def test_clusters(self):
fin_sites = make_file_from_list([
['1', '1', '2', '.', '1', '+'],
['1', '2', '3', '.', '1', '+'],
['1', '3', '4', '.', '1', '+'],
['1', '4', '5', '.', '2', '+'],
['1', '4', '5', '.', '1', '-'],
['1', '5', '6', '.', '1', '+'],
['1', '6', '7', '.', '1', '-'],
['1', '7', '8', '.', '1', '-'],
['1', '10', '11', '.', '1', '+'],
['1', '11', '12', '.', '2', '+'],
['1', '12', '13', '.', '1', '+'],
])
fin_peaks = make_file_from_list([
['1', '4', '5', 'cl1', '1', '+'],
['1', '4', '5', 'cl2', '1', '-'],
['1', '5', '6', 'cl3', '1', '+'],
['1', '11', '12', 'cl4', '2', '+'],
])
fout_clusters = get_temp_file_name()
clusters.run(fin_sites, fin_peaks, fout_clusters, dist=3, slop=2)
result = make_list_from_file(fout_clusters, fields_separator='\t')
expected = [
['1', '2', '6', 'cl1,cl3', '5', '+'],
['1', '4', '7', 'cl2', '2', '-'],
['1', '10', '13', 'cl4', '4', '+'],
]
self.assertEqual(expected, result)
def template(cross_links, annotation, subtype='biotype',
excluded_types=None):
"""
Utility function for testing iCount.analysis.annotate
Instead of input files, accept the file content in form of lists and create
temporary files from them on the fly. This avoids the problem of having a
bunch of multiple small files or one large file (which would violate the
idea of test isolation).
For example of how to use this function check any test that uses it.
Parameters
----------
cross_links : list
List representation of cross-links file.
annotation : list
List representation of annotation file.
Returns
-------
list
List representation of output file of analysis.annotate().
"""
cross_links_file = make_file_from_list(cross_links, extension='bed.gz')
annotation_file = make_file_from_list(annotation, extension='gtf.gz')
out_file = get_temp_file_name(extension='bed.gz')
annotate.annotate_cross_links(annotation_file, cross_links_file, out_file, subtype=subtype,
excluded_types=excluded_types)
return make_list_from_file(out_file, fields_separator='\t')
def test_rnamaps(self):
regions = make_file_from_list([
['1', '.', 'intergenic', '1', '100', '.', '+', '.', ''],
['1', '.', 'intergenic', '1', '610', '.', '-', '.', ''],
['1', '.', 'UTR5', '101', '160', '.', '+', '.', ''],
['1', '.', 'intron', '161', '320', '.', '+', '.', ''],
['1', '.', 'CDS', '321', '380', '.', '+', '.', ''],
['1', '.', 'intron', '381', '540', '.', '+', '.', ''],
['1', '.', 'UTR3', '541', '600', '.', '+', '.', ''],
['1', '.', 'intergenic', '601', '1000', '.', '+', '.', ''],
['1', '.', 'ncRNA', '611', '700', '.', '-', '.', ''],
['1', '.', 'intron', '701', '800', '.', '-', '.', ''],
['1', '.', 'ncRNA', '801', '900', '.', '-', '.', ''],
['1', '.', 'intergenic', '901', '1000', '.', '-', '.', ''],
])
cross_links = make_file_from_list([
['1', '120', '121', '.', '1', '+'],
['1', '350', '351', '.', '1', '+'],
['1', '550', '551', '.', '1', '+'],
['1', '750', '751', '.', '1', '-'],
])
command_basic = [
'iCount',
'rnamaps',
cross_links,
regions,
'-S',
'40', # Supress lower than ERROR messages.
]
self.assertEqual(subprocess.call(command_basic), 0)
def test_limits_downstream(self):
"""Landmarks with too short upstream segment should not be used."""
regions = make_file_from_list([
[
'chr1', '.', 'CDS', '150', '200', '.', '+', '.',
'gene_name "A";'
],
[
'chr1', '.', 'intron', '201', '350', '.', '+', '.',
'gene_name "A";'
],
])
fn = rnamaps.make_landmarks_file(regions, 'exon-intron')
self.assertEqual(make_list_from_file(fn), [])
regions = make_file_from_list([
[
'chr1', '.', 'CDS', '151', '200', '.', '-', '.',
'gene_name "A";'
],
[
'chr1', '.', 'intron', '201', '351', '.', '-', '.',
'gene_name "A";'
],
])
fn = rnamaps.make_landmarks_file(regions, 'intron-exon')
self.assertEqual(make_list_from_file(fn), [])
def test_basic(self):
regions = make_file_from_list([
[
'chr1', '.', 'CDS', '150', '200', '.', '+', '.',
'gene_name "A";'
],
[
'chr1', '.', 'intron', '201', '351', '.', '+', '.',
'gene_name "A";'
],
])
fn = rnamaps.make_landmarks_file(regions, 'exon-intron')
self.assertEqual(make_list_from_file(fn), [
['chr1', '200', '201', 'A', '.', '+'],
])
regions = make_file_from_list([
[
'chr1', '.', 'CDS', '150', '200', '.', '-', '.',
'gene_name "A";'
],
[
'chr1', '.', 'intron', '201', '351', '.', '-', '.',
'gene_name "A";'
],
])
fn = rnamaps.make_landmarks_file(regions, 'intron-exon')
self.assertEqual(make_list_from_file(fn), [
['chr1', '199', '200', 'A', '.', '-'],
])
def setUp(self):
warnings.simplefilter("ignore", ResourceWarning)
# Temporary file names to use for output:
self.tmp1 = get_temp_file_name()
self.tmp2 = get_temp_file_name()
self.dir = get_temp_dir()
self.dir2 = get_temp_dir()
self.cross_links = make_file_from_list([
['1', '16', '17', '.', '5', '+'],
['1', '14', '15', '.', '5', '+'],
['1', '15', '16', '.', '5', '+'],
],
extension='bed')
self.peaks = make_file_from_list([
['1', '15', '16', '.', '15', '+'],
])
self.annotation = make_file_from_list([
['1', '.', 'CDS', '10', '20', '.', '+', '.', 'biotype "A";'],
['1', '.', 'ncRNA', '10', '20', '.', '+', '.', 'biotype "A";'],
['1', '.', 'CDS', '10', '20', '.', '+', '.', 'biotype "A";'],
['1', '.', 'CDS', '10', '20', '.', '+', '.', 'biotype "B";'],
['1', '.', 'CDS', '10', '20', '.', '-', '.', 'biotype "C";'],
['1', '.', 'CDS', '12', '18', '.', '+', '.', 'biotype "A";'],
['1', '.', 'CDS', '30', '40', '.', '+', '.', 'biotype "D";'],
])
self.gtf = make_file_from_list([
['1', '.', 'gene', '10', '20', '.', '+', '.', 'gene_id "A";'],
[
'1', '.', 'transcript', '10', '20', '.', '+', '.',
'gene_id "A"; transcript_id "AA";'
],
[
'1', '.', 'exon', '10', '20', '.', '+', '.',
'gene_id "A"; transcript_id "AA"; exon_number "1";'
],
])
self.bam = make_bam_file(
{
'chromosomes': [
('1', 3000),
('2', 2000),
],
'segments': [
('name3:rbc:CCCC:', 0, 0, 100, 20, [(0, 100)], {
'NH': 1
}),
('name4:ABC', 0, 0, 300, 20, [(0, 200)], {
'NH': 11
}),
]
},
rnd_seed=0)
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 get_summary_reports(self, annotation, cross_links):
"""Help running tests for ``summary_report`` with less clutter."""
annotation_file = make_file_from_list(annotation)
cross_links_file = make_file_from_list(cross_links)
segment.summary_templates(annotation_file, self.out_dir)
summary.summary_reports(annotation_file, cross_links_file, self.out_dir, self.out_dir)
return [
make_list_from_file(os.path.join(self.out_dir, segment.SUMMARY_TYPE), '\t'),
make_list_from_file(os.path.join(self.out_dir, segment.SUMMARY_SUBTYPE), '\t'),
make_list_from_file(os.path.join(self.out_dir, segment.SUMMARY_GENE), '\t'),
]
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_negative_strand(self):
"""
Whole read is in single transcript, single segment. But the segment
borders on intergenic (downstream).
"""
gtf_neg_data = [
i[:6] + ['-'] + i[7:] for i in intervals_to_list(self.gtf_data)
]
gtf_neg = make_file_from_list(gtf_neg_data)
bam = make_bam_file({
'chromosomes': [('1', 1000)],
'segments': [
# (qname, flag, refname, pos, mapq, cigar, tags)
('name2:rbc:CCCC', 16, 0, 549, 255, [(0, 30)], {
'NH': 1
}),
]
})
expected = [
['RNAmap', 'type', 'position', 'all', 'explicit'],
['CDS-intergenic', '20', '0.5', '0'],
['intergenic-CDS', '-80', '0.5', '0'],
]
rnamaps.run(bam,
gtf_neg,
self.out,
self.strange,
self.cross_tr,
mismatches=1,
implicit_handling='split')
self.assertEqual(expected, make_list_from_file(self.out))
def test_segment(self):
fai = make_file_from_list([
['1', '2000'],
['MT', '500'],
],
bedtool=False)
command_basic = [
'iCount',
'segment',
self.gtf,
self.tmp1,
fai,
'-S',
'40', # Supress lower than ERROR messages.
]
command_full = [
'iCount',
'segment',
self.gtf,
self.tmp1,
fai,
'--report_progress',
'-S',
'40', # Supress lower than ERROR messages.
]
self.assertEqual(subprocess.call(command_basic), 0)
self.assertEqual(subprocess.call(command_full), 0)
def test_run(self):
fin_annotation = make_file_from_list([
[
'1', '.', 'gene', '10', '20', '.', '+', '.',
'gene_name "A"; gene_id "1";'
],
[
'1', '.', 'transcript', '10', '20', '.', '+', '.',
'gene_name "B"; gene_id "1";'
],
[
'2', '.', 'CDS', '10', '20', '.', '+', '.',
'gene_name "C"; gene_id "1";'
],
])
fin_sites = make_file_from_list([
['1', '14', '15', '.', '3', '+'],
['1', '16', '17', '.', '5', '+'],
['2', '16', '17', '.', '5', '+'],
])
fout_peaks = get_temp_file_name(extension='.bed.gz')
fout_scores = get_temp_file_name(extension='.tsv.gz')
peaks.run(fin_annotation, fin_sites, fout_peaks, scores=fout_scores)
out_peaks = make_list_from_file(fout_peaks, fields_separator='\t')
out_scores = make_list_from_file(fout_scores, fields_separator='\t')
# Remove header:
out_scores = out_scores[1:]
expected_peaks = [
['1', '14', '15', 'A-1', '3', '+'],
['1', '16', '17', 'A-1', '5', '+'],
]
expected_scores = [
['1', '14', '+', 'A', '1', '3', '8', '0.036198'],
['1', '16', '+', 'A', '1', '5', '8', '0.036198'],
[
'2', '16', '+', 'not_annotated', 'not_annotated', '5',
'not_calculated', '1'
],
]
self.assertEqual(out_peaks, expected_peaks)
self.assertEqual(out_scores, expected_scores)
def test_limits_downstream(self):
"""Landmarks with too short upstream segment should not be used."""
regions = make_file_from_list([
['chr1', '.', 'CDS', '150', '200', '.', '+', '.', 'gene_name "A";'],
['chr1', '.', 'intron', '201', '350', '.', '+', '.', 'gene_name "A";'],
])
landmarks = landmark.make_single_type_landmarks(regions, 'exon-intron')
landmarks = [list(map(str, item)) for item in landmarks]
self.assertEqual(landmarks, [])
regions = make_file_from_list([
['chr1', '.', 'CDS', '151', '200', '.', '-', '.', 'gene_name "A";'],
['chr1', '.', 'intron', '201', '351', '.', '-', '.', 'gene_name "A";'],
])
landmarks = landmark.make_single_type_landmarks(regions, 'intron-exon')
landmarks = [list(map(str, item)) for item in landmarks]
self.assertEqual(landmarks, [])
def test_no_landmark(self):
"""Landmark is missing on this chromosome / stramd."""
xlinks = make_file_from_list([
['chrX', '22', '23', '.', '3', '+'],
])
distances, total_cdna = rnamaps.compute_distances(
self.landmarks, xlinks, 'exon-intron')
self.assertEqual(total_cdna, 3)
self.assertEqual(distances, {})
def test_basic(self):
segmentation = [
# Transcript #1
[
'1', '.', 'ncRNA', '1', '10', '.', '+', '.',
'biotype "A"; gene_name "X";'
],
[
'1', '.', 'intron', '11', '20', '.', '+', '.',
'biotype "A"; gene_name "X";'
],
[
'1', '.', 'CDS', '21', '30', '.', '+', '.',
'biotype "A"; gene_name "X";'
],
[
'1', '.', 'UTR3', '31', '40', '.', '+', '.',
'biotype "A"; gene_name "X";'
],
# Transcript #1
[
'1', '.', 'CDS', '5', '14', '.', '+', '.',
'biotype "A"; gene_name "X";'
],
[
'1', '.', 'intron', '15', '24', '.', '+', '.',
'biotype "A"; gene_name "X";'
],
[
'1', '.', 'CDS', '25', '34', '.', '+', '.',
'biotype "A"; gene_name "X";'
],
# Also negative strand:
[
'1', '.', 'CDS', '3', '32', '.', '-', '.',
'biotype "A"; gene_name "X";'
],
]
expected = [
['1', '0', '4', '.', '.', '+'],
['1', '4', '10', '.', '.', '+'],
['1', '10', '14', '.', '.', '+'],
['1', '14', '20', '.', '.', '+'],
['1', '20', '24', '.', '.', '+'],
['1', '24', '30', '.', '.', '+'],
['1', '30', '34', '.', '.', '+'],
['1', '34', '40', '.', '.', '+'],
['1', '2', '32', '.', '.', '-'],
]
segmentation_file = make_file_from_list(segmentation)
borders_file = region.construct_borders(BedTool(segmentation_file))
results = make_list_from_file(borders_file, fields_separator='\t')
self.assertEqual(
expected,
# Sort results by chrom, strand, start, stop
sorted(results, key=lambda x: (x[0], x[-1], int(x[1]), int(x[2]))))
def _make_types_length(annotation, subtype='biotype', excluded_types=None):
"""
Run function `make_types_length_file` with data from `annotation`.
"""
annotation_file = make_file_from_list(annotation)
out_file = get_temp_file_name()
fai = make_file_from_list(bedtool=False,
data=[
['1', '100'],
['6', '100'],
['20', '100'],
])
result, _ = summary.make_types_length_file(annotation_file,
fai,
out_file,
subtype=subtype,
excluded_types=excluded_types)
return make_list_from_file(result, fields_separator='\t')
def setUp(self):
warnings.simplefilter("ignore", ResourceWarning)
self.landmarks = make_file_from_list([
['chr1', '10', '11', 'G1', '.', '+'],
['chr1', '20', '21', 'G1', '.', '+'],
['chr1', '20', '21', 'G2', '.', '-'],
['chr2', '10', '11', 'G3', '.', '+'],
])
def merge_bed_wrapper(data):
"""
TODO
"""
files = []
for file_ in data:
files.append(make_file_from_list(file_))
out_file = get_temp_file_name()
merge_bed(out_file, files)
return make_list_from_file(out_file, fields_separator='\t')
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 merge_bed_wrapper(data):
"""
TODO
"""
files = []
for file_ in data:
files.append(make_file_from_list(file_))
out_file = tempfile.NamedTemporaryFile(delete=False).name
return make_list_from_file(merge_bed(out_file, files),
fields_separator='\t')
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_no_required_attributes(self):
"""
Raise error if transcript_id attribute is not present.
"""
gtf = make_file_from_list([
['1', '.', 'transcript', '500', '600', '.', '+', '.', 'gene_id "G1";'],
])
message = "First element in gene content is neither gene or transcript!"
with self.assertRaisesRegex(Exception, message):
list((segment._get_gene_content(gtf, ['1', 'MT'])))
def test_basic(self):
regions = make_file_from_list([
['chr1', '.', 'CDS', '150', '200', '.', '+', '.', 'gene_name "A";'],
['chr1', '.', 'intron', '201', '351', '.', '+', '.', 'gene_name "A";'],
])
landmarks = landmark.make_single_type_landmarks(regions, 'exon-intron')
landmarks = [list(map(str, item)) for item in landmarks]
self.assertEqual(landmarks, [
['chr1', '200', '201', 'exon-intron;A', '.', '+'],
])
regions = make_file_from_list([
['chr1', '.', 'CDS', '150', '200', '.', '-', '.', 'gene_name "A";'],
['chr1', '.', 'intron', '201', '351', '.', '-', '.', 'gene_name "A";'],
])
landmarks = landmark.make_single_type_landmarks(regions, 'intron-exon')
landmarks = [list(map(str, item)) for item in landmarks]
self.assertEqual(landmarks, [
['chr1', '199', '200', 'intron-exon;A', '.', '-'],
])
def setUp(self):
warnings.simplefilter("ignore", ResourceWarning)
bed_data = [
['1', '4', '5', '.', '5', '+'],
['1', '5', '6', '.', '1', '+'],
['1', '5', '6', '.', '1', '-'],
['2', '5', '6', '.', '3', '+'],
]
self.bed = make_file_from_list(bed_data, extension='bed')
self.bedgraph = get_temp_file_name(extension='bedgraph')
def _make_summary_report(annotation,
cross_links,
chrom_lengths,
subtype='biotype',
excluded_types=None):
"""
Run function `make_summary_report` with input/output data as lists.
"""
annotation_file = make_file_from_list(annotation)
cross_links_file = make_file_from_list(cross_links)
chrom_length_file = make_file_from_list(chrom_lengths, bedtool=False)
out_file = tempfile.NamedTemporaryFile(delete=False).name
summary.make_summary_report(annotation_file,
cross_links_file,
out_file,
chrom_length_file,
subtype=subtype,
excluded_types=excluded_types)
return make_list_from_file(out_file, fields_separator='\t')
def test_basic(self):
xlinks = make_file_from_list([
['chr1', '12', '13', '.', '3', '+'],
])
distances, total_cdna = rnamaps.compute_distances(
self.landmarks, xlinks, 'exon-intron')
self.assertEqual(total_cdna, 3)
self.assertEqual(distances, {
'chr1__+__10__G1': {
2: 3
},
})
def test_basic(self):
# seg is compositon of BED6 and GTF interval:
nonmerged = make_file_from_list([
[
'1', '.', 'UTR3', '1', '10', '.', '+', '.',
'biotype "lncRNA";gene_id "id1";'
],
[
'1', '.', 'UTR3', '11', '20', '.', '+', '.',
'biotype "lncRNA";gene_id "id1";'
],
[
'1', '.', 'UTR3', '21', '30', '.', '+', '.',
'biotype "lncRNA";gene_id "id2";'
],
[
'1', '.', 'UTR3', '31', '40', '.', '+', '.',
'biotype "lncRNA";gene_id "id1";'
],
[
'1', '.', 'UTR3', '31', '40', '.', '-', '.',
'biotype "lncRNA";gene_id "id1";'
],
])
expected = [
[
'1', '.', 'UTR3', '1', '20', '.', '+', '.',
'biotype "lncRNA";gene_id "id1";'
],
[
'1', '.', 'UTR3', '21', '30', '.', '+', '.',
'biotype "lncRNA";gene_id "id2";'
],
[
'1', '.', 'UTR3', '31', '40', '.', '+', '.',
'biotype "lncRNA";gene_id "id1";'
],
[
'1', '.', 'UTR3', '31', '40', '.', '-', '.',
'biotype "lncRNA";gene_id "id1";'
],
]
region.merge_regions(nonmerged, self.tmp)
results = make_list_from_file(self.tmp, fields_separator='\t')
# Since order of attrs can be arbitrary, equality checks are more complex:
for res, exp in zip(results, expected):
self.assertEqual(res[:8], exp[:8])
self.assertEqual(
';'.join(sorted(res[8].split(';'))),
';'.join(sorted(exp[8].split(';'))),
)
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 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_basic(self):
regions = make_file_from_list([
['chr1', '.', 'CDS', '150', '200', '.', '+', '.', 'gene_name "A";'],
['chr1', '.', 'intron', '201', '400', '.', '+', '.', 'gene_name "A";'],
['chr1', '.', 'CDS', '401', '600', '.', '+', '.', 'gene_name "A";'],
])
landmarks = get_temp_file_name(extension='bed')
landmark.make_landmarks(regions, landmarks)
self.assertEqual(make_list_from_file(landmarks), [
['chr1', '200', '201', 'exon-intron;A', '.', '+'],
['chr1', '400', '401', 'intron-exon;A', '.', '+'],
])
