reading chromosomes X and Y

EGA-archive · Oct 18, 2024 · 535b73e · 535b73e
1 parent d9028cd
commit 535b73e
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 2 deletions.
diff --git a/.dockerignore b/.dockerignore
@@ -1,2 +1,4 @@
 files/vcf/*
-files/vcf/files_to_read/*
+files/vcf/files_to_read/*
+*.vcf.gz
+*.vcf.bgz
diff --git a/conf/conf.py b/conf/conf.py
@@ -4,7 +4,7 @@
 
 #### VCF Conversion config parameters ####
 allele_frequency=1 # introduce float number, leave 1 if you want to convert all the variants
-reference_genome='GRCh38' # Choose one between NCBI36, GRCh37, GRCh38
+reference_genome='GRCh37' # Choose one between NCBI36, GRCh37, GRCh38
 datasetId='COVID_pop11_fin_2'
 case_level_data=False
 

diff --git a/genomicVariations_vcf.py b/genomicVariations_vcf.py
@@ -434,6 +434,10 @@ def generate(dict_properties):
             '''
             chromos=re.sub(r"</?\[>", "", chrom)
             chromos=chromos.replace("chr","")
+            if 'X' in chrom:
+                chromos = '23'
+            elif 'Y' in chrom:
+                chromos = '24'
             if conf.reference_genome == 'GRCh37':
                 dict_to_xls['identifiers|genomicHGVSId'] = 'NC_0000'+str(chromos) + '.10' + ':' + 'g.' + str(start) + ref + '>' + alt[0]
             elif conf.reference_genome == 'GRCh38':