def test_merging_stop_codons_4(self):
"""
Situation:
* 1 stop codon split in two exons
"""
intervals = list_to_intervals([
# for this test no more than one interval is needed...
['1', '.', 'transcript', '20', '70', '.', '+', '.', '.'],
['1', '.', 'stop_codon', '40', '40', '.', '+', '.', '.'],
['1', '.', 'stop_codon', '60', '61', '.', '+', '.', '.'],
])
exons = list_to_intervals([
['1', '.', 'exon', '20', '40', '.', '+', '.', '.'],
['1', '.', 'exon', '60', '70', '.', '+', '.', '.'],
])
cdses = list_to_intervals([
['1', '.', 'CDS', '30', '39', '.', '+', '.', '.'],
])
expeted_new_cdses = [
['1', '.', 'CDS', '30', '40', '.', '+', '.', '.'],
['1', '.', 'CDS', '60', '61', '.', '+', '.', '.'],
]
expeted_utrs = [
['1', '.', 'UTR5', '20', '29', '.', '+', '.', '.'],
['1', '.', 'UTR3', '62', '70', '.', '+', '.', '.'],
]
new_cdses, utrs = segment._get_non_cds_exons(cdses, exons, intervals)
new_cdses, utrs = intervals_to_list(new_cdses), intervals_to_list(utrs)
self.assertEqual(expeted_new_cdses, new_cdses)
self.assertEqual(expeted_utrs, utrs)
# Negative strand:
intervals = list_to_intervals([
# for this test no more than one interval is needed...
['1', '.', 'transcript', '20', '80', '.', '-', '.', '.'],
['1', '.', 'stop_codon', '39', '40', '.', '-', '.', '.'],
['1', '.', 'stop_codon', '60', '60', '.', '-', '.', '.'],
])
exons = list_to_intervals([
['1', '.', 'exon', '20', '40', '.', '-', '.', '.'],
['1', '.', 'exon', '60', '80', '.', '-', '.', '.'],
])
cdses = list_to_intervals([
['1', '.', 'CDS', '61', '65', '.', '-', '.', '.'],
])
expeted_new_cdses = [
['1', '.', 'CDS', '60', '65', '.', '-', '.', '.'],
['1', '.', 'CDS', '39', '40', '.', '-', '.', '.'],
]
expeted_utrs = [
['1', '.', 'UTR3', '20', '38', '.', '-', '.', '.'],
['1', '.', 'UTR5', '66', '80', '.', '-', '.', '.'],
]
new_cdses, utrs = segment._get_non_cds_exons(cdses, exons, intervals)
new_cdses, utrs = intervals_to_list(new_cdses), intervals_to_list(utrs)
self.assertEqual(expeted_new_cdses, new_cdses)
self.assertEqual(expeted_utrs, utrs)
def test_1(self):
"""
Situation:
* no stop codons
* 1 "empty" exon before first cds
* 1 "empty" exon after last cds
* 1 exons shared by UTR5 and CDS
* 1 exons shared by UTR3 and CDS
"""
intervals = list_to_intervals([
# for this test no more than one interval is needed...
['1', '.', 'transcript', '20', '90', '.', '+', '.', '.'],
])
exons = list_to_intervals([
['1', '.', 'exon', '20', '30', '.', '+', '.', '.'],
['1', '.', 'exon', '40', '50', '.', '+', '.', '.'],
['1', '.', 'exon', '60', '70', '.', '+', '.', '.'],
['1', '.', 'exon', '80', '90', '.', '+', '.', '.'],
])
cdses = list_to_intervals([
['1', '.', 'CDS', '45', '50', '.', '+', '.', '.'],
['1', '.', 'CDS', '60', '65', '.', '+', '.', '.'],
])
expeted_new_cdses = [
['1', '.', 'CDS', '45', '50', '.', '+', '.', '.'],
['1', '.', 'CDS', '60', '65', '.', '+', '.', '.'],
]
expeted_utrs = [
['1', '.', 'UTR5', '20', '30', '.', '+', '.', '.'],
['1', '.', 'UTR5', '40', '44', '.', '+', '.', '.'],
['1', '.', 'UTR3', '66', '70', '.', '+', '.', '.'],
['1', '.', 'UTR3', '80', '90', '.', '+', '.', '.'],
]
new_cdses, utrs = segment._get_non_cds_exons(cdses, exons, intervals)
new_cdses, utrs = intervals_to_list(new_cdses), intervals_to_list(utrs)
self.assertEqual(expeted_new_cdses, new_cdses)
self.assertEqual(expeted_utrs, utrs)
# Also test for negative strand:
intervals, exons, cdses = map(reverse_strand,
[intervals, exons, cdses])
expeted_new_cdses = reverse_strand(expeted_new_cdses)
expeted_utrs = [
['1', '.', 'UTR3', '20', '30', '.', '-', '.', '.'],
['1', '.', 'UTR3', '40', '44', '.', '-', '.', '.'],
['1', '.', 'UTR5', '66', '70', '.', '-', '.', '.'],
['1', '.', 'UTR5', '80', '90', '.', '-', '.', '.'],
]
new_cdses, utrs = segment._get_non_cds_exons(cdses, exons, intervals)
new_cdses, utrs = intervals_to_list(new_cdses), intervals_to_list(utrs)
self.assertEqual(expeted_new_cdses, new_cdses)
self.assertEqual(expeted_utrs, utrs)
def test_merging_stop_codons_1(self):
"""
Situation:
* stop codon and CDS completely overlap
"""
intervals = list_to_intervals([
# for this test no more than is needed...
['1', '.', 'transcript', '20', '62', '.', '+', '.', '.'],
['1', '.', 'stop_codon', '60', '62', '.', '+', '.', '.'],
])
exons = list_to_intervals([
['1', '.', 'exon', '20', '40', '.', '+', '.', '.'],
['1', '.', 'exon', '60', '62', '.', '+', '.', '.'],
])
cdses = list_to_intervals([
['1', '.', 'CDS', '20', '40', '.', '+', '.', '.'],
['1', '.', 'CDS', '60', '62', '.', '+', '.', '.'],
])
expeted_new_cdses = [
['1', '.', 'CDS', '20', '40', '.', '+', '.', '.'],
['1', '.', 'CDS', '60', '62', '.', '+', '.', '.'],
]
expeted_utrs = []
new_cdses, utrs = segment._get_non_cds_exons(cdses, exons, intervals)
new_cdses, utrs = intervals_to_list(new_cdses), intervals_to_list(utrs)
self.assertEqual(expeted_new_cdses, new_cdses)
self.assertEqual(expeted_utrs, utrs)
# Negative strand:
intervals = list_to_intervals([
# for this test no more than is needed...
['1', '.', 'transcript', '20', '80', '.', '-', '.', '.'],
['1', '.', 'stop_codon', '20', '22', '.', '-', '.', '.'],
])
exons = list_to_intervals([
['1', '.', 'exon', '20', '22', '.', '+', '.', '.'],
['1', '.', 'exon', '60', '80', '.', '+', '.', '.'],
])
cdses = list_to_intervals([
['1', '.', 'CDS', '20', '22', '.', '-', '.', '.'],
['1', '.', 'CDS', '60', '80', '.', '-', '.', '.'],
])
expeted_new_cdses = [
['1', '.', 'CDS', '20', '22', '.', '-', '.', '.'],
['1', '.', 'CDS', '60', '80', '.', '-', '.', '.'],
]
expeted_utrs = []
new_cdses, utrs = segment._get_non_cds_exons(cdses, exons, intervals)
new_cdses, utrs = intervals_to_list(new_cdses), intervals_to_list(utrs)
self.assertEqual(expeted_new_cdses, new_cdses)
self.assertEqual(expeted_utrs, utrs)
def test_merging_stop_codons_3(self):
"""
Situation:
* 1 stop codon given on same exon as CDS, bit inside CDS!
"""
intervals = list_to_intervals([
# for this test no more than one interval is needed...
['1', '.', 'transcript', '60', '70', '.', '+', '.', '.'],
['1', '.', 'stop_codon', '63', '65', '.', '+', '.', '.'],
])
exons = list_to_intervals([
['1', '.', 'exon', '60', '70', '.', '+', '.', '.'],
])
cdses = list_to_intervals([
['1', '.', 'CDS', '60', '65', '.', '+', '.', '.'],
])
expeted_new_cdses = [
['1', '.', 'CDS', '60', '65', '.', '+', '.', '.'],
]
expeted_utrs = [
['1', '.', 'UTR3', '66', '70', '.', '+', '.', '.'],
]
new_cdses, utrs = segment._get_non_cds_exons(cdses, exons, intervals)
new_cdses, utrs = intervals_to_list(new_cdses), intervals_to_list(utrs)
self.assertEqual(expeted_new_cdses, new_cdses)
self.assertEqual(expeted_utrs, utrs)
# Negative strand:
intervals = list_to_intervals([
# for this test no more than one interval is needed...
['1', '.', 'transcript', '60', '70', '.', '-', '.', '.'],
['1', '.', 'stop_codon', '65', '67', '.', '-', '.', '.'],
])
exons = list_to_intervals([
['1', '.', 'exon', '60', '70', '.', '-', '.', '.'],
])
cdses = list_to_intervals([
['1', '.', 'CDS', '65', '70', '.', '-', '.', '.'],
])
expeted_new_cdses = [
['1', '.', 'CDS', '65', '70', '.', '-', '.', '.'],
]
expeted_utrs = [
['1', '.', 'UTR3', '60', '64', '.', '-', '.', '.'],
]
new_cdses, utrs = segment._get_non_cds_exons(cdses, exons, intervals)
new_cdses, utrs = intervals_to_list(new_cdses), intervals_to_list(utrs)
self.assertEqual(expeted_new_cdses, new_cdses)
self.assertEqual(expeted_utrs, utrs)