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):
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 setUp(self):
warnings.simplefilter("ignore", ResourceWarning)
self.out_dir = get_temp_dir()
self.type_header = ['Type', 'Length', 'cDNA #', 'cDNA %']
self.subtype_header = ['Subtype', 'Length', 'cDNA #', 'cDNA %']
self.gene_header = [
'Gene name (Gene ID)', 'Length', 'cDNA #', 'cDNA %'
]
def setUp(self):
self.dir = get_temp_dir()
self.index_dir = get_temp_dir()
self.genome = make_fasta_file(num_sequences=2, seq_len=1000)
self.reads = make_fastq_file(genome=self.genome)
self.annotation = 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";'
],
])
warnings.simplefilter("ignore", ResourceWarning)
def setUp(self):
self.dir = get_temp_dir()
self.adapter = 'CCCCCCCCC'
self.barcodes = [
'NNNGGTTNN',
'NNNTTGTNN',
'NNNCAATNN',
'NNNACCTNN',
'NNNGGCGNN',
]
self.reads = make_fastq_file(barcodes=self.barcodes,
adapter=self.adapter)
warnings.simplefilter("ignore", ResourceWarning)
def test_templates1(self):
out_dir = get_temp_dir()
segmentation = make_file_from_list([
['1', '.', 'intergenic', '1', '10', '.', '+', '.', 'gene_id ".";'],
[
'1', '.', 'UTR3', '11', '20', '.', '+', '.',
'biotype "mRNA";gene_name "ABC";gene_id "G1";'
],
[
'1', '.', 'intron', '21', '30', '.', '+', '.',
'biotype "lncRNA";gene_name "ABC";gene_id "G1";'
],
[
'1', '.', 'CDS', '31', '40', '.', '+', '.',
'biotype "mRNA";gene_name "DEF";gene_id "G2";'
],
[
'1', '.', 'intron', '41', '50', '.', '+', '.',
'biotype "sRNA,lncRNA";gene_name "DEF"; gene_id "G2";'
],
])
region.summary_templates(segmentation, out_dir)
results_type = make_list_from_file(
os.path.join(out_dir, region.TEMPLATE_TYPE), '\t')
self.assertEqual(results_type, [
['CDS', '10'],
['UTR3', '10'],
['intron', '20'],
['intergenic', '10'],
])
results_subtype = make_list_from_file(os.path.join(
out_dir, region.TEMPLATE_SUBTYPE),
fields_separator='\t')
self.assertEqual(results_subtype, [
['CDS mRNA', '10'],
['UTR3 mRNA', '10'],
['intron lncRNA', '15'],
['intron sRNA', '5'],
['intergenic', '10'],
])
results_gene = make_list_from_file(os.path.join(
out_dir, region.TEMPLATE_GENE),
fields_separator='\t')
self.assertEqual(results_gene, [
['.', '', '10'],
['G1', 'ABC', '20'],
['G2', 'DEF', '20'],
])
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 test_e2e(self):
"""
From raw reads and ENSEMBL annotation to rnamaps.
"""
# Make segmentation
seg = get_temp_file_name(extension='gtf')
iCount.genomes.segment.get_regions(self.gtf, seg, self.fai)
# 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)
# Make all sorts of analysis and save it:
normal_out = get_temp_file_name(extension='tsv')
strange_out = get_temp_file_name(extension='bam')
cross_tr_out = get_temp_file_name(extension='tsv')
iCount.analysis.rnamaps.run(bam, seg, normal_out, strange_out, cross_tr_out,
implicit_handling='split')
# Normal output:
expected_out = [
['RNAmap', 'type', 'position', 'all', 'explicit'],
['CDS-CDS', '-40', '0.3333', '0'],
['CDS-UTR3', '-25', '0.25', '0'],
['CDS-intergenic', '-20', '1', '1'],
['CDS-intergenic', '30', '0.5', '0'],
['CDS-intergenic', '250', '1', '0'],
['CDS-intron', '-40', '0.3333', '0'],
['CDS-intron', '-25', '0.25', '0'],
['UTR5-CDS', '5', '0.25', '0'],
['UTR5-intron', '-10', '1', '1'],
['UTR5-intron', '-8', '2', '2'],
['UTR5-intron', '10', '0.5', '0'],
['UTR5-intron', '13', '1', '0'],
['intergenic-CDS', '-70', '0.5', '0'],
['intergenic-CDS', '10', '0.3333', '0'],
['intergenic-UTR5', '-20', '1', '1'],
['intron-CDS', '-40', '0.5', '0'],
['intron-CDS', '-37', '1', '0'],
['intron-CDS', '5', '0.25', '0'],
]
self.assertEqual(expected_out, make_list_from_file(normal_out))
# Cross transcript:
expected_cross_transcript = [
['chrom', 'strand', 'xlink', 'second-start', 'end-position', 'read_len'],
['1', '+', '234', '236', '284', '50'],
]
self.assertEqual(expected_cross_transcript, make_list_from_file(cross_tr_out))
# Strange:
strange_reads = list(pysam.AlignmentFile(strange_out, 'rb')) # pylint: disable=no-member
self.assertEqual(len(strange_reads), 1)
strange_read = strange_reads[0]
self.assertEqual(strange_read.query_name, 'name_strange:rbc:GGGG')
self.assertEqual(strange_read.reference_start, 250)
self.assertEqual(strange_read.cigar, [(0, 45), (2, 15), (0, 70)])
def setUp(self):
self.tempdir = get_temp_dir()
warnings.simplefilter("ignore", ResourceWarning)
def setUp(self):
self.tempdir = get_temp_dir()
self.tmpfile = get_temp_file_name(extension='.gtf.gz')
warnings.simplefilter("ignore", ResourceWarning)
