"snoRNA": "ncRNA",
"snRNA": "ncRNA"
}
with open(gff_file) as gff_fd:
for record in GFF.parse(gff_fd):
annotations_dict[record.id] = record
rcParams.update({'font.size': 7})
plt.figure(1, dpi=300, figsize=(8, 6))
index = 1
for sample, letter in zip(sample_set_names_list, letter_list_part1):
collection = CollectionVCF(from_file=True, vcf_file=sample + "_good.vcf")
plt.subplot(3, 2, index)
collection.get_location(annotations_dict, use_synonym=True, synonym_dict=annotation_synonym_dict)
location_pie(collection, annotation_colors=[],
ref_genome=None, explode=True, annotation_black_list=annotation_black_list,
allow_several_counts_of_record=False,
counts_filename="location_counts.t",
counts_dir="location_counts",
legend_font=6,
combine_mixed=True
)
plt.title("%s. %s" % (letter, sample), fontweight='bold')
index += 1
for format_ext in ["svg", "eps", "pdf", "png"]:
plt.savefig("good_mutation_pie_mixed_combined_normed.%s" % format_ext, bbox_inches='tight')
plt.close()
os.chdir(workdir)
os.system("mkdir -p %s" % sample_set_name)
os.chdir(sample_set_name)
os.system("mkdir -p %s %s" % (clustering_dir, rainfall_dir))
#os.system("pwd")
mutations = CollectionVCF(
vcf_file="../SNP_annotated_raw_vcf/%s_SNP.vcf" % sample_set_name,
from_file=True)
"""
mutations.rainfall_plot("%s_mutations" % (sample_set_name), ref_genome=reference, draw_gaps=True,
masked_regions=bad_region_dict)
"""
mutations.get_location(annotations_dict,
use_synonym=True,
synonym_dict=annotation_synonym_dict)
mutations.check_location(bad_regions)
mutations.check_by_ref_and_alt(ref_alt_variants["desaminases"], "DA")
annotation_black_list = [
"gene", "region", "ARS", "long_terminal_repeat", "noncoding_exon",
"intron", "repeat_region", "telomere", "gene_cassette",
"five_prime_UTR_intron"
]
"""
mutations.location_pie(annotation_black_list=annotation_black_list,
figsize=(30, 30),
pie_filename="%s_SNP_raw_variant_location_pie.svg" % sample_set_name,
full_genome_pie_filename="%s_SNP_raw_variant_location_full_genome_pie.svg" % sample_set_name,
counts_filename="%s_SNP_raw_variant_location_counts.t" % sample_set_name)
annotations_dict = {}
with open(gff_file) as gff_fd:
for record in GFF.parse(gff_fd):
annotations_dict[record.id] = record
for sample in samples_list:
print("Handling %s" % sample)
os.chdir(workdir)
os.chdir(sample)
if alignment_dir not in os.listdir("."):
continue
os.chdir(alignment_dir)
os.system("mkdir -p %s" % clustering_dir)
mutations = CollectionVCF(vcf_file=sample + suffix, from_file=True)
mutations.get_location(annotations_dict)
mutations.check_by_ref_and_alt(ref_alt_variants["desaminases"], "DA")
"""
for record in mutations:
print (record)
print(record.flags)
"""
#for record in mutations:
# print(record.description)
mutations.location_pie(annotation_black_list=[
"gene", "region", "ARS", "long_terminal_repeat"
],
figsize=(40, 40),
pie_filename="variant_location_pie.svg",
counts_filename="variant_location_counts.t")
print("Totaly %s mutations" % len(mutations))
