added documentation and removed test readouts

src/common/functions.py

@@ -33,7 +33,7 @@ def load_webapp_env():
     return webapp_env
 
 # converts one line from the variant table to a vcf record
-def variant_to_vcf(chr, pos, ref, alt, path):
+def variant_to_vcf(chr, pos, ref, alt, path, reference_genome="GRCh38"):
     #CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO
     chr_num = validate_chr(chr)
     if not chr_num:
@@ -46,7 +46,7 @@ def variant_to_vcf(chr, pos, ref, alt, path):
     vcf_record = [chr, str(pos), '.', str(ref), str(alt), '.', '.', '.']
 
     file = open(path, "w")
-    write_vcf_header(["##contig=<ID=%s>"%chr], output_func = file.write, tail = "\n")
+    write_vcf_header(["##contig=<ID=%s>"%chr], output_func = file.write, tail = "\n", reference_genome=reference_genome)
     file.write('\t'.join(vcf_record) + '\n')
     file.close()
     return True
@@ -203,11 +203,6 @@ def preprocess_variant(infile, do_liftover=False):
         if returncode != 0: return returncode, err_msg, command_output
         returncode, err_msg, command_output = execute_command(["mv", infile + ".leftnormalized", infile], "mv")
         if returncode != 0: return returncode, err_msg, command_output
-        print("GRCH37 LEFTNORMALIZE:")
-        with open(infile, "r") as f:
-            for line in f:
-                if not line.startswith('##contig='):
-                    print(f.read())
         # check
         returncode, err_msg, vcf_errors_pre = check_vcf(infile, ref_genome="GRCh37")
         if vcf_errors_pre != '': return 1, err_msg + " " + vcf_errors_pre, command_output
@@ -223,11 +218,6 @@ def preprocess_variant(infile, do_liftover=False):
         if returncode != 0: return returncode, err_msg, command_output
         returncode, err_msg, command_output = execute_command(["mv", infile + ".lifted", infile], "mv")
         if returncode != 0: return returncode, err_msg, command_output
-        print("LIFTED FILE:")
-        with open(infile, "r") as f:
-            for line in f:
-                if not line.startswith('##contig='):
-                    print(f.read())
 
     # leftnormalize
     returncode, err_msg, command_output = left_align_vcf(infile, outfile= infile + ".leftnormalized", ref_genome="GRCh38")
@@ -236,11 +226,6 @@ def preprocess_variant(infile, do_liftover=False):
     if returncode != 0: return returncode, err_msg, command_output
     returncode, err_msg, command_output = execute_command(["mv", infile + ".leftnormalized", infile], "mv")
     if returncode != 0: return returncode, err_msg, command_output
-    print("GRCH38 LEFTNORMALIZE:")
-    with open(infile, "r") as f:
-        for line in f:
-            if not line.startswith('##contig='):
-                print(f.read())
     # check
     returncode, err_msg, vcf_errors_pre = check_vcf(infile, ref_genome="GRCh38")
     if vcf_errors_pre != '': return 1, err_msg + " " + vcf_errors_pre, command_output

src/frontend_celery/start_celery.sh

@@ -51,7 +51,6 @@ pwd
 
 
 source .venv/bin/activate
-echo $(which python)
 export WEBAPP_ENV=$we
 vep_install_dir=$ROOT/tools/ensembl-vep-release-107.0
 cpan_dir=$vep_install_dir/cpan

src/frontend_celery/webapp/download/download_functions.py

@@ -780,44 +780,30 @@ def get_possible_classes_enigma_pms2_100(class_counts):
 
 
 
-def get_possible_classes_enigma_mlh_100(class_counts):
+
+
+
+def get_possible_classes_enigma_insight_mmr_100(class_counts):
     possible_classes = set()
 
