,8 +13,8 @@ def usage():
         "Arguments: ",
         "  -required: i : nanoport long reads",
         "             r : reference sequences. (1 or 2)",
-        "  -optional: o : number of frames to be tested",
-        "             b : beginning(s) position of frame(s) (replacing nbr).",
+        "  -optional: o : number of start positions to be tested",
+        "             b : start position(s) (replacing -o).",
         "             d : depth(s).",
         "             s : sizes of regions",
         "             t : threshold for sequence consensus",
@@ -70,12 +70,12 @@ try:
     beginings = config['B']
 except:
     try:
-        nb_frame = int(config['O'])
+        nb_start_position = int(config['O'])
     except:
-        nb_frame = 1
+        nb_start_position = 1
     beginings=[]
-    first_begining = (genome_size_min - int(REGION_SIZES[-1]))/(nb_frame+1)
-    for i in range(nb_frame):
+    first_begining = (genome_size_min - int(REGION_SIZES[-1]))/(nb_start_position+1)
+    for i in range(nb_start_position):
         beginings.append(int((i+1)*first_begining))
 
 DATA_SETS=[]
@@ -84,9 +84,9 @@ i=0
 if type(beginings) != int: # equal : if len(beginings) > 1
    for start in beginings:
        i += 1
-       DATA_SETS.append(os.path.join(EXP,EXP_NAME,PREFIX_FRAME + str(start)))
+       DATA_SETS.append(os.path.join(EXP,EXP_NAME,PREFIX_START_POSITION + str(start)))
 else:
-    DATA_SETS.append(os.path.join(EXP,EXP_NAME,PREFIX_FRAME + str(beginings)))
+    DATA_SETS.append(os.path.join(EXP,EXP_NAME,PREFIX_START_POSITION + str(beginings)))
     beginings = [int(beginings)]
 
 
@@ -127,7 +127,7 @@ rule data_set_preparation :
     output :
         os.path.join(EXP,EXP_NAME,'data','reads.fasta'),
         os.path.join(EXP,EXP_NAME,'data','ref.fasta'),
-        expand(os.path.join('{data_set}','frame_start','frame_start.txt') , data_set = DATA_SETS)
+        expand(os.path.join('{data_set}','start_position.txt') , data_set = DATA_SETS)
     message :
         "Data set preparation for "+EXP + '/'+ EXP_NAME
     log:
@@ -135,7 +135,7 @@ rule data_set_preparation :
     conda:
         "env_conda/python3.yaml"
     shell:
-        'ORDER="./src/data_set_preparation.py -i {input} -p '+PREFIX_FRAME+' -n '+ EXP + '/'+EXP_NAME + ' -b ' + ' '.join(map(str,beginings)) + '";'
+        'ORDER="./src/data_set_preparation.py -i {input} -p '+PREFIX_START_POSITION+' -n '+ EXP + '/'+EXP_NAME + ' -b ' + ' '.join(map(str,beginings)) + '";'
         'echo "ORDER: $ORDER" >{log};'
         '$ORDER 2>&1 >>{log}'
 
@@ -165,7 +165,7 @@ rule alignment_reads_on_ref :
 rule reads_map_region :
     input :
         aln = os.path.join(EXP,EXP_NAME,'alignement','aln_reads_on_ref.sam'),
-        start = os.path.join('{data_set}','frame_start','frame_start.txt')
+        start = os.path.join('{data_set}','start_position.txt')
     output :
         os.path.join('{data_set}','read_map_region','reads_r{region_size}.fasta')
     message:
@@ -372,7 +372,7 @@ rule abpoa_correction :
 rule region_seq :
     input :
         ref = EXP + '/'+ EXP_NAME + '/data/ref.fasta',
-        start = "{data_set}/frame_start/frame_start.txt"
+        start = "{data_set}/start_position.txt"
     output :
         "{data_set}/seq_selectes_region/region_seq_r{region_size}.fasta"
     message:

msa_limit.py

@@ -24,9 +24,9 @@ def usage():
         "       name of the experiment",
         "    -o <int> ",
         "       default: 10",
-        "       number of frames to be tested",
+        "       number of start positions to be tested",
         "    -b <int>,<int>,...",
-        "       beginning(s) position of frame(s) (replacing -o)",
+        "       start position(s) (replacing -o)",
         "    -d <int>,<int>,...",
         "       default: 10,20,50",
         "       sequencing depth(s) (number of reads)",
@@ -108,11 +108,11 @@ def summary():
             exp_names=re.sub('\n', r' ', exp_names)
         if os.path.exists("results_mean"):
             result = subprocess.run("rm -r results_mean",shell=True)
-        if os.path.exists("results_all_frames"):
-            result = subprocess.run("rm -r results_all_frames",shell=True)
+        if os.path.exists("results_all_start_positions"):
+            result = subprocess.run("rm -r results_all_start_positions",shell=True)
         result = subprocess.run("./src/total_data_format.py -n " + exp_names,shell=True)
         result = subprocess.run("./src/total_data_format.py -m -n " + exp_names,shell=True)
-        print("See folders: results_mean & results_all_frames")
+        print("See folders: results_mean & results_all_start_positions")
     else:
         print("No experiment has been launched yet")
 
@@ -253,8 +253,8 @@ else:
         lines.append("B: [" + beginings + "]")
     except:
         try:
-            nb_frame = sys.argv[sys.argv.index("-o")+1]
-            lines.append("O: [" + nb_frame + "]")
+            nb_start_position = sys.argv[sys.argv.index("-o")+1]
+            lines.append("O: [" + nb_start_position + "]")
         except:
             pass
     cores=""

src/data_set_preparation.py

@@ -10,7 +10,7 @@ except:
 try:
     prefix = sys.argv[sys.argv.index("-p")+1]
 except:
-	sys.stderr.write("ERROR: The prefix for frame is missing.\n")
+	sys.stderr.write("ERROR: The prefix for start position is missing.\n")
 
 try:
     exp_name = sys.argv[sys.argv.index("-n")+1]
@@ -47,5 +47,5 @@ os.system(order)
 
 
 for start in starts:
-    order = "echo " + start + " >" + exp_name + "/" + prefix + start + "/frame_start/frame_start.txt"
+    order = "echo " + start + " >" + exp_name + "/" + prefix + start + "/start_position.txt"
     os.system(order)

src/total_data_format.py

@@ -4,7 +4,7 @@ import subprocess
 EXP = "experiments"
 ATTRIBUTES_TO_DISPLAY=["percentage_Identity","percentage_Error","percentage_Match"]
 ATTRIBUTES_TO_DISPLAY_THRESHOLD_INDEPENDANT=["time","memory"]
-PREFIX="frame_"
+PREFIX="start_position_"
 RESULT_FOLDER="results"
 NAME_DATA_FILE="data_align_t"
 NAME_META_CONSENSUS="meta_consensus_"
@@ -49,7 +49,7 @@ except:
 files={}
 i=0
 result = subprocess.run("if [ ! -d results_mean ]; then mkdir results_mean;fi",shell=True)
-result = subprocess.run("if [ ! -d results_all_frames ]; then mkdir results_all_frames;fi",shell=True)
+result = subprocess.run("if [ ! -d results_all_start_positions ]; then mkdir results_all_start_positions;fi",shell=True)
 #-----------------------------------------------------------------------------
 # Retrieved what was needed to read the files
 #-----------------------------------------------------------------------------
@@ -146,10 +146,10 @@ for threshold in files :
 		if attribute in ATTRIBUTES_TO_DISPLAY_THRESHOLD_INDEPENDANT:
 			pass
 			output_mean=open("results_mean/data_" + add_name_file_output + "mean_"+ attribute + ".csv","w")
-			output_all=open("results_all_frames/data_" + add_name_file_output + "all_frame_"+ attribute + ".csv","w")
+			output_all=open("results_all_start_positions/data_" + add_name_file_output + "all_start_position_"+ attribute + ".csv","w")
 		else:
 			output_mean=open("results_mean/data_" + add_name_file_output + "mean_"+ attribute + "_" + threshold + ".csv","w")
-			output_all=open("results_all_frames/data_" + add_name_file_output + "all_frame_"+ attribute + "_" + threshold + ".csv","w")
+			output_all=open("results_all_start_positions/data_" + add_name_file_output + "all_start_position_"+ attribute + "_" + threshold + ".csv","w")
 		output_mean.write(",,")
 		output_all.write(",,")
 		for exp_name in data["order"]: