def test_srnabench(self):
"""testing reading seqbuster files function"""
from mirtop.libs import logger
logger.initialize_logger("test", True, True)
logger = logger.getLogger(__name__)
from mirtop.importer import srnabench
annotate("data/examples/srnabench", srnabench.read_file, create=False)
def main(**kwargs):
kwargs = parse_cl(sys.argv[1:])
initialize_logger(kwargs['args'].out, kwargs['args'].debug,
kwargs['args'].print_debug)
logger = mylog.getLogger(__name__)
start = time.time()
if "gff" in kwargs:
logger.info("Run annotation")
reader(kwargs["args"])
elif "stats" in kwargs:
logger.info("Run stats.")
stats(kwargs["args"])
elif "compare" in kwargs:
logger.info("Run compare.")
compare(kwargs["args"])
elif "simulator" in kwargs:
logger.info("Run simulation")
simulate(kwargs["args"])
elif "counts" in kwargs:
logger.info("Run convert of GFF to TSV containing expression")
convert_gff_counts(kwargs["args"])
elif "export" in kwargs:
logger.info("Run export of GFF into other format.")
isomirs.convert(kwargs["args"])
elif "validator" in kwargs:
logger.info("Run validator.")
validator.check_multiple(kwargs["args"])
elif "query" in kwargs["args"]:
logger.info("Not yet ready: This will allow queries to GFF files.")
logger.info('It took %.3f minutes' % ((time.time() - start) / 60))
def test_srnabench(self):
"""testing reading seqbuster files function"""
from mirtop.libs import logger
logger.initialize_logger("test", True, True)
logger = logger.getLogger(__name__)
from mirtop.importer import srnabench
annotate("data/examples/srnabench", srnabench.read_file, create=False)
def main(**kwargs):
kwargs = parse_cl(sys.argv[1:])
initialize_logger(kwargs['args'].out, kwargs['args'].debug,
kwargs['args'].print_debug)
logger = mylog.getLogger(__name__)
start = time.time()
if "gff" in kwargs:
logger.info("Run annotation")
reader(kwargs["args"])
elif "stats" in kwargs:
logger.info("Run stats.")
stats(kwargs["args"])
elif "compare" in kwargs:
logger.info("Run compare.")
compare(kwargs["args"])
elif "simulator" in kwargs:
logger.info("Run simulation")
simulate(kwargs["args"])
elif "counts" in kwargs:
logger.info("Run convert of GFF to TSV containing expression")
convert_gff_counts(kwargs["args"])
elif "export" in kwargs:
logger.info("Run export of GFF into other format.")
isomirs.convert(kwargs["args"])
elif "validator" in kwargs:
logger.info("Run validator.")
validator.check_multiple(kwargs["args"])
elif "query" in kwargs["args"]:
logger.info("Not yet ready: This will allow queries to GFF files.")
logger.info('It took %.3f minutes' % ((time.time()-start)/60))
def test_collapse(self):
"""testing GFF function"""
from mirtop.libs import logger
logger.initialize_logger("test", True, True)
logger = logger.getLogger(__name__)
from mirtop.bam import bam
bam_fn = "data/aligments/collapsing-isomirs.sam"
annotate(bam_fn, bam.read_bam)
return True
def test_read_genomic(self):
from mirtop.mirna import mapper
from mirtop.libs import logger
logger.initialize_logger("test_read_files", True, True)
map_mir = mapper.read_gtf_to_mirna("data/examples/annotate/hsa.gff3")
print(map_mir)
# if map_mir["hsa-let-7a-1"]["hsa-let-7a-5p"][0] != 5:
# raise ValueError("GFF is not loaded correctly.")
return True
def test_read_genomic(self):
from mirtop.mirna import mapper
from mirtop.libs import logger
logger.initialize_logger("test_read_files", True, True)
map_mir = mapper.read_gtf_to_mirna("data/examples/annotate/hsa.gff3")
print(map_mir)
# if map_mir["hsa-let-7a-1"]["hsa-let-7a-5p"][0] != 5:
# raise ValueError("GFF is not loaded correctly.")
return True
def test_collapse(self):
"""testing GFF function"""
from mirtop.libs import logger
logger.initialize_logger("test", True, True)
logger = logger.getLogger(__name__)
from mirtop.bam import bam
bam_fn = "data/aligments/collapsing-isomirs.sam"
annotate(bam_fn, bam.read_bam)
return True
def test_optimir(self):
"""testing reading optimir files function"""
from mirtop.libs import logger
logger.initialize_logger("test", True, True)
logger = logger.getLogger(__name__)
from mirtop.importer import optimir
annotate("data/examples/optimir/synthetic_100_full.gff3",
optimir.read_file,
create=False)
def test_seqbuster(self):
"""testing reading seqbuster files function"""
from mirtop.libs import logger
logger.initialize_logger("test", True, True)
logger = logger.getLogger(__name__)
from mirtop.importer import seqbuster
print("\nperfect\n")
annotate("data/examples/seqbuster/reads20.mirna", seqbuster.read_file)
print("\naddition\n")
annotate("data/examples/seqbuster/readsAdd.mirna", seqbuster.read_file)
def test_seqbuster(self):
"""testing reading seqbuster files function"""
from mirtop.libs import logger
logger.initialize_logger("test", True, True)
logger = logger.getLogger(__name__)
from mirtop.importer import seqbuster
print("\nperfect\n")
annotate("data/examples/seqbuster/reads20.mirna", seqbuster.read_file)
print("\naddition\n")
annotate("data/examples/seqbuster/readsAdd.mirna", seqbuster.read_file)
def main(**kwargs):
kwargs = parse_cl(sys.argv[1:])
initialize_logger(kwargs['args'].out, kwargs['args'].debug,
kwargs['args'].print_debug)
logger = mylog.getLogger(__name__)
start = time.time()
if "annotate" in kwargs:
logger.info("Run annotation")
mirna.miraligner(kwargs["args"])
elif "simulator" in kwargs:
logger.info("Run simulation")
simulate(kwargs["args"])
logger.info('It took %.3f minutes' % ((time.time() - start) / 60))
def test_prost(self):
"""testing reading prost files function"""
from mirtop.libs import logger
logger.initialize_logger("test", True, True)
logger = logger.getLogger(__name__)
from mirtop.mirna import fasta
precursors = fasta.read_precursor("data/examples/annotate/hairpin.fa",
"hsa")
fn = "data/examples/prost/prost.example.txt"
from mirtop.importer import prost
reads = prost.read_file(fn, precursors, "miRBasev21",
"data/examples/annotate/hsa.gff3")
annotate("data/example/prost/prost.example.txt", reads, True)
def test_prost(self):
"""testing reading prost files function"""
from mirtop.libs import logger
logger.initialize_logger("test", True, True)
logger = logger.getLogger(__name__)
from mirtop.mirna import fasta
precursors = fasta.read_precursor("data/examples/annotate/hairpin.fa",
"hsa")
fn = "data/examples/prost/prost.example.txt"
from mirtop.importer import prost
reads = prost.read_file(
fn, precursors, "miRBasev21", "data/examples/annotate/hsa.gff3")
annotate("data/example/prost/prost.example.txt", reads, True)
def test_read(self):
from mirtop.mirna import mapper, fasta
from mirtop.libs import logger
logger.initialize_logger("test_read_files", True, True)
map_mir = mapper.read_gtf_to_precursor(
"data/examples/annotate/hsa.gff3")
print map_mir
if map_mir["hsa-let-7a-1"]["hsa-let-7a-5p"][0] != 5:
raise ValueError("GFF is not loaded correctly.")
fasta_precursor = fasta.read_precursor(
"data/examples/annotate/hairpin.fa", "hsa")
# read data/aligments/let7-perfect.bam
return True
def test_read(self):
from mirtop.mirna import mapper, fasta
from mirtop.libs import logger
logger.initialize_logger("test_read_files", True, True)
map_mir = mapper.read_gtf_to_precursor(
"data/examples/annotate/hsa.gff3")
print(map_mir)
if map_mir["hsa-let-7a-1"]["hsa-let-7a-5p"][0] != 5:
raise ValueError("GFF is not loaded correctly.")
fasta_precursor = fasta.read_precursor(
"data/examples/annotate/hairpin.fa", "hsa")
print(fasta_precursor)
fasta_precursor2 = fasta.read_precursor(
"data/examples/annotate/hairpin.fa", None)
print(fasta_precursor2)
if fasta_precursor != fasta_precursor2:
raise ValueError("species value generates two different dicts.")
# read data/aligments/let7-perfect.bam
return True
def test_alignment_genomic(self):
"""testing alignments function"""
from mirtop.bam import bam
from mirtop.libs import logger
logger.initialize_logger("test_read_files", True, True)
# print(annotate("data/examples/annotate/hsa-let-7a-5ploss1_neg.sam",
# bam.read_bam,
# gtf="data/db/hsa.gff3", genomic=True))
print("\ngenomic\n")
with make_workdir():
for example in [
"hsa-let-7a-nm", "hsa-let-7a-5ploss1",
"hsa-let-7a-3ploss1", "hsa-let-7a-5ploss1_neg"
]:
print(
annotate("data/examples/annotate/%s.sam" % example,
bam.read_bam,
gtf="data/db/mirbase/hsa.gff3",
genomic=True))
def test_counts(self):
"""testing convert_gff_counts in convert.py function"""
from mirtop.libs import logger
from mirtop.gff.convert import convert_gff_counts
import argparse
logger.initialize_logger("test counts", True, True)
logger = logger.getLogger(__name__)
args = argparse.Namespace()
args.hairpin = "data/examples/annotate/hairpin.fa"
args.sps = "hsa"
args.gtf = "data/examples/annotate/hsa.gff3"
args.gff = 'data/examples/synthetic/let7a-5p.gtf'
args.out = 'data/examples/synthetic'
args.add_extra = True
convert_gff_counts(args)
os.remove(os.path.join(args.out, "expression_counts.tsv"))
return True
def main(**kwargs):
kwargs = parse_cl(sys.argv[1:])
initialize_logger(kwargs['args'].out, kwargs['args'].debug,
kwargs['args'].print_debug)
logger = mylog.getLogger(__name__)
start = time.time()
if "gff" in kwargs:
logger.info("Run annotation")
reader(kwargs["args"])
elif "simulator" in kwargs:
logger.info("Run simulation")
simulate(kwargs["args"])
elif "check" in kwargs["args"]:
logger.info("Not yet ready: This will check GFF files.")
elif "query" in kwargs["args"]:
logger.info("Not yet ready: This will allow queries to GFF files.")
elif "convert" in kwargs["args"]:
logger.info(
"Not yet ready: This will output tabular format from GFF files.")
logger.info('It took %.3f minutes' % ((time.time() - start) / 60))
def test_counts(self):
"""testing convert_gff_counts in convert.py function"""
from mirtop.libs import logger
from mirtop.gff.convert import convert_gff_counts
import argparse
logger.initialize_logger("test counts", True, True)
logger = logger.getLogger(__name__)
args = argparse.Namespace()
args.hairpin = "data/examples/annotate/hairpin.fa"
args.sps = "hsa"
args.gtf = "data/examples/annotate/hsa.gff3"
args.gff = 'data/examples/synthetic/let7a-5p.gtf'
args.out = 'data/examples/synthetic'
args.add_extra = True
convert_gff_counts(args)
os.remove(os.path.join(args.out, "expression_counts.tsv"))
return True
def test_alignment(self):
"""testing alignments function"""
from mirtop.libs import logger
logger.initialize_logger("test", True, True)
logger = logger.getLogger(__name__)
from mirtop.mirna import fasta, mapper
precursors = fasta.read_precursor("data/examples/annotate/hairpin.fa",
"hsa")
matures = mapper.read_gtf_to_precursor(
"data/examples/annotate/hsa.gff3")
# matures = mirtop.mirna.read_mature("data/examples/annotate/mirnas.gff", "hsa")
def annotate(fn, precursors, matures):
from mirtop.bam import bam
from mirtop.gff import body
reads = bam.read_bam(fn, precursors)
ann = bam.annotate(reads, matures, precursors)
gff = body.create(ann, "miRBase21", "example", fn + ".gff3", "#")
print "\nlast1D\n"
annotate("data/aligments/let7-last1D.sam", precursors, matures)
#mirna TGAGGTAGTAGGTTGTATAGTT
#seq AGAGGTAGTAGGTTGTA
print "\n1D\n"
annotate("data/aligments/let7-1D.sam", precursors, matures)
#mirna TGAGGTAG-TAGGTTGTATAGTT
#seq TGAGGTAGGTAGGTTGTATAGTTA
print "\nlast7M1I\n"
annotate("data/aligments/let7-last7M1I.sam", precursors, matures)
#mirna TGAGGTAGTAGGTTGTATAGTT
#seq TGAGGTAGTAGGTTGTA-AGT
print "\nmiddle1D\n"
annotate("data/aligments/let7-middle1D.sam", precursors, matures)
#mirna TGAGGTAGTAGGTTGTATAGTT
#seq TGAGGTAGTAGGTTGTATAGTT
print "\nperfect\n"
annotate("data/aligments/let7-perfect.sam", precursors, matures)
#mirna TGAGGTAGTAGGTTGTATAGTT
#seq TGAGGTAGTAGGTTGTATAG (3tt 3TT)
print "\ntriming\n"
annotate("data/aligments/let7-triming.sam", precursors, matures)
def test_srnabench(self):
"""testing reading seqbuster files function"""
from mirtop.libs import logger
logger.initialize_logger("test", True, True)
logger = logger.getLogger(__name__)
from mirtop.mirna import fasta, mapper
precursors = fasta.read_precursor("data/examples/annotate/hairpin.fa",
"hsa")
matures = mapper.read_gtf_to_precursor(
"data/examples/annotate/hsa.gff3")
def annotate(fn, precursors, matures):
from mirtop.importer import srnabench
from mirtop.bam import bam
reads = srnabench.read_file(fn, precursors)
ann = bam.annotate(reads, matures, precursors)
return True
print "\nsRNAbench\n"
annotate("data/examples/srnabench/reads.annotation", precursors,
matures)
def test_collapse(self):
"""testing GFF function"""
from mirtop.libs import logger
from mirtop.mirna import mapper, fasta
from mirtop.gff import body, header
logger.initialize_logger("test", True, True)
logger = logger.getLogger(__name__)
precursors = fasta.read_precursor("data/examples/annotate/hairpin.fa",
"hsa")
# depend on https://github.com/miRTop/mirtop/issues/6
matures = mapper.read_gtf_to_precursor(
"data/examples/annotate/hsa.gff3")
# matures = mirtop.mirna.read_mature("data/examples/annotate/mirnas.gff", "hsa")
from mirtop.bam import bam
bam_fn = "data/aligments/collapsing-isomirs.sam"
reads = bam.read_bam(bam_fn, precursors)
ann = bam.annotate(reads, matures, precursors)
fn = bam_fn + ".gff"
h = header.create(bam_fn, ["example"], "miRBase21")
gff = body.create(ann, "miRBase21", "example", fn, header)