     # pathogenic
-    #1 Very Strong (PVS1) AND ≥ 1 Strong (PVS1_Strong, PS1, PS2, PS3, PP1_Strong, PP3_Strong, PP4_Strong)
-    #1 Very Strong (PVS1) AND ≥ 2 Supporting (PS3_Supporting, PM2_Supporting, PM5_Supporting, PP1, PP3, PP4)
-    #USELESS: 1 Very Strong (PVS1) AND 1 Moderate (PVS1_Moderate, PS1_Moderate, PS2_Moderate, PS3_Moderate, PM3, PM5, PM6, PP1_Moderate, PP3_Moderate, PP4_Moderate)
-    #1 Very Strong (PVS1) AND ≥ 1 Moderate (PVS1_Moderate, PS1_Moderate, PS2_Moderate, PS3_Moderate, PM3, PM5, PM6, PP1_Moderate, PP3_Moderate, PP4_Moderate)
-
-    #≥ 2 Strong (PVS1_Strong, PS1, PS2, PS3, PP1_Strong, PP3_Strong, PP4_Strong)
-    #1 Strong (PVS1_Strong, PS1, PS2, PS3, PP1_Strong, PP3_Strong, PP4_Strong) AND ≥ 3 Moderate (PVS1_Moderate, PS1_Moderate, PS2_Moderate, PS3_Moderate, PM3, PM5, PM6, PP1_Moderate, PP3_Moderate, PP4_Moderate)
-    #1 Strong (PVS1_Strong, PS1, PS2, PS3, PP1_Strong, PP3_Strong, PP4_Strong) AND 2 Moderate (PVS1_Moderate, PS1_Moderate, PS2_Moderate, PS3_Moderate, PM3, PM5, PM6, PP1_Moderate, PP3_Moderate, PP4_Moderate) AND ≥ 2 Supporting (PS3_Supporting, PM2_Supporting, PM5_Supporting, PP1, PP3, PP4)
-    #1 Strong (PVS1_Strong, PS1, PS2, PS3, PP1_Strong, PP3_Strong, PP4_Strong) AND 1 Moderate (PVS1_Moderate, PS1_Moderate, PS2_Moderate, PS3_Moderate, PM3, PM5, PM6, PP1_Moderate, PP3_Moderate, PP4_Moderate) AND ≥ 4 Supporting (PS3_Supporting, PM2_Supporting, PM5_Supporting, PP1, PP3, PP4)
-
     if class_counts['pvs'] >= 2:
         possible_classes.add(5)
     if class_counts['pvs'] == 1:
         if class_counts['ps'] >= 1 or class_counts['pm'] >= 1 or class_counts['pp'] >= 2:
             possible_classes.add(5)
-    if class_counts['ps'] >= 2:
+    if class_counts['ps'] >= 3:
         possible_classes.add(5)
     if class_counts['ps'] == 1:
         if class_counts['pm'] >= 3 or (class_counts['pm'] == 2 and class_counts['pp'] >= 2) or (class_counts['pm'] == 1 and class_counts['pp'] >= 4):
             possible_classes.add(5)
 
     #Likely Pathogenic
-    #1 Strong (PVS1_Strong, PS1, PS2, PS3, PP1_Strong, PP4_Strong) AND 1 Moderate (PVS1_Moderate, PS1_Moderate, PS2_Moderate, PS3_Moderate, PM3, PM5, PM6, PP1_Moderate, PP3_Moderate, PP4_Moderate)
-    #1 Strong (PVS1_Strong, PS1, PS2, PS3, PP1_Strong, PP4_Strong) AND ≥ 2 Supporting (PS3_Supporting, PM2_Supporting, PM5_Supporting, PP1, PP3, PP4)
-    #1 Strong (PVS1_Strong, PS1, PS2, PS3, PP1_Strong, PP4_Strong) AND 2 Moderate (PVS1_Moderate, PS1_Moderate, PS2_Moderate, PS3_Moderate, PM3, PM5, PM6, PP1_Moderate, PP3_Moderate, PP4_Moderate)
-
-    #≥ 3 Moderate (PVS1_Moderate, PS1_Moderate, PS2_Moderate, PS3_Moderate, PM3, PM5, PM6, PP1_Moderate, PP3_Moderate, PP4_Moderate)
-    #2 Moderate (PVS1_Moderate, PS1_Moderate, PS2_Moderate, PS3_Moderate, PM3, PM5, PM6, PP1_Moderate, PP3_Moderate, PP4_Moderate) AND ≥ 2 Supporting (PS3_Supporting, PM2_Supporting, PM5_Supporting, PP1, PP3, PP4)
-    #1 Moderate (PVS1_Moderate, PS1_Moderate, PS2_Moderate, PS3_Moderate, PM3, PM5, PM6, PP1_Moderate, PP3_Moderate, PP4_Moderate) AND ≥ 4 Supporting (PS3_Supporting, PM2_Supporting, PM5_Supporting, PP1, PP3, PP4)
-
-    #1 Very Strong (PVS1) AND 1 Supporting (PS3_Supporting, PM2_Supporting, PM5_Supporting, PP1, PP3, PP4)
     if class_counts['ps'] == 1:
         if (class_counts['pm'] >= 1 and class_counts['pm'] <= 2) or class_counts['pp'] >= 2:
             possible_classes.add(4)
+    if class_counts['ps'] == 2:
+        possible_classes.add(4)
     if class_counts['pm'] >= 3:
         possible_classes.add(4)
     if class_counts['pm'] == 2 and class_counts['pp'] >= 2:
@@ -828,22 +814,25 @@ def get_possible_classes_enigma_mlh_100(class_counts):
         possible_classes.add(4)
 
