Update ClinVar paths

reimandlab · Oct 4, 2020 · 80468ca · 80468ca
1 parent 8cfd7e5
commit 80468ca
Show file tree

Hide file tree

Showing 3 changed files with 7 additions and 10 deletions.
diff --git a/website/data/download.sh b/website/data/download.sh
@@ -95,11 +95,8 @@ cd mutations
 
 wget https://www.dropbox.com/s/lhou9rnwl6lwuwj/mc3.v0.2.8.PUBLIC.maf.gz
 wget https://www.dropbox.com/s/zodasbvinx339tw/ESP6500_muts_annotated.txt.gz
-# v2017:
-# wget https://www.dropbox.com/s/du2qe1skxwmuep2/clinvar_muts_annotated.txt.gz
-# v2019:
-wget ftp://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh37/clinvar_20190520.vcf.gz
-wget ftp://ftp.ncbi.nlm.nih.gov/pub/clinvar/xml/ClinVarFullRelease_2019-05.xml.gz
+wget ftp://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh37/clinvar_20201003.vcf.gz
+wget ftp://ftp.ncbi.nlm.nih.gov/pub/clinvar/xml/ClinVarFullRelease_2020-10.xml.gz
 
 wget https://www.dropbox.com/s/pm74k3qwxrqmu2q/all_mimp_annotations_p085.rsav
 

diff --git a/website/data/mutations/annotate_clinvar.sh b/website/data/mutations/annotate_clinvar.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 ./ensure_annovar.sh
-file=clinvar_20190520.vcf.gz
+file=clinvar_20201003.vcf.gz
 gunzip ${file} -c > clinvar.avinput
 
 ./annovar/table_annovar.pl clinvar.avinput humandb/ -buildver hg19 -out clinvar_annotated -remove -protocol refGene -operation g -nastring . -thread 2 -otherinfo -vcfinput

diff --git a/website/imports/mutations/clinvar.py b/website/imports/mutations/clinvar.py
@@ -23,7 +23,7 @@ class ClinVarImporter(MutationImporter):
     name = 'clinvar'
     model = InheritedMutation
     default_path = 'data/mutations/clinvar_muts_annotated.txt.gz'
-    default_xml_path = 'data/mutations/ClinVarFullRelease_2019-05.xml.gz'
+    default_xml_path = 'data/mutations/ClinVarFullRelease_2020-10.xml.gz'
     header = [
         'Chr', 'Start', 'End', 'Ref', 'Alt', 'Func.refGene', 'Gene.refGene',
         'GeneDetail.refGene', 'ExonicFunc.refGene', 'AAChange.refGene', 'Otherinfo',
@@ -346,7 +346,7 @@ def import_disease_associations(self):
 
     def remove_muts_without_origin(self):
 
-        origin_blacklist = {
+        origin_exclusion_list = {
             'not applicable',
             'not provided',
             'not-reported',
@@ -355,12 +355,12 @@ def remove_muts_without_origin(self):
             'unknown'
         }
 
-        print('ClinVar mutations origin blacklist: ', origin_blacklist)
+        print('ClinVar mutations origin exclusion list: ', origin_exclusion_list)
 
         print('Removing ClinVar associations with blacklisted or missing origin; NOTE:')
         print('\torigin is not set also when the mutation was skipped due to other reasons, such as non-human species')
         removed_cnt = ClinicalData.query.filter(
-            or_(ClinicalData.origin == None, ClinicalData.origin.in_(origin_blacklist))
+            or_(ClinicalData.origin == None, ClinicalData.origin.in_(origin_exclusion_list))
         ).delete(synchronize_session='fetch')
         db.session.commit()
         print(f'Removed {removed_cnt} associations')