fix bug when no vcf is used in search and graphical general table

.gitignore

@@ -13,3 +13,4 @@ samplesIDs/*
 guides/
 *.csv
 PostProcess/CRISTA_predictors.pkl
+*.txt

PostProcess/process_summaries.py

@@ -24,6 +24,7 @@ def init_summary_by_sample(path_samplesID):
     dict_pop = {}
     dict_superpop = {}
     with open(f"{path_samplesID}", "r") as sid:
+        # print('pathid',path_samplesID)
         sid.readline()
         for line in sid:
             splitted = line.strip().split("\t")

PostProcess/resultIntegrator.py

@@ -897,6 +897,7 @@ def createBedforMultiAlternative(variantList, samples):
     if base_end>0 and base_end<=len(saveDict['Spacer+PAM']):
         end=base_end
 
+    # print('basestart:',base_start,' baseend:',base_end)
     if saveDict['REF/ALT_origin_(highest_CFD)'] == 'alt':
         value=base_counting(saveDict['Aligned_protospacer+PAM_ALT_(highest_CFD)'],start-1,end)
         #check count A
@@ -948,6 +949,7 @@ def createBedforMultiAlternative(variantList, samples):
 if check_personal_existence:
     columns_to_remove.remove(columns_of_dict.index('Annotation_personal')+1)
 for base in base_set.strip().split(','):
+    # print('base',base)
     if base == '_':
         break
     base=base.upper()

PostProcess/submit_job_automated_new_multiple_vcfs.sh

@@ -456,9 +456,10 @@ while read samples; do
 	# tail -n +2 $samples >> "$output_folder/.sampleID.txt"
 	grep -v '#' "${current_working_directory}/samplesIDs/$samples" >>"$output_folder/.sampleID.txt"
 done <$sampleID
-if [ "$vcf_name" != "_" ]; then
-	sed -i 1i"#SAMPLE_ID\tPOPULATION_ID\tSUPERPOPULATION_ID\tSEX" "$output_folder/.sampleID.txt"
-fi
+# if [ "$vcf_name" != "_" ]; then
+touch "$output_folder/.sampleID.txt"
+sed -i 1i"#SAMPLE_ID\tPOPULATION_ID\tSUPERPOPULATION_ID\tSEX" "$output_folder/.sampleID.txt"
+# fi
 
 sampleID=$output_folder/.sampleID.txt
 

pages/main_page.py

@@ -455,6 +455,7 @@ def change_url(
         with open(os.path.join(result_dir, ".list_vcfs.txt"), mode="w") as handle_vcf:
             if not ref_var:
                 vcf_folder = "_"
+                handle_vcf.write(f"{vcf_folder}\n")
             if VARIANTS_DATA[0] in ref_var:  # 1000 genomes
                 vcf_folder = "hg38_1000G"
                 sample_list.append("hg38_1000G.samplesID.txt")  # 1KGP samples
@@ -608,7 +609,7 @@ def change_url(
     else:
         be_start = int(be_start)
     if be_stop is None or not bool(be_stop):
-        be_stop = 1
+        be_stop = 0
     else:
         be_stop = int(be_stop)
     if be_nt is None or not bool(be_nt):

pages/pages_utils.py

@@ -214,7 +214,7 @@
 # CRISPR guides file
 GUIDES_FILE = ".guides.txt"
 # sample IDs file
-SAMPLES_FILE = ".sampleID.txt"
+SAMPLES_FILE = ".samplesID.txt"
 # PAMs file
 PAMS_FILE = ".pam.txt"
 # email file

pages/results_page.py

@@ -2906,9 +2906,8 @@ def update_table_general_profile(
                 data_guides[str(i) + "MM"] = "\n".join(tmp)
         else:
             for j in range(mms + 1):
-                tmp = [
-                    data_general_count.iloc[: (max_bulges + 1), j].values.astype(str)
-                ]
+                tmp = list(data_general_count.iloc[:, j].values.astype(str))
+                tmp=tmp[:max_bulges+1]
                 # tmp.insert(len(tmp)//2, "")
                 data_guides[str(j) + "MM"] = "\n".join(tmp)
         data_guides["Total"] = "\n".join(data_guides["Total"])