Skip to content

Commit

Permalink
Merge pull request #31 from openvar/develop_2_0
Browse files Browse the repository at this point in the history 
Develop 2 0
  • Loading branch information
Peter J. Freeman authored Apr 14, 2022
2 parents 8a9aaf6 + 0083bf7 commit 1baf789
Showing 1 changed file with 35 additions and 18 deletions.
53 changes: 35 additions & 18 deletions VariantFormatter/variantformatter.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -42,13 +42,13 @@ class GenomicDescriptions(object):
description reference nucleotide sequence corresponding to the specified range
"""
# Initialise and add initialisation data to the object
def __init__(self, p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build):
def __init__(self, p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build, variant_description):
if p_vcf == "None":
p_vcf = None
try:
if g_hgvs == "None":
g_hgvs = None
elif ('NC_012920.1' in g_hgvs.ac or 'NC_001807.4' in g_hgvs.ac) and "g" in g_hgvs.type:
elif ('NC_012920.1' in g_hgvs.ac or 'NC_001807.4' in g_hgvs.ac) and ":g." in variant_description:
gen_error = "The given reference sequence (%s) does not match the DNA type (g). For %s, " \
"please use (m). " \
"For g. variants, please use a linear genomic reference sequence" % (g_hgvs.ac, g_hgvs.ac)
Expand All @@ -62,6 +62,13 @@ def __init__(self, p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genom
if gen_error == "None":
gen_error = None

# Warn incorrect m. accession for hg19
try:
if ("NC_012920.1" in str(g_hgvs) or "NC_001807.4" in gen_error) and "hg19" in genome_build:
gen_error = "NC_012920.1 is not associated with genome build hg19, instead use genome build GRCh37"
except TypeError:
pass

# Create object
self.p_vcf = p_vcf
try:
Expand All @@ -87,7 +94,7 @@ class FormatVariant(object):
# Initialise and add initialisation data to the object
def __init__(self, variant_description, genome_build, vfo, transcript_model=None, specify_transcripts=None,
checkOnly=False, liftover=False):

self.variant_description = variant_description
self.vfo = vfo
# Add warning level
Expand All @@ -101,7 +108,8 @@ def __init__(self, variant_description, genome_build, vfo, transcript_model=None
hgvs_ref_bases = None
un_norm_hgvs = None
gen_error = "genome_build must be one of: 'GRCh37'; 'GRCh38'; 'hg19'; 'hg38'"
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build)
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build,
variant_description)
self.genomic_descriptions = gds
self.warning_level = 'genomic_variant_warning'
return
Expand All @@ -116,7 +124,8 @@ def __init__(self, variant_description, genome_build, vfo, transcript_model=None
hgvs_ref_bases = None
un_norm_hgvs = None
gen_error = "transcript_model must be one of: 'ensembl'; 'refseq'; 'all'"
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build)
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build,
variant_description)
self.genomic_descriptions = gds
self.warning_level = 'genomic_variant_warning'
return
Expand Down Expand Up @@ -164,7 +173,8 @@ def __init__(self, variant_description, genome_build, vfo, transcript_model=None
hgvs_ref_bases = None
un_norm_hgvs = None
gen_error = edit_warnings
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build)
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build,
variant_description)
self.genomic_descriptions = gds
self.warning_level = 'genomic_variant_warning'
return
Expand All @@ -191,7 +201,8 @@ def __init__(self, variant_description, genome_build, vfo, transcript_model=None
hgvs_ref_bases = None
un_norm_hgvs = None
gen_error = str(e)
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build)
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build,
variant_description)
self.genomic_descriptions = gds
self.warning_level = 'genomic_variant_warning'
return
Expand All @@ -206,7 +217,8 @@ def __init__(self, variant_description, genome_build, vfo, transcript_model=None
hgvs_ref_bases = None
un_norm_hgvs = None
gen_error = str(e)
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build)
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build,
variant_description)
self.genomic_descriptions = gds
self.warning_level = 'genomic_variant_warning'
return
Expand All @@ -217,7 +229,8 @@ def __init__(self, variant_description, genome_build, vfo, transcript_model=None
hgvs_ref_bases = None
un_norm_hgvs = None
gen_error = genomic_level['error']
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build)
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build,
variant_description)
self.genomic_descriptions = gds
self.warning_level = 'genomic_variant_warning'
return
Expand All @@ -233,7 +246,9 @@ def __init__(self, variant_description, genome_build, vfo, transcript_model=None
gen_error = None

# vcf2hgvs route
elif re.match('chr[\w\d]+\-', self.variant_description) or re.match('chr[\w\d]+:', self.variant_description) or re.match('[\w\d]+\-', self.variant_description) or re.match('[\w\d]+:', self.variant_description):
elif re.match('chr[\w\d]+\-', self.variant_description) or re.match(
'chr[\w\d]+:', self.variant_description) or re.match('[\w\d]+\-', self.variant_description) \
or re.match('[\w\d]+:', self.variant_description):
try:
genomic_level = formatter.vcf2hgvs_genomic(self.variant_description, self.genome_build, self.vfo)
except Exception as e:
Expand All @@ -246,7 +261,8 @@ def __init__(self, variant_description, genome_build, vfo, transcript_model=None
hgvs_ref_bases = None
un_norm_hgvs = None
gen_error = genomic_level['error']
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build)
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build,
variant_description)
self.genomic_descriptions = gds
self.warning_level = 'genomic_variant_warning'
return
Expand All @@ -262,22 +278,23 @@ def __init__(self, variant_description, genome_build, vfo, transcript_model=None
hgvs_ref_bases = None
un_norm_hgvs = None
gen_error = 'Variant description ' + self.variant_description + ' is not in a supported format'
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build)
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error, genome_build,
variant_description)
self.genomic_descriptions = gds
self.warning_level = 'submission_warning'
return

# Create genomic_descriptions object
try:
if recovery_error is not None:
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error=recovery_error,
genome_build=genome_build)
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, recovery_error,
genome_build, variant_description)
else:
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error=gen_error,
genome_build=genome_build)
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error,
genome_build, variant_description)
except UnboundLocalError:
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error=gen_error,
genome_build=genome_build)
gds = GenomicDescriptions(p_vcf, g_hgvs, un_norm_hgvs, hgvs_ref_bases, gen_error,
genome_build, variant_description)
self.genomic_descriptions = gds

# Return on checkonly
Expand Down

0 comments on commit 1baf789

Please sign in to comment.