def test_annotate_prioritize_cds_1():
print("Tests annotation priority for overlapping transcripts (-). "
"Interval: 'III', '13465', '13466', 'H10E21.3', '0', '-' "
"Should return CDS")
qchrom = 'III'
qstart = 13465
qstop = 13466
qname = 'H10E21.3'
qscore = 0
qstrand = '-'
region_priority = [
['protein_coding', 'CDS'],
['protein_coding', 'exon'],
]
stranded = True,
# transcript_priority = transcript_priority_1()
# gene_priority = gene_priority_1()
chrom, start, end, name, score, strand, \
gene, rname, region, annotation = a.annotate(
qchrom, qstart, qstop, qname, qscore, qstrand,
stranded, region_priority, region_priority,
features_dict, cds_dict, keys
)
assert rname == 'H10E21.3a,H10E21.3b'
assert region == 'CDS'
def test_annotate_prioritize_cds_2():
print("Tests annotation priority for overlapping transcripts (-). "
"Interval: 'III', '13465', '13466', 'H10E21.3', '0', '-' "
"Should return CDS even if it's the 2nd priority.")
# interval = pybedtools.create_interval_from_list(
# ['III', '13465', '13466', 'H10E21.3', '0', '-']
# )
qchrom = 'III'
qstart = 13465
qstop = 13466
qname = 'H10E21.3'
qscore = 0
qstrand = '-'
region_priority = [
['protein_coding', '3UTR'],
['protein_coding', 'CDS'],
]
stranded = True,
chrom, start, end, name, score, strand, \
gene, rname, region, annotation = a.annotate(
qchrom, qstart, qstop, qname, qscore, qstrand,
stranded, region_priority, region_priority,
features_dict, cds_dict, keys
)
assert rname == 'H10E21.3a,H10E21.3b'
assert region == 'CDS'
def test_utr_classification_2():
print("This tests the same region (chr11:70266235-70266302:+ "
"as test_utr_classification_1, but re-orders the priority "
"such that 3utr is higher than 5utr. Supposed to return 3utr")
chroms = ['chr11']
db = 'test/data/gencode.v19.annotation.chr11.70M-71M.gtf.db'
species = 'hg19'
exons_dict, \
transcripts_dict, cds_dict, features_dict, \
keys = a.create_definitions(
db, chroms, species
)
qchrom = 'chr11'
qstart = 70266235
qstop = 70266302
qname = 'CTTN'
qscore = 0
qstrand = '+'
region_priority = [
['protein_coding', '3utr'],
['protein_coding', '5utr'],
['protein_coding', 'CDS'],
]
stranded = True,
chrom, start, end, name, score, strand, \
gene, rname, region, annotation = a.annotate(
qchrom, qstart, qstop, qname, qscore, qstrand,
stranded, region_priority, region_priority,
features_dict, cds_dict, keys
)
assert region == '3utr'
def test_annotate_prioritize_4():
print("Tests annotation priority for overlapping transcripts (-/+). "
"Interval: 'III', '16600', '16601', 'H10E21.1b', '0', '+' "
"Should return 5'UTR.")
