def tabix(args):
"""
Annotates primers with SNP information.
"""
vcf_in = VariantFile(args.vcf)
p_info = pt.create_tabix_df(args.p_info)
p_left = pt.primer_range_left(p_info["Sequence ID"],
p_info["Primer Rank"],
p_info["Chromosome"],
p_info["Primer Left Seq"],
p_info["Position1"])
p_right = pt.primer_range_right(p_info["Sequence ID"],
p_info["Primer Rank"],
p_info["Chromosome"],
p_info["Primer Right Seq"],
p_info["Position2"])
pn_left = pt.match_pinfo_to_vcf(p_left, vcf_in)
pn_right = pt.match_pinfo_to_vcf(p_right, vcf_in)
left_snps = pt.tabix_fetch(pn_left["Sequence ID"],
pn_left["Primer Rank"],
pn_left["Chromosome"],
pn_left["Position1"],
pn_left["Position2"],
vcf_in)
right_snps = pt.tabix_fetch(pn_right["Sequence ID"],
pn_right["Primer Rank"],
pn_right["Chromosome"],
pn_right["Position1"],
pn_right["Position2"],
vcf_in)
left_df = pt.tabix_results_to_df(left_snps, "L", "Left SNP Count")
right_df = pt.tabix_results_to_df(right_snps, "R", "Right SNP Count")
merged_df = pt.merge_left_right(left_df, right_df, p_info)
merged_df.to_csv(args.output, index=False)
def test_merge_left_right(self):
"""
Merge the left and right SNP dataframes.
"""
left = pt.primer_range_left(self.pvcf['Sequence ID'],
self.pvcf['Primer Rank'],
self.pvcf['Chromosome'],
self.pvcf['Primer Left Seq'],
self.pvcf['Position1'])
normalized = pt.match_pinfo_to_vcf(left, self.vcf_in)
left_snps = pt.tabix_fetch(normalized['Sequence ID'],
normalized['Primer Rank'],
normalized['Chromosome'],
normalized['Position1'],
normalized['Position2'], self.vcf_in)
left_df = pt.tabix_results_to_df(left_snps, "L", "Left SNP Count")
right = pt.primer_range_right(self.pvcf['Sequence ID'],
self.pvcf['Primer Rank'],
self.pvcf['Chromosome'],
self.pvcf['Primer Right Seq'],
self.pvcf['Position2'])
normalized = pt.match_pinfo_to_vcf(right, self.vcf_in)
right_snps = pt.tabix_fetch(normalized['Sequence ID'],
normalized['Primer Rank'],
normalized['Chromosome'],
normalized['Position1'],
normalized['Position2'], self.vcf_in)
right_df = pt.tabix_results_to_df(left_snps, "R", "Right SNP Count")
merged_df = pt.merge_left_right(left_df, right_df, self.pvcf)
self.assertTrue('Left SNP Count'
and 'Right SNP Count' in merged_df.columns)
def test_primer_range_right(self):
"""
Test the range info is added to the dataframe.
"""
self.assertEqual(
len(
pt.primer_range_left(self.pinfo['Sequence ID'],
self.pinfo['Primer Rank'],
self.pinfo['Chromosome'],
self.pinfo['Primer Right Seq'],
self.pinfo['Position2']).columns), 6)
def test_tabix_fetch(self):
"""
Fetches snp info and assigns to primers.
"""
left = pt.primer_range_left(self.pvcf['Sequence ID'],
self.pvcf['Primer Rank'],
self.pvcf['Chromosome'],
self.pvcf['Primer Left Seq'],
self.pvcf['Position1'])
normalized = pt.match_pinfo_to_vcf(left, self.vcf_in)
left_snps = pt.tabix_fetch(normalized['Sequence ID'],
normalized['Primer Rank'],
normalized['Chromosome'],
normalized['Position1'],
normalized['Position2'], self.vcf_in)
self.assertEqual(len(left_snps), 20)
def test_tabix_results_to_df(self):
"""
Generates a pd.DataFrame from the tabix results.
"""
left = pt.primer_range_left(self.pvcf['Sequence ID'],
self.pvcf['Primer Rank'],
self.pvcf['Chromosome'],
self.pvcf['Primer Left Seq'],
self.pvcf['Position1'])
normalized = pt.match_pinfo_to_vcf(left, self.vcf_in)
left_snps = pt.tabix_fetch(normalized['Sequence ID'],
normalized['Primer Rank'],
normalized['Chromosome'],
normalized['Position1'],
normalized['Position2'], self.vcf_in)
left_df = pt.tabix_results_to_df(left_snps, "L", "Left SNP Count")
self.assertEqual(left_df['Left SNP Count'][0], 10)