def test_04(self):
samplename = 'SRR207111_HeLa18-30'
sampledir = '../share/small_RNA-seq_alignments/SRP006788/'
subprocess.call(['tar', '-xzf', sampledir + samplename + '.tar.gz'])
output_file = 'test.gtf'
command = ['flaimapper', '-o', output_file, '-f', '2', samplename + '.bam']
with subprocess.Popen(command) as pipe:
pipe.wait()
exit_code = pipe.poll()
self.assertEqual(exit_code, 0)
data = parse_gff(output_file)
u81_14 = False
u81_46 = False
u81_54 = False
i = 0
k = 0
for chunk in data: # range(len(data)):
chunk = data[i]
if chunk[0] == 'HGNC=10101&HUGO-Symbol=SNORD81&HUGO-Name=small_nucleolar_RNA,_C/D_box_81&LOCI=[chr1:173833274-173833370:strand=-]&SOURCE=RefSeq&SOURCE-ACCESSION=NR_003938&GENOME=hg19':
k += 1
if chunk[1] == 14 and chunk[2] == 36:
u81_14 = True
elif chunk[1] == 46 and chunk[2] == 67:
u81_46 = True
elif chunk[1] == 54 and chunk[2] == 79:
u81_54 = True
i += 1
if u81_14 and u81_46 and u81_54:
os.remove(output_file)
self.assertTrue(u81_14, "The first of the three SNORD81 fragments was not detected")
self.assertTrue(u81_46, "The second of the three SNORD81 fragments was not detected")
self.assertTrue(u81_54, "The third of the three SNORD81 fragments was not detected")
self.assertTrue(k == (3 * 2), "More than 3 fragments (%i) of SNORD81 were detected" % k) # *2 because every entry generates two GTF lines
from flaimapper.ncRNA import ncRNA
from flaimapper.utils import fasta_entry_names
from flaimapper.utils import parse_gff
from flaimapper.utils import link_mirbase_to_ncrnadb09
from flaimapper.FlaiMapperObject import FlaiMapperObject
import sys
tmp_dir = sys.argv[1].rstrip("/") + "/"
verbosity = "quiet"
miRNAs = miRBase("../../../../share/annotations/miRBase_20/miRNA.dat")
ncrna_library_names = fasta_entry_names(
"../../../../share/annotations/ncRNA_annotation/ncrnadb09.fa")
regions = parse_gff(
"../../../../share/annotations/ncRNA_annotation/ncrnadb09.gtf")
links = link_mirbase_to_ncrnadb09(
miRNAs, ncrna_library_names) # Crosslink miRBase with reference ncRNAs
dataset_id = "SRP041082"
experiments = ['SRR1232072', 'SRR1232073']
for experiment in experiments:
alignments = [
"../../../../share/small_RNA-seq_alignments/" + dataset_id + "/" +
experiment
]
# Load flaimapper
flaimapper = FlaiMapperObject('sslm', verbosity)
for alignment in alignments:
from flaimapper.miRBase import miRBase
from flaimapper.ncRNA import ncRNA
from flaimapper.utils import fasta_entry_names
from flaimapper.utils import parse_gff
from flaimapper.utils import link_mirbase_to_ncrnadb09
from flaimapper.FlaiMapperObject import FlaiMapperObject
import sys
tmp_dir = sys.argv[1].rstrip("/")+"/"
verbosity = "quiet"
miRNAs = miRBase("../../../../share/annotations/miRBase_20/miRNA.dat")
ncrna_library_names = fasta_entry_names("../../../../share/annotations/ncRNA_annotation/ncrnadb09.fa")
regions = parse_gff("../../../../share/annotations/ncRNA_annotation/ncrnadb09.gtf")
links = link_mirbase_to_ncrnadb09(miRNAs,ncrna_library_names) # Crosslink miRBase with reference ncRNAs
dataset_id = "SRP028959"
experiments = ['SRR954957', 'SRR954958', 'SRR954959']
for experiment in experiments:
alignments = ["../../../../share/small_RNA-seq_alignments/"+dataset_id+"/"+experiment]
# Load flaimapper
flaimapper = FlaiMapperObject('sslm',verbosity)
for alignment in alignments:
flaimapper.add_alignment(alignment)
results = flaimapper.count_reads_per_region(miRNAs,links,regions,10)
keys = sorted(results.keys())