folder name change

Snakefile

@@ -20,7 +20,7 @@ def usage():
         "             t : threshold for sequence consensus",
         "             m : MSA to run (muscle,mafft,poa,kalign,spoa,kalign3,clustalo).",
         "             n : exp name",
-        '\nEx: snakemake --config in="raw/covid.fastq" r="raw/ref_covid.fasta" b="1,15000" name="covid" d="10,100" s="100,200" t="50" m="mafft".',sep="\n")
+        '\nEx: snakemake --config in="covid.fastq" r="ref_covid.fasta" b="1,15000" name="covid" d="10,100" s="100,200" t="50" m="mafft".',sep="\n")
     sys.exit()
 
 #Argument testing
@@ -123,9 +123,9 @@ rule data_set_preparation :
         READ_FILE,
         REF_FILE
     output :
-        os.path.join(EXP,EXP_NAME,'raw','reads.fasta'),
-        os.path.join(EXP,EXP_NAME,'raw','ref.fasta'),
-        expand(os.path.join('{data_set}','raw','start_region.txt') , data_set = DATA_SETS)
+        os.path.join(EXP,EXP_NAME,'data','reads.fasta'),
+        os.path.join(EXP,EXP_NAME,'data','ref.fasta'),
+        expand(os.path.join('{data_set}','region_start','region_start.txt') , data_set = DATA_SETS)
     message :
         "Data set preparation for "+EXP + '/'+ EXP_NAME
     log:
@@ -142,8 +142,8 @@ rule data_set_preparation :
 #-------------------------------------------------------------------------------
 rule alignment_reads_on_ref :
     input :
-        os.path.join(EXP,EXP_NAME,'raw','ref.fasta') ,
-        os.path.join(EXP,EXP_NAME,'raw','reads.fasta')
+        os.path.join(EXP,EXP_NAME,'data','ref.fasta') ,
+        os.path.join(EXP,EXP_NAME,'data','reads.fasta')
     output :
         os.path.join(EXP,EXP_NAME,'alignement','aln_reads_on_ref.sam')
     message :
@@ -163,7 +163,7 @@ 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}','raw','start_region.txt')
+        start = os.path.join('{data_set}','region_start','region_start.txt')
     output :
         os.path.join('{data_set}','read_map_region','reads_r{region_size}.fasta')
     message:
@@ -369,8 +369,8 @@ rule abpoa_correction :
 #-------------------------------------------------------------------------------
 rule region_seq :
     input :
-        ref = EXP + '/'+ EXP_NAME + '/raw/ref.fasta',
-        start = "{data_set}/raw/start_region.txt"
+        ref = EXP + '/'+ EXP_NAME + '/data/ref.fasta',
+        start = "{data_set}/data/start_region.txt"
     output :
         "{data_set}/seq_selectes_region/region_seq_r{region_size}.fasta"
     message:

src/data_set_preparation.py

@@ -12,12 +12,6 @@ try:
 except:
 	sys.stderr.write("ERROR: The prefix for regions is missing.\n")
 
-try:
-    diploid = sys.argv[sys.argv.index("-d")]
-    diploid = True
-except:
-	diploid = False
-
 try:
     exp_name = sys.argv[sys.argv.index("-n")+1]
 except:
@@ -45,21 +39,13 @@ else:
 			end_starts = 1
 
 
-order = "ln -s " + input_read + " " + exp_name + "/raw/reads.fasta"
+order = "ln -s " + input_read + " " + exp_name + "/data/reads.fasta"
 os.system(order)
 
-if (diploid):
-    pass
-    order = "head -2 " + input_ref + " >" + exp_name + "/raw/ref_1.fasta"
-    os.system(order)
-    order = "tail -2 " + input_ref + " >" + exp_name + "/raw/ref_2.fasta"
-    os.system(order)
-else:
-    pass
-    order = "ln -s " + input_ref + " " + exp_name + "/raw/ref.fasta"
+order = "ln -s " + input_ref + " " + exp_name + "/data/ref.fasta"
 os.system(order)
 
 
 for start in starts:
-    order = "echo " + start + " >" + exp_name + "/" + prefix + start + "/raw/start_region.txt"
+    order = "echo " + start + " >" + exp_name + "/" + prefix + start + "/region_start/region_start.txt"
     os.system(order)