def test_add_biotype_attribute1(self):
gene_content = {
'gene': create_interval_from_list(
['1', '.', 'gene', '1', '200', '.', '+', '.', 'gene_biotype "G";']
),
'transcript1': list_to_intervals([
['1', '.', 'CDS', '1', '5', '.', '+', '.', 'gene_biotype "G"; transcript_biotype "A";'],
['1', '.', 'ncRNA', '1', '5', '.', '+', '.', 'gene_biotype "G"; transcript_biotype "A";'],
['1', '.', 'intron', '1', '5', '.', '+', '.', '.'],
]),
'transcript2': list_to_intervals([
['1', '.', 'ncRNA', '1', '5', '.', '+', '.', 'gene_biotype "G"; transcript_biotype "B";'],
['1', '.', 'intron', '1', '5', '.', '+', '.', '.'],
]),
}
out = segment._add_biotype_attribute(gene_content)
for transcript_id, tr_intervals in sorted(out.items()):
if transcript_id == 'gene':
# I this case tjhi is single interval not a list of intervals:
self.assertEqual(tr_intervals.attrs['biotype'], 'A, B, G')
elif transcript_id == 'transcript1':
for interval in tr_intervals:
self.assertEqual(interval.attrs['biotype'], 'A')
elif transcript_id == 'transcript2':
for interval in tr_intervals:
self.assertEqual(interval.attrs['biotype'], 'B')
def test_all_good(self):
gtf_in_data = list_to_intervals([
['1', '.', 'gene', '400', '500', '.', '+', '.',
'gene_id "G2";'],
['1', '.', 'transcript', '400', '500', '.', '+', '.',
'gene_id "G2"; transcript_id "T3";'],
['1', '.', 'exon', '400', '430', '.', '+', '.',
'gene_id "G2"; transcript_id "T3"; exon_number "1"'],
['1', '.', 'CDS', '410', '430', '.', '+', '.',
'gene_id "G2"; transcript_id "T3";'],
['1', '.', 'exon', '470', '500', '.', '+', '.',
'gene_id "G2"; transcript_id "T3"; exon_number "2"'],
['1', '.', 'CDS', '470', '490', '.', '+', '.',
'gene_id "G2"; transcript_id "T3";'],
])
gtf_in_file = make_file_from_list(intervals_to_list(gtf_in_data))
gtf_out = tempfile.NamedTemporaryFile(mode='w+', delete=False)
gtf_out.close()
genome_file = make_file_from_list(
[
['1', '2000'],
['MT', '500'],
], bedtool=False)
gtf_out_data = list_to_intervals(make_list_from_file(segment.get_regions(
gtf_in_file, gtf_out.name, genome_file), fields_separator='\t'))
expected = list_to_intervals([
['1', '.', 'intergenic', '1', '399', '.', '+', '.',
'gene_id "."; transcript_id ".";'],
['1', '.', 'intergenic', '1', '2000', '.', '-', '.',
'gene_id "."; transcript_id ".";'],
['1', '.', 'transcript', '400', '500', '.', '+', '.',
'gene_id "G2";transcript_id "T3"; biotype ".";'],
['1', '.', 'UTR5', '400', '409', '.', '+', '.',
'gene_id "G2";exon_number "1";transcript_id "T3"; biotype ".";'],
['1', '.', 'gene', '400', '500', '.', '+', '.',
'gene_id "G2"; biotype "[.]";'],
['1', '.', 'CDS', '410', '430', '.', '+', '.',
'gene_id "G2";transcript_id "T3"; biotype ".";'],
['1', '.', 'intron', '431', '469', '.', '+', '.',
'gene_id "G2"; transcript_id "T3"; biotype ".";'],
['1', '.', 'CDS', '470', '490', '.', '+', '.',
'gene_id "G2";transcript_id "T3"; biotype ".";'],
['1', '.', 'UTR3', '491', '500', '.', '+', '.',
'gene_id "G2";exon_number "2";transcript_id "T3"; biotype ".";'],
['1', '.', 'intergenic', '501', '2000', '.', '+', '.',
'gene_id "."; transcript_id ".";'],
['MT', '.', 'intergenic', '1', '500', '.', '+', '.',
'gene_id "."; transcript_id ".";'],
['MT', '.', 'intergenic', '1', '500', '.', '-', '.',
'gene_id "."; transcript_id ".";'],
])
self.assertEqual(expected, gtf_out_data)
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_get_introns(self):
exons = list_to_intervals([
['1', '.', 'exon', '1', '10', '.', '+', '.', 'transcript_id "42"; exon_number "1"'],
['1', '.', 'exon', '20', '30', '.', '+', '.', 'gene_name "42"; '],
['1', '.', 'exon', '40', '50', '.', '+', '.', 'gene_id "FHIT"; useless_data "3"'],
])
expected = list_to_intervals([
['1', '.', 'exon', '11', '19', '.', '+', '.', 'transcript_id "42";'],
['1', '.', 'exon', '31', '39', '.', '+', '.', 'gene_id "FHIT";'],
])
self.assertEqual(segment._get_introns(exons), expected)
def test_complement(self):
genome_file = make_file_from_list(
[
['1', '2000'],
['2', '1000'],
['MT', '500'],
], bedtool=False)
genes = list_to_intervals([
['1', '.', 'gene1', '200', '400', '.', '+', '.', '.'],
['1', '.', 'gene2', '300', '600', '.', '+', '.', '.'],
['1', '.', 'gene3', '200', '500', '.', '+', '.', '.'],
['2', '.', 'gene4', '100', '200', '.', '+', '.', '.'],
['2', '.', 'gene5', '100', '300', '.', '-', '.', '.'],
])
complement = make_list_from_file(segment._complement(genes, genome_file, '+'), fields_separator='\t')
empty_col8 = 'ID "inter%s"; gene_id "."; transcript_id ".";'
expected = [
['1', '.', 'intergenic', '1', '199', '.', '+', '.', empty_col8 % "P00000"],
['1', '.', 'intergenic', '601', '2000', '.', '+', '.', empty_col8 % "P00001"],
['2', '.', 'intergenic', '1', '99', '.', '+', '.', empty_col8 % "P00002"],
['2', '.', 'intergenic', '201', '1000', '.', '+', '.', empty_col8 % "P00003"],
['MT', '.', 'intergenic', '1', '500', '.', '+', '.', empty_col8 % "P00004"],
]
self.assertEqual(complement, expected)
def test_all_good(self):
gtf_in_data = list_to_intervals([
['1', '.', 'gene', '400', '500', '.', '+', '.', 'gene_id "G2";'],
['1', '.', 'transcript', '400', '500', '.', '+', '.', 'gene_id "G2"; transcript_id "T3";'],
['1', '.', 'exon', '400', '430', '.', '+', '.', 'gene_id "G2"; transcript_id "T3"; exon_number "1"'],
['1', '.', 'CDS', '410', '430', '.', '+', '.', 'gene_id "G2"; transcript_id "T3";'],
['1', '.', 'exon', '470', '500', '.', '+', '.', 'gene_id "G2"; transcript_id "T3"; exon_number "2"'],
['1', '.', 'CDS', '470', '490', '.', '+', '.', 'gene_id "G2"; transcript_id "T3";'],
])
gtf_in_file = make_file_from_list(intervals_to_list(gtf_in_data))
gtf_out = get_temp_file_name()
genome_file = make_file_from_list([
['1', '2000'],
['MT', '500'],
], bedtool=False)
segment.get_segments(gtf_in_file, gtf_out, genome_file)
gtf_out_data = list_to_intervals(make_list_from_file(gtf_out, fields_separator='\t'))
expected = list_to_intervals([
['1', '.', 'intergenic', '1', '399', '.', '+', '.', 'gene_id "."; transcript_id ".";'],
['1', '.', 'intergenic', '1', '2000', '.', '-', '.', 'gene_id "."; transcript_id ".";'],
['1', '.', 'transcript', '400', '500', '.', '+', '.', 'gene_id "G2";transcript_id "T3"; biotype ".";'],
['1', '.', 'UTR5', '400', '409', '.', '+', '.',
'gene_id "G2";exon_number "1";transcript_id "T3"; biotype ".";'],
['1', '.', 'gene', '400', '500', '.', '+', '.', 'gene_id "G2"; biotype "[.]";'],
['1', '.', 'CDS', '410', '430', '.', '+', '.', 'gene_id "G2";transcript_id "T3"; biotype ".";'],
['1', '.', 'intron', '431', '469', '.', '+', '.', 'gene_id "G2"; transcript_id "T3"; biotype ".";'],
['1', '.', 'CDS', '470', '490', '.', '+', '.', 'gene_id "G2";transcript_id "T3"; biotype ".";'],
['1', '.', 'UTR3', '491', '500', '.', '+', '.',
'gene_id "G2";exon_number "2";transcript_id "T3"; biotype ".";'],
['1', '.', 'intergenic', '501', '2000', '.', '+', '.', 'gene_id "."; transcript_id ".";'],
['MT', '.', 'intergenic', '1', '500', '.', '+', '.', 'gene_id "."; transcript_id ".";'],
['MT', '.', 'intergenic', '1', '500', '.', '-', '.', 'gene_id "."; transcript_id ".";'],
])
self.assertEqual(expected, gtf_out_data)
out_dir = os.path.dirname(os.path.abspath(gtf_out))
self.assertTrue(os.path.isfile(os.path.join(out_dir, region.REGIONS_FILE)))
self.assertTrue(os.path.isfile(os.path.join(out_dir, 'landmarks.bed.gz')))
def test_no_exons(self):
"""
Fail if no exons are given.
"""
intervals = list_to_intervals([
['1', '.', 'transcript', '1', '100', '.', '+', '.', '.'],
])
with self.assertRaises(AssertionError):
segment._process_transcript_group(intervals)
def test_filter_col8(self):
interval = list_to_intervals([
['1', '.', 'CDS', '1', '2', '.', '+', '.', 'gene_name "B"; transcript_id "A"; key42 "A"; key43: "?";'],
])[0]
expected = 'gene_name "B"; transcript_id "A";'
self.assertEqual(segment._filter_col8(interval), expected)
expected = 'gene_name "B"; key42 "A";'
self.assertEqual(segment._filter_col8(interval, keys=['gene_name', 'key42']), expected)
def setUp(self):
warnings.simplefilter("ignore", (ResourceWarning, ImportWarning))
self.gtf_data = list_to_intervals([
['1', '.', 'intergenic', '1', '99', '.', '+', '.',
'gene_id "."; transcript_id ".";'],
# Gene #1:
['1', '.', 'gene', '100', '499', '.', '+', '.',
'gene_id "G1";'],
# Transcript #1
['1', '.', 'transcript', '100', '249', '.', '+', '.',
'gene_id "G1"; transcript_id "T1";'],
['1', '.', 'UTR5', '100', '149', '.', '+', '.',
'gene_id "G1"; transcript_id "T1"; exon_number "1";'],
['1', '.', 'intron', '150', '199', '.', '+', '.',
'gene_id "G1"; transcript_id "T1";'],
['1', '.', 'CDS', '200', '229', '.', '+', '.',
'gene_id "G1"; transcript_id "T1"; exon_number "2";'],
['1', '.', 'intron', '230', '239', '.', '+', '.',
'gene_id "G1"; transcript_id "T1";'],
['1', '.', 'UTR3', '240', '249', '.', '+', '.',
'gene_id "G1"; transcript_id "T1"; exon_number "3";'],
# Transcript #2
['1', '.', 'transcript', '240', '499', '.', '+', '.',
'gene_id "G1"; transcript_id "T2";'],
['1', '.', 'CDS', '240', '299', '.', '+', '.',
'gene_id "G1"; transcript_id "T2"; exon_number "1";'],
['1', '.', 'intron', '300', '399', '.', '+', '.',