     #Benign
-    #≥ 2 Strong (BS1, BS2, BS3, BS4, BP5_Strong)
-    #1 Stand Alone (BA1, BS1_Stand Alone)
     if class_counts['ba'] >= 1:
         possible_classes.add(1)
     if class_counts['bs'] >= 2:
         possible_classes.add(1)
 
     #Likely Benign
-    #1 Strong (BS1, BS2, BS3, BS4, BP5_Strong) AND 1 Supporting (BS3_Supporting, BS4_Supporting, BP4, BP5, BP7)
     if class_counts['bs'] == 1 and class_counts['bp'] == 1:
         possible_classes.add(2)
+    if class_counts['bp'] >= 2:
+        possible_classes.add(1)
 
     return possible_classes
 
 
 
+
+
+
+
 #######################################
 ########### DECISION MAKING ###########
 #######################################

src/frontend_celery/webapp/download/download_routes.py

@@ -200,30 +200,29 @@ def calculate_class(scheme_type = None, version = None, selected_classes = ''):
     elif 'acmg' in scheme_type:
         class_counts = download_functions.get_class_counts(selected_classes) # count how often we have each strength
 
+        # get a set of possible classes depending on selected criteria depending on the gene and version
         if 'brca1' in scheme_type and version == "v1.0.0":
-            possible_classes = download_functions.get_possible_classes_enigma_brca1_1_0_0(class_counts) # get a set of possible classes depending on selected criteria
+            possible_classes = download_functions.get_possible_classes_enigma_brca1_1_0_0(class_counts) 
         elif 'brca1' in scheme_type and version == "v1.1.0":
-            possible_classes = download_functions.get_possible_classes_enigma_brca12_1_1_0(class_counts) # get a set of possible classes depending on selected criteria
+            possible_classes = download_functions.get_possible_classes_enigma_brca12_1_1_0(class_counts) 
         elif 'brca2' in scheme_type and version == "v1.0.0":
-            possible_classes = download_functions.get_possible_classes_enigma_brca2_1_0_0(class_counts) # get a set of possible classes depending on selected criteria
+            possible_classes = download_functions.get_possible_classes_enigma_brca2_1_0_0(class_counts) 
         elif 'brca2' in scheme_type and version == "v1.1.0":
-            possible_classes = download_functions.get_possible_classes_enigma_brca12_1_1_0(class_counts) # get a set of possible classes depending on selected criteria
+            possible_classes = download_functions.get_possible_classes_enigma_brca12_1_1_0(class_counts) 
         elif 'palb2' in scheme_type and (version == "v1.0.0" or version == "v1.1.0"):
-            possible_classes = download_functions.get_possible_classes_enigma_palb2(class_counts) # get a set of possible classes depending on selected criteria
+            possible_classes = download_functions.get_possible_classes_enigma_palb2(class_counts) 
         elif 'tp53' in scheme_type and version == "v1.4.0":
-            possible_classes = download_functions.get_possible_classes_enigma_tp53(class_counts) # get a set of possible classes depending on selected criteria
+            possible_classes = download_functions.get_possible_classes_enigma_tp53(class_counts) 
         elif 'atm' in scheme_type and version == "v1.1.0":
-            possible_classes = download_functions.get_possible_classes_enigma_atm_1_1_0(class_counts) # get a set of possible classes depending on selected criteria
+            possible_classes = download_functions.get_possible_classes_enigma_atm_1_1_0(class_counts) 
         elif 'atm' in scheme_type and version == "v1.3.0":
