def variants_to_protein_sequences_dataframe(
expressed_vcf="data/b16.f10/b16.expressed.vcf",
not_expressed_vcf="data/b16.f10/b16.not-expressed.vcf",
tumor_rna_bam="data/b16.f10/b16.combined.sorted.bam",
min_mapping_quality=0,
max_protein_sequences_per_variant=1,
variant_sequence_assembly=False):
"""
Helper function to load pair of VCFs and tumor RNA BAM
and use them to generate a DataFrame of expressed variant protein
sequences.
"""
expressed_variants = load_vcf(expressed_vcf)
not_expressed_variants = load_vcf(not_expressed_vcf)
combined_variants = VariantCollection(
list(expressed_variants) + list(not_expressed_variants))
samfile = load_bam(tumor_rna_bam)
allele_reads_generator = reads_overlapping_variants(
variants=combined_variants,
samfile=samfile,
min_mapping_quality=min_mapping_quality)
protein_sequences_generator = reads_generator_to_protein_sequences_generator(
allele_reads_generator,
max_protein_sequences_per_variant=max_protein_sequences_per_variant,
variant_sequence_assembly=variant_sequence_assembly)
df = protein_sequences_generator_to_dataframe(protein_sequences_generator)
return df, expressed_variants, combined_variants
def test_variants_to_protein_sequences_dataframe_filtered_all_reads_by_mapping_quality():
# since the B16 BAM has all MAPQ=255 values then all the reads should get dropped
# if we set the minimum quality to 256
variants = load_vcf("data/b16.f10/b16.vcf")
samfile = load_bam("data/b16.f10/b16.combined.sorted.bam")
allele_reads_generator = reads_overlapping_variants(
variants=variants,
samfile=samfile,
min_mapping_quality=256)
protein_sequences_generator = reads_generator_to_protein_sequences_generator(
allele_reads_generator,
max_protein_sequences_per_variant=1)
df = protein_sequences_generator_to_dataframe(protein_sequences_generator)
print(df)
eq_(
len(df),
0,
"Expected 0 entries, got %d: %s" % (len(df), df))