'gene_id "G1"; transcript_id "T2";'],
['1', '.', 'CDS', '400', '499', '.', '+', '.',
'gene_id "G1"; transcript_id "T2"; exon_number "2";'],
# intergenic
['1', '.', 'intergenic', '500', '599', '.', '+', '.',
'gene_id "."; transcript_id ".";'],
# Gene #1:
['1', '.', 'gene', '600', '999', '.', '+', '.',
'gene_id "G2";'],
# Transcript #3
['1', '.', 'transcript', '600', '799', '.', '+', '.',
'gene_id "G2"; transcript_id "T3";'],
['1', '.', 'CDS', '600', '649', '.', '+', '.',
'gene_id "G2"; transcript_id "T3"; exon_number "1";'],
['1', '.', 'intron', '650', '749', '.', '+', '.',
'gene_id "G2"; transcript_id "T3";'],
['1', '.', 'CDS', '750', '799', '.', '+', '.',
'gene_id "G2"; transcript_id "T3"; exon_number "2";'],
])
self.gtf = make_file_from_list(intervals_to_list(self.gtf_data))
self.strange = get_temp_file_name()
self.cross_tr = get_temp_file_name()
self.out = get_temp_file_name()
def test_check_consistency_fail3(self):
"""
Unallowed order of types.
"""
intervals = list_to_intervals([
['1', '.', 'transcript', '1', '100', '.', '+', '.', '.'],
['1', '.', 'UTR3', '1', '49', '.', '+', '.', '.'],
['1', '.', 'CDS', '50', '100', '.', '+', '.', '.'],
])
with self.assertRaises(AssertionError):
segment._check_consistency(intervals)
def test_check_consistency_fail2(self):
"""
Overlaping intervals.
"""
intervals = list_to_intervals([
['1', '.', 'transcript', '1', '100', '.', '+', '.', '.'],
['1', '.', 'UTR5', '1', '50', '.', '+', '.', '.'],
['1', '.', 'CDS', '50', '100', '.', '+', '.', '.'],
])
with self.assertRaises(AssertionError):
segment._check_consistency(intervals)
def test_check_consistency_pass(self): # pylint: disable=no-self-use
intervals = list_to_intervals([
['1', '.', 'transcript', '1', '100', '.', '+', '.', '.'],
['1', '.', 'UTR5', '1', '9', '.', '+', '.', '.'],
['1', '.', 'CDS', '10', '49', '.', '+', '.', '.'],
['1', '.', 'intron', '50', '59', '.', '+', '.', '.'],
['1', '.', 'CDS', '60', '89', '.', '+', '.', '.'],
['1', '.', 'UTR3', '90', '100', '.', '+', '.', '.'],
])
# If no AssertionError is raised, this is succes:
segment._check_consistency(intervals)
def setUp(self):
warnings.simplefilter("ignore", (ResourceWarning, ImportWarning))
self.gtf_data = list_to_intervals([
[
'1', '.', 'intergenic', '1', '2', '.', '+', '.',
'gene_id "."; transcript_id ".";'
],
# Gene #1:
['1', '.', 'gene', '3', '7', '.', '+', '.', 'gene_id "G1";'],
# Transcript #1
[
'1', '.', 'transcript', '3', '6', '.', '+', '.',
'gene_id "G1"; transcript_id "T1";'
],
[
'1', '.', 'CDS', '3', '3', '.', '+', '.',
'gene_id "G1"; transcript_id "T1"; exon_number "2";'
],
[
'1', '.', 'intron', '4', '6', '.', '+', '.',
'gene_id "G1"; transcript_id "T1";'
],
[
'1', '.', 'UTR3', '5', '6', '.', '+', '.',
'gene_id "G1"; transcript_id "T1"; exon_number "3";'
],
# Transcript #2
[
'1', '.', 'transcript', '4', '7', '.', '+', '.',
'gene_id "G1"; transcript_id "T2";'
],
[
'1', '.', 'ncRNA', '4', '5', '.', '+', '.',
'gene_id "G1"; transcript_id "T2"; exon_number "1";'
],
[
'1', '.', 'intron', '6', '6', '.', '+', '.',
'gene_id "G1"; transcript_id "T2";'
],
[
'1', '.', 'ncRNA', '7', '7', '.', '+', '.',
'gene_id "G1"; transcript_id "T2"; exon_number "2";'
],
# intergenic
[
'1', '.', 'intergenic', '8', '9', '.', '+', '.',
'gene_id "."; transcript_id ".";'
],
])
self.gtf = make_file_from_list(intervals_to_list(self.gtf_data))
def test_all_good(self):
"""
* second gene has no 'gene' interval - but it is present in output as it should
* last interval is on chromosome 2, but it is not in the output
"""
gtf_data = list_to_intervals([
['1', '.', 'gene', '100', '300', '.', '+', '.',
'gene_id "G1";'],
['1', '.', 'transcript', '100', '250', '.', '+', '.',
'gene_id "G1"; transcript_id "T1";'],
['1', '.', 'exon', '100', '150', '.', '+', '.',
'gene_id "G1"; transcript_id "T1"; exon_number "1";'],
['1', '.', 'exon', '200', '250', '.', '+', '.',
'gene_id "G1"; transcript_id "T1"; exon_number "2";'],
['1', '.', 'transcript', '150', '300', '.', '+', '.',
'gene_id "G1"; transcript_id "T2";'],
['1', '.', 'exon', '150', '200', '.', '+', '.',
'gene_id "G1"; transcript_id "T2"; exon_number "1";'],
['1', '.', 'exon', '250', '300', '.', '+', '.',
'gene_id "G1"; transcript_id "T2"; exon_number "2";'],
['1', '.', 'transcript', '400', '500', '.', '+', '.',
'gene_id "G2"; transcript_id "T3";'],
['1', '.', 'exon', '400', '430', '.', '+', '.',
'gene_id "G2"; transcript_id "T3"; exon_number "1"'],
['1', '.', 'CDS', '410', '430', '.', '+', '.',
'gene_id "G2"; transcript_id "T3";'],
['1', '.', 'exon', '470', '500', '.', '+', '.',
'gene_id "G2"; transcript_id "T3"; exon_number "2"'],
['1', '.', 'CDS', '470', '490', '.', '+', '.',
'gene_id "G2"; transcript_id "T3";'],
['2', '.', 'CDS', '470', '490', '.', '+', '.',
'gene_id "G3"; transcript_id "T4";'],
])
gtf = make_file_from_list(intervals_to_list(gtf_data))
gene1, gene2 = list(segment._get_gene_content(gtf, ['1', 'MT'], report_progress=True))
expected1 = {
'gene': gtf_data[0],
'T1': gtf_data[1:4],
'T2': gtf_data[4:7],
}
extra_gene = create_interval_from_list(
['1', '.', 'gene', '400', '500', '.', '+', '.', 'gene_id "G2";'])
expected2 = {
'gene': extra_gene,
'T3': gtf_data[7:-1],
}
self.assertEqual(gene1, expected1)
self.assertEqual(gene2, expected2)
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_fail_validating(self, print_mock):
"""
Fail on validation.
Mock the print function to suppress the actual printing during test.
"""
intervals = list_to_intervals([
['1', '.', 'transcript', '1', '200', '.', '+', '.', 'transcript_id "42";'],
['1', '.', 'exon', '1', '30', '.', '+', '.', 'exon_number "1";'],
['1', '.', 'exon', '60', '100', '.', '+', '.', 'exon_number "2";'],
])
with self.assertRaises(AssertionError):
segment._process_transcript_group(intervals)
self.assertEqual(print_mock.call_count, 8)
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)
def test_no_transcript_interval(self):
"""
If not transcript interval is given, it is determined by function
Also this is the case if no CDS are given - all exons turn to ncRNA.
"""
intervals = list_to_intervals([
['1', '.', 'exon', '1', '30', '.', '+', '.', 'exon_number "1";'],
['1', '.', 'exon', '60', '100', '.', '+', '.', 'exon_number "2";'],
])
expected = [
['1', '.', 'transcript', '1', '100', '.', '+', '.', ''],
['1', '.', 'intron', '31', '59', '.', '+', '.', ''],
['1', '.', 'ncRNA', '1', '30', '.', '+', '.', 'exon_number "1";'],
['1', '.', 'ncRNA', '60', '100', '.', '+', '.', 'exon_number "2";'],
]
output = intervals_to_list(segment._process_transcript_group(intervals))
self.assertEqual(output, expected)
def setUp(self):
warnings.simplefilter("ignore", (ResourceWarning, ImportWarning))
self.gtf_data = list_to_intervals([
[
'1', '.', 'intergenic', '1', '799', '.', '-', '.',
attrs(tid='.', iid='interN00000')
],
[
'1', '.', 'intergenic', '1', '99', '.', '+', '.',
attrs(tid='.', iid='interP00000')
],
# Gene #1:
[
'1', '.', 'gene', '100', '499', '.', '+', '.',
attrs('G1', bio='.')
],
# Transcript #1
[
'1', '.', 'transcript', '100', '249', '.', '+', '.',
attrs('G1', 'T1', bio='.')
],
[
'1', '.', 'UTR5', '100', '149', '.', '+', '.',
attrs('G1', 'T1', 1, bio='.')
],
[
'1', '.', 'intron', '150', '199', '.', '+', '.',
attrs('G1', 'T1', bio='.')
],
[
'1', '.', 'CDS', '200', '229', '.', '+', '.',
attrs('G1', 'T1', 2, bio='.')
],
[
'1', '.', 'intron', '230', '239', '.', '+', '.',
attrs('G1', 'T1', bio='.')
],
[
'1', '.', 'UTR3', '240', '249', '.', '+', '.',
attrs('G1', 'T1', 3, bio='.')
],
# Transcript #2
[
'1', '.', 'transcript', '240', '499', '.', '+', '.',
attrs('G1', 'T2', bio='.')
],
[
'1', '.', 'CDS', '240', '299', '.', '+', '.',
attrs('G1', 'T2', 1, bio='.')
],
[
'1', '.', 'intron', '300', '399', '.', '+', '.',
attrs('G1', 'T1', bio='.')
],
[
'1', '.', 'CDS', '400', '499', '.', '+', '.',
attrs('G1', 'T2', 2, bio='.')
],
# intergenic
[
'1', '.', 'intergenic', '500', '599', '.', '+', '.',
attrs(tid='.', iid='interP00001')
],
# Gene #1:
[
'1', '.', 'gene', '600', '799', '.', '+', '.',
attrs('G2', bio='.')
],
# Transcript #3
[
'1', '.', 'transcript', '600', '799', '.', '+', '.',
attrs('G2', 'T3', bio='.')
],
[
'1', '.', 'CDS', '600', '649', '.', '+', '.',
attrs('G2', 'T3', 1, bio='.')
],
[
'1', '.', 'intron', '650', '749', '.', '+', '.',
attrs('G2', 'T3', bio='.')
],
[
'1', '.', 'CDS', '750', '799', '.', '+', '.',
attrs('G2', 'T3', 2, bio='.')
],
[
'1', '.', 'intergenic', '800', '999', '.', '+', '.',
attrs(tid='.', iid='interP00002')
],
# Gene #3:
[
'1', '.', 'gene', '800', '899', '.', '-', '.',
attrs('G3', bio='.')
],
# Transcript #3
[
'1', '.', 'transcript', '800', '899', '.', '-', '.',
attrs('G3', 'T4', bio='.')
],
[
'1', '.', 'CDS', '800', '899', '.', '-', '.',
attrs('G3', 'T4', 1, bio='.')
],
[
'1', '.', 'intergenic', '900', '999', '.', '-', '.',
attrs(tid='.', iid='interN00001')
],
])
self.gtf = make_file_from_list(intervals_to_list(self.gtf_data),
extension='gtf')
self.strange = get_temp_file_name(extension='bam')
self.cross_tr = get_temp_file_name(extension='tsv')
self.out = get_temp_file_name(extension='tsv')