-            possible_classes = download_functions.get_possible_classes_enigma_atm_1_3_0(class_counts) # get a set of possible classes depending on selected criteria
+            possible_classes = download_functions.get_possible_classes_enigma_atm_1_3_0(class_counts) 
         elif 'pten' in scheme_type and version == "v3.0.0":
-            possible_classes = download_functions.get_possible_classes_enigma_pten(class_counts) # get a set of possible classes depending on selected criteria
+            possible_classes = download_functions.get_possible_classes_enigma_pten(class_counts) 
         elif 'pten' in scheme_type and version == "v3.1.0":
-            possible_classes = download_functions.get_possible_classes_enigma_pten_310(class_counts) # get a set of possible classes depending on selected criteria
-        elif 'pms2' in scheme_type and version == "v1.0.0":
-            possible_classes = download_functions.get_possible_classes_enigma_pms2_100(class_counts) # get a set of possible classes depending on selected criteria
-        elif 'mlh1' in scheme_type and version == "v1.0.0":
-            possible_classes = download_functions.get_possible_classes_enigma_mlh_100(class_counts) # get a set of possible classes depending on selected criteria
+            possible_classes = download_functions.get_possible_classes_enigma_pten_310(class_counts) 
+        elif any([gene_symbol in scheme_type for gene_symbol in ['pms2', 'mlh1', 'msh2', 'msh6']]) and version == "v1.0.0": # MMR genes
+            possible_classes = download_functions.get_possible_classes_enigma_insight_mmr_100(class_counts) 
         else:
             raise RuntimeError('The class could not be calculated with given parameters. Did you specify a supported scheme and version? (either "acmg" or VUS "task-force" based)')
 

src/frontend_celery/webapp/tasks.py

@@ -258,9 +258,7 @@ def import_one_variant_heredicare(self, vid, user_id, user_roles, import_variant
 
 def fetch_heredicare(vid, user_id, conn:Connection, insert_variant = True, perform_annotation = True):
     heredicare_interface = Heredicare()
-    print("THE VID: " + str(vid))
     variant, status, message = heredicare_interface.get_variant(vid)
-    print(variant)
 
     if status != 'success': # error in variant retrieval from heredicare
         return status, message
@@ -566,7 +564,7 @@ def validate_and_insert_variant(chrom, pos, ref, alt, genome_build, conn: Connec
 
 
     tmp_file_path = functions.get_random_temp_file("vcf")
-    functions.variant_to_vcf(chrom, pos, ref, alt, tmp_file_path)
+    functions.variant_to_vcf(chrom, pos, ref, alt, tmp_file_path, genome_build)
 
     do_liftover = genome_build == 'GRCh37'
     returncode, err_msg, command_output = functions.preprocess_variant(tmp_file_path, do_liftover = do_liftover)

src/frontend_celery/webapp/templates/index.html

@@ -93,6 +93,19 @@ <h4>Overview</h4>
 <div class="bst bsb">
     <h4>Changelog</h4>
 
+    <div class="underline">v 1.13.7 (20.08.2024)</div>
+    <div>
+        General changes:
+        <ul>
+            <li>Added ACMG schemes for MMR genes (pms2, mlh1, msh2, msh6)</li>
+        </ul>
+        Bugfixes:
+        <ul>
+            <li>Fixed some minor issues with HerediCaRe up- and downloads</li>
+            <li>Downgraded CrossMap to v0.7.0 because v0.7.3 yields wrong results for specific variants</li>
+        </ul>
+    </div>
+
     <div class="underline">v 1.13.6 (16.08.2024)</div>
     <div>
         General changes: