def test_run_simple(self):
bam_fname = make_bam_file(self.data)
unique_fname = get_temp_file_name(extension='.bed.gz')
multi_fname = get_temp_file_name(extension='.bed.gz')
strange_fname = get_temp_file_name(extension='.bam.gz')
result = xlsites.run(bam_fname,
unique_fname,
multi_fname,
strange_fname,
mapq_th=5,
report_progress=True)
# pylint: disable=no-member
self.assertEqual(result.all_recs, 6)
# Unmapped records:
self.assertEqual(result.notmapped_recs, 1)
# Mapped records:
self.assertEqual(result.mapped_recs, 5)
# Records with too low quality:
self.assertEqual(result.lowmapq_recs, 1)
# Records used in analysis
self.assertEqual(result.used_recs, 4)
# Records with invalid randomers
self.assertEqual(result.invalidrandomer_recs, 1)
# Records with no randomers:
self.assertEqual(result.norandomer_recs, 1)
# Barcode counter:
self.assertEqual(result.bc_cn, {'': 2, 'ACG': 1, 'CCCC': 1})
# Strange counter:
self.assertEqual(result.strange_recs, 1)
def test_bed2bedgraph(self):
command_basic = [
'iCount',
'bedgraph',
self.cross_links,
get_temp_file_name(extension='bedgraph'),
'-S',
'40', # Supress lower than ERROR messages.
]
command_full = [
'iCount',
'bedgraph',
self.cross_links,
get_temp_file_name(extension='bedgraph'),
'--name',
'Name.',
'--description',
'Description.',
'--visibility',
'full',
'--priority',
'20',
'--color',
'256,0,0',
'--alt_color',
'0,256,0',
'--max_height_pixels',
'100:50:0',
'-S',
'40', # Supress lower than ERROR messages.
]
self.assertEqual(subprocess.call(command_basic), 0)
self.assertEqual(subprocess.call(command_full), 0)
def test_e2e(self):
"""
From raw reads and ENSEMBL annotation to rnamaps.
"""
# Make segmentation & regions file
seg = get_temp_file_name(extension='gtf')
out_dir = get_temp_dir()
iCount.genomes.segment.get_segments(self.gtf, seg, self.fai)
iCount.genomes.region.make_regions(seg, out_dir)
regions = os.path.join(out_dir, iCount.genomes.region.REGIONS_FILE)
# Build STAR index:
genome_index = get_temp_dir()
rcode = iCount.externals.star.build_index(self.fasta, genome_index, annotation=self.gtf)
self.assertEqual(rcode, 0)
# Map reads:
map_dir = get_temp_dir()
rcode = iCount.externals.star.map_reads(
self.reads, genome_index, out_dir=map_dir, annotation=self.gtf)
self.assertEqual(rcode, 0)
# Get bam with mapped reads:
bam = [fname for fname in os.listdir(map_dir) if fname.startswith('Aligned')][0]
bam = os.path.join(map_dir, bam)
sites_single = get_temp_file_name(extension='bed.gz')
sites_multi = get_temp_file_name(extension='bed.gz')
skipped = get_temp_file_name(extension='bam')
iCount.mapping.xlsites.run(bam, sites_single, sites_multi, skipped)
iCount.analysis.rnamaps.run(sites_single, regions)
def setUp(self):
self.adapter = 'AAAATTTTCCCCGGGG'
self.reads = make_fastq_file(
adapter=self.adapter,
num_sequences=100,
out_file=get_temp_file_name(extension='fastq'))
self.tmp = get_temp_file_name(extension='fastq')
warnings.simplefilter("ignore", ResourceWarning)
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_plot(self):
image_file = get_temp_file_name(extension='png')
norm_file = get_temp_file_name(extension='txt')
rnamaps.make_normalization(self.gtf, norm_file)
rnamaps.plot_rna_map(norm_file,
'CDS-intron',
normalization=norm_file,
outfile=image_file)
self.assertTrue(os.path.isfile(image_file))
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_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 test_barcode_size_diff(self):
# One mismatch, second barcode.
barcodes = ['NAAANN', 'NNCCCNN']
adapter = 'CCCCCC'
data = [
'@header1',
'TACATT' + adapter + make_sequence(40, rnd_seed=0),
'+',
make_quality_scores(50, rnd_seed=0) + '!J',
'@header2',
'AACCCTT' + adapter + make_sequence(39, rnd_seed=0),
'+',
make_quality_scores(50, rnd_seed=0) + '!J',
]
fq_fname = get_temp_file_name(extension='fq')
fq_file = iCount.files.fastq.FastqFile(fq_fname, 'wt')
fq_file.write(iCount.files.fastq.FastqEntry(*data[:4]))
fq_file.write(iCount.files.fastq.FastqEntry(*data[4:]))
fq_file.close()
handle = demultiplex._extract(fq_fname, barcodes, mismatches=1)
read1, exp_id1, randomer1 = next(handle)
self.assertEqual(exp_id1, 0)
self.assertEqual(randomer1, 'TTT')
self.assertEqual(read1.id, data[0])
self.assertEqual(read1.seq, data[1][6:])
self.assertEqual(read1.plus, '+')
self.assertEqual(read1.qual, data[3][6:])
read2, exp_id2, randomer2 = next(handle)
self.assertEqual(exp_id2, 1)
self.assertEqual(randomer2, 'AATT')
self.assertEqual(read2.id, data[4])
self.assertEqual(read2.seq, data[5][7:])
self.assertEqual(read2.plus, '+')
self.assertEqual(read2.qual, data[7][7:])
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_plot(self):
outfile = get_temp_file_name(extension='png')
plot_combined.plot_combined(self.results_file,
outfile,
top_n=2,
nbins=50)
self.assertTrue(os.path.isfile(outfile))
def test_normalisation(self):
norm_file = get_temp_file_name(extension='txt')
rnamaps.make_normalization(self.gtf, norm_file)
expected = [
['RNAmap_type', 'distance', 'segments'],
['CDS-UTR3', '-1', '1'],
['CDS-UTR3', '0', '1'],
['CDS-UTR3', '1', '1'],
['CDS-intron', '-1', '1'],
['CDS-intron', '0', '1'],
['CDS-intron', '1', '1'],
['CDS-intron', '2', '1'],
['integrenic-CDS', '-2', '1'],
['integrenic-CDS', '-1', '1'],
['integrenic-CDS', '0', '1'],
['intron-UTR3', '-3', '1'],
['intron-UTR3', '-2', '1'],
['intron-UTR3', '-1', '1'],
['intron-UTR3', '0', '1'],
['intron-UTR3', '1', '1'],
['intron-ncRNA', '-1', '1'],
['intron-ncRNA', '0', '1'],
['ncRNA-integrenic', '-1', '1'],
['ncRNA-integrenic', '0', '1'],
['ncRNA-integrenic', '1', '1'],
['ncRNA-intron', '-2', '1'],
['ncRNA-intron', '-1', '1'],
['ncRNA-intron', '0', '1'],
['ncRNA-ncRNA', '-2', '1'],
['ncRNA-ncRNA', '-1', '1'],
['ncRNA-ncRNA', '0', '1'],
]
self.assertEqual(expected, make_list_from_file(norm_file))
def test_cutadapt(self):
adapter = 'CCCCCCCCC'
fastq = make_fastq_file(adapter=adapter,
out_file=get_temp_file_name(extension='fastq'),
rnd_seed=0)
command_basic = [
'iCount',
'cutadapt',
fastq,
self.tmp1,
adapter,
'-S',
'40', # Supress lower than ERROR messages.
]
command_full = [
'iCount',
'cutadapt',
fastq,
self.tmp1,
adapter,
'--qual_trim',
'20',
'--minimum_length',
'15',
'-S',
'40', # Supress lower than ERROR messages.
]
self.assertEqual(subprocess.call(command_basic), 0)
self.assertEqual(subprocess.call(command_full), 0)
def test_plot(self):
outfile = get_temp_file_name(extension='png')
plot_rnaheatmap.plot_rnaheatmap(self.results_file,
outfile,
top_n=2,
binsize=10)
self.assertTrue(os.path.isfile(outfile))
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 create_fq_file(self, entries):
fname = get_temp_file_name(extension='fq')
fq_file = FastqFile(fname, 'wt')
for entry in entries:
fq_file.write(entry)
fq_file.close()
return fname
def test_xlsites(self):
# Make a sample bam file
unique = get_temp_file_name(extension='.bed')
multi = get_temp_file_name(extension='.bed')
strange = get_temp_file_name(extension='.bam')
command_basic = [
'iCount',
'xlsites',
self.bam,
unique,
multi,
strange,
'-S',
'40', # Supress lower than ERROR messages.
]
command_full = [
'iCount',
'xlsites',
self.bam,
unique,
multi,
strange,
'--group_by',
'start',
'--quant',
'cDNA',
'--mismatches',
'2',
'--mapq_th',
'0',
'--multimax',
'50',
'--gap_th',
'4',
'--ratio_th',
'0.1',
'--max_barcodes',
'10000',
'-S',
'40', # Supress lower than ERROR messages.
]
self.assertEqual(subprocess.call(command_basic), 0)
self.assertEqual(subprocess.call(command_full), 0)
def test_error_open_bamfile(self):
"""
Provide onyl file with no content - error shoud be raised.
"""
bam_fname = get_temp_file_name()
message = r"Error opening BAM file: .*"
with self.assertRaisesRegex(ValueError, message):
xlsites._processs_bam_file(bam_fname, self.metrics, 50, self.tmp)
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_regions(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)
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 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 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', '.', '+'],
])
def test_fastq_file_write(self):
data = [
['@header1', 'AAA', '+', 'FFF'],
['@header2', 'AAAA', '+', 'FFFF'],
]
fq_file_name = get_temp_file_name(extension='fq.gz')
fq_file = iCount.files.fastq.FastqFile(fq_file_name, 'wt')
for line in data:
fq_file.write(iCount.files.fastq.FastqEntry(*line))
fq_file.close()
result = make_list_from_file(fq_file_name)
expected = [['@header1'], ['AAA'], ['+'], ['FFF'], ['@header2'], ['AAAA'], ['+'], ['FFFF']]
self.assertEqual(result, expected)
def test_rnamaps(self):
command_basic = [
'iCount',
'rnamaps',
self.bam,
self.gtf,
self.tmp1,
get_temp_file_name(extension='.bam'),
self.tmp2,
'-S',
'40', # Supress lower than ERROR messages.
]
self.assertEqual(subprocess.call(command_basic), 0)
def test_peaks(self):
command_basic = [
'iCount',
'peaks',
self.annotation,
self.cross_links,
get_temp_file_name(extension='.bed.gz'),
'-S',
'40', # Supress lower than ERROR messages.
]
command_full = [
'iCount',
'peaks',
self.annotation,
self.cross_links,
get_temp_file_name(extension='.bed.gz'),
'--scores',
get_temp_file_name(extension='.tsv.gz'),
'--half_window',
'3',
'--fdr',
'0.05',
'--perms',
'10',
'--rnd_seed',
'42',
'--features',
'gene',
'--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_annotation(self):
# Execute only full command (with --target_dir), to avoid downloading to cwd.
command_full = [
'iCount',
'annotation',
'human',
'27',
'--out_dir',
self.dir,
'--annotation',
get_temp_file_name(extension='gtf.gz'),
'-S',
'40', # Supress lower than ERROR messages.
]
self.assertEqual(subprocess.call(command_full), 0)
def setUp(self):
warnings.simplefilter("ignore", ResourceWarning)
self.dir = get_temp_dir()
self.adapter = 'AAAAAAAAAA'
self.barcodes5 = [
'NNAAAN',
'NGGGN',
'NGGGN',
]
self.barcodes3 = [
'.',
'NNGGG',
'NCCC',
]
# Header: early version Illumina header
# Barcodes: exact match to the barcode set #1
self.entry1 = FastqEntry(
'@header1/1',
'GGAAAG' + make_sequence(40) + self.adapter,
'+',
make_quality_scores(56),
)
# Header: contains id and description
# Barcodes: one mismatch on 5' end for barcode set #2
self.entry2 = FastqEntry(
'@header2 blah',
'AGGTA' + make_sequence(40) + 'AAGGG' + self.adapter,
'+',
make_quality_scores(60),
)
# Header: simple header
# Barcodes: one mismatch on 3' end for barcode set #3
self.entry3 = FastqEntry(
'@header3',
'TGGGT' + make_sequence(40) + 'TACC' + self.adapter,
'+',
make_quality_scores(59),
)
self.fq_fname = get_temp_file_name(extension='fq')
self.fq_file = iCount.files.fastq.FastqFile(self.fq_fname, 'wt')
for entry in [self.entry1, self.entry2, self.entry3]:
self.fq_file.write(entry)
self.fq_file.close()
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 test_genome(self):
# Download just MT and Y chromosome, or test can last too long...
command_full = [
'iCount',
'genome',
'homo_sapiens',
'--release',
'84',
'--out_dir',
self.dir,
'--genome',
get_temp_file_name(extension='fa.gz'),
'--chromosomes',
'MT',
'Y',
'-S',
'40', # Supress lower than ERROR messages.
]
self.assertEqual(subprocess.call(command_full), 0)
def test_genome(self):
# Download just MT and Y chromosome, or test can last too long...
# Only test ENSEMBL, since GENCODE does not allow download of single chromosome.
command_full = [
'iCount',
'genome',
'homo_sapiens',
'84',
'--source',
'ensembl',
'--out_dir',
self.dir,
'--genome',
get_temp_file_name(extension='fa.gz'),
'--chromosomes',
'MT',
'Y',
'-S',
'40', # Supress lower than ERROR messages.
]
self.assertEqual(subprocess.call(command_full), 0)