# interval = pybedtools.create_interval_from_list(
# ['III', '16600', '16601', 'H10E21.1a', '0', '+']
# )
qchrom = 'III'
qstart = 16600
qstop = 16601
qname = 'H10E21.1b'
qscore = 0
qstrand = '+'
region_priority = [
['protein_coding', 'three_prime_utr'],
['protein_coding', 'five_prime_utr'],
['protein_coding', 'CDS'],
]
stranded = True,
chrom, start, end, name, score, strand, \
gene, rname, region, annotation = a.annotate(
qchrom, qstart, qstop, qname, qscore, qstrand,
stranded, region_priority, region_priority,
features_dict, cds_dict, keys
)
print(annotation)
assert rname == 'H10E21.1a' or rname == 'H10E21.1b' # don't know which transcript is returned, should clear that up
assert region == 'five_prime_utr'
def test_intergenic_1():
print("Tests a region that is intergenic (+)")
qchrom = 'chr19'
qstart = 10050000
qstop = 10006000
qname = 'intergenic'
qscore = 0
qstrand = '+'
region_priority = [
['protein_coding', '3utr'],
['protein_coding', '5utr'],
['protein_coding', 'CDS'],
]
stranded = True,
chrom, start, end, name, score, strand, \
gene, rname, region, annotation = a.annotate(
qchrom, qstart, qstop, qname, qscore, qstrand,
stranded, region_priority, region_priority,
chr19_features_dict, chr19_cds_dict, chr19_keys
)
print(annotation)
assert rname == 'intergenic' # don't know which transcript is returned, should clear that up
assert region == 'intergenic'
def test_annotate_distintron_1():
print("Tests annotation priority for overlapping transcripts (+). "
"Interval: 'chr21:46553734-46553788', 'ADARB1', '0', '+' "
"Should return distintron")
qchrom = 'chr21'
qstart = 46553734
qstop = 46553788
qname = 'ADARB1'
qscore = 0
qstrand = '+'
transcript_priority = [
['protein_coding', 'distintron500'],
['non_coding', 'proxintron500'],
]
gene_priority = [
['non_coding', 'proxintron500'],
['protein_coding', 'distintron500'],
]
stranded = True,
chrom, start, end, name, score, strand, \
gene, rname, region, annotation = a.annotate(
qchrom, qstart, qstop, qname, qscore, qstrand,
stranded, transcript_priority, gene_priority,
chr21_features_dict, chr21_cds_dict, chr21_keys
)
assert rname == 'ADARB1'
assert region == 'distintron500'
def test_annotate_cds_2():
print("Tests annotation priority for overlapping transcripts (-). "
"Interval: 'chr19:4852152-4852191', 'PLIN3', '0', '-' "
"Should return CDS")
# interval = pybedtools.create_interval_from_list(
# ['chr19', '4852152', '4852191', 'PLIN3', '0', '-']
# )
qchrom = 'chr19'
qstart = 4852152
qstop = 4852191
qname = 'PLIN3'
qscore = 0
qstrand = '-'
region_priority = [
['protein_coding', 'CDS'],
['non_coding', 'exon'],
]
stranded = True,
chrom, start, end, name, score, strand, \
gene, rname, region, annotation = a.annotate(
qchrom, qstart, qstop, qname, qscore, qstrand,
stranded, region_priority, region_priority,
chr19_features_dict, chr19_cds_dict, chr19_keys
)
# assert get_transcript_id(priority) == 'ENST00000589163.1'
assert region == 'CDS'
assert rname == 'PLIN3'
assert gene == 'ENSG00000105355.4'
def test_annotate_prioritize_noncoding_exon_2():
print("Tests annotation priority for overlapping transcripts (+). "
"Interval: 'chr19:5071035-5071036', 'KDM4B', '0', '+' "
"Should return a retained intron (noncoding exon)")
# interval = pybedtools.create_interval_from_list(
# ['chr19', '5071035', '5071036', 'KDM4B', '0', '+']
# )
region_priority = [['non_coding', 'exon'], ['protein_coding', 'CDS']]
qchrom = 'chr19'
qstart = 5071035
qstop = 5071036
qname = 'KDM4B'
qscore = 0
qstrand = '+'
stranded = True,
chrom, start, end, name, score, strand, \
gene, rname, region, annotation = a.annotate(
qchrom, qstart, qstop, qname, qscore, qstrand,
stranded, region_priority, region_priority,
chr19_features_dict, chr19_cds_dict, chr19_keys
)
assert rname == 'KDM4B'
assert gene == 'ENSG00000127663.10'
assert region == 'noncoding_exon'
def test_annotate_prioritize_cds_1():
print("Tests annotation priority for overlapping transcripts (+). "
"Interval: 'chr19', '5071035', '5071036', 'KDM4B', '0', '+' "
"Should return CDS")
# interval = pybedtools.create_interval_from_list(
# ['chr19', '5071035', '5071036', 'KDM4B', '0', '+']
# )
qchrom = 'chr19'
qstart = 5071035
qstop = 5071036
qname = 'KDM4B'
qscore = 0
qstrand = '+'
region_priority = [
['protein_coding', 'CDS'],
['protein_coding', 'exon'],
]
stranded = True
chrom, start, end, name, score, strand, \
gene, rname, region, annotation = a.annotate(
qchrom, qstart, qstop, qname, qscore, qstrand,
stranded, region_priority, region_priority,
chr19_features_dict, chr19_cds_dict, chr19_keys
)
# assert get_transcript_id(priority) == 'ENST00000159111.4'
assert rname == 'KDM4B'
assert gene == 'ENSG00000127663.10'
assert region == 'CDS'