Merge pull request #19 from pinellolab/thread_limit_removal

Thread limit removal

.gitignore

@@ -15,3 +15,4 @@ guides/
 *.pkl
 *.txt
 *.zip
+PostProcess/dnaShape.pkl

PostProcess/annotate_final_results.py

@@ -21,6 +21,8 @@
 with open(inAnnotationFile, 'r') as annotations:
     for line in annotations:
         x = line.split('\t')
+        if 'vuoto.txt' in inAnnotationFile:
+            break
         annotations_list = str(x[3]).strip()
         if str(x[0]) in annotationDict.keys():
             annotationDict[str(x[0])][int(x[1]):int(x[2])] = str(x[0])+'\t'+annotations_list

PostProcess/pool_post_analisi_indel.py

@@ -17,8 +17,8 @@
 dict_folder = sys.argv[10]
 final_res = sys.argv[11]
 final_res_alt = sys.argv[12]
-# ncpus=int(sys.argv[13])
-ncpus = 4
+ncpus=int(sys.argv[13])
+# ncpus = 4
 
 
 def start_analysis(f):
@@ -35,8 +35,8 @@ def start_analysis(f):
     if 'vcf.gz' in f:
         chrs.append(f)
 
-t = 6
-if ncpus < 6:
-    t = ncpus
-with Pool(processes=t) as pool:
+# t = 6
+# if ncpus < 6:
+#     t = ncpus
+with Pool(processes=ncpus) as pool:
     pool.map(start_analysis, chrs)

PostProcess/pool_post_analisi_snp.py

@@ -35,8 +35,8 @@ def start_analysis(f):
     if '.fa' in f and '.fai' not in f:
         chrs.append(f)
 
-t = 6
-if ncpus < 6:
-    t = ncpus
-with Pool(processes=t) as pool:
+# t = 6
+# if ncpus < 6:
+#     t = ncpus
+with Pool(processes=ncpus) as pool:
     pool.map(start_analysis, chrs)

PostProcess/pool_search_indels.py

@@ -20,10 +20,11 @@
 output_folder = sys.argv[10]
 true_pam = sys.argv[11]
 current_working_directory = sys.argv[12]
+threads = int(sys.argv[13])
 
 
 def search_indels(f):
-    global use_thread
+    # global use_thread
     splitted = f.split('.')
     for elem in splitted:
         if "chr" in elem:
@@ -42,18 +43,18 @@ def search_indels(f):
     if 'vcf.gz' == f[-6:]:
         chrs.append(f)
 
-cpus = len(os.sched_getaffinity(0))
-if cpus - 3 < 10:
-    if cpus - 3 < 0:
-        t = 1
-    else:
-        t = cpus - 3
-else:
-    t = 10
+# cpus = len(os.sched_getaffinity(0))
+# if cpus - 3 < 10:
+#     if cpus - 3 < 0:
+#         t = 1
+#     else:
+#         t = cpus - 3
+# else:
+#     t = 10
 
 os.chdir(output_folder)
 # with Pool(processes=t) as pool:
-with Pool(processes=t) as pool:
+with Pool(processes=threads) as pool:
     pool.map(search_indels, chrs)
 
 

PostProcess/radar_chart_dict_generator.py

@@ -332,6 +332,8 @@ def fillDict(guide, guideDict, motifDict):
 
 # read all the annotations
 for line in inAnnotationsFile:
+    if 'vuoto.txt' in sys.argv[4]: #se vuoto.txt usato come annotazione, skippa lettura
+            break
     annotations_list = line.strip().split('\t')[3].split(',')
     for annotation in annotations_list:
         if '_personal' not in annotation:

PostProcess/submit_job_automated_new_multiple_vcfs.sh

@@ -329,7 +329,7 @@ while read vcf_f; do
 			cd $starting_dir
 			#commented to avoid indels search
 			#TODO REMOVE POOL SCRIPT FROM PROCESSING
-			./pool_search_indels.py "$ref_folder" "$vcf_folder" "$vcf_name" "$guide_file" "$pam_file" $bMax $mm $bDNA $bRNA "$output_folder" $true_pam "$current_working_directory/"
+			./pool_search_indels.py "$ref_folder" "$vcf_folder" "$vcf_name" "$guide_file" "$pam_file" $bMax $mm $bDNA $bRNA "$output_folder" $true_pam "$current_working_directory/" "$ncpus"
 			# mv "$output_folder/indels_${ref_name}+${vcf_name}_${pam_name}_${guide_name}_${mm}_${bDNA}_${bRNA}.targets.txt" "$output_folder/crispritz_targets"
 			awk '($3 !~ "n") {print $0}' "$output_folder/indels_${ref_name}+${vcf_name}_${pam_name}_${guide_name}_${mm}_${bDNA}_${bRNA}.targets.txt" >"$output_folder/indels_${ref_name}+${vcf_name}_${pam_name}_${guide_name}_${mm}_${bDNA}_${bRNA}.targets.txt.tmp"
 			mv "$output_folder/indels_${ref_name}+${vcf_name}_${pam_name}_${guide_name}_${mm}_${bDNA}_${bRNA}.targets.txt.tmp" "$output_folder/indels_${ref_name}+${vcf_name}_${pam_name}_${guide_name}_${mm}_${bDNA}_${bRNA}.targets.txt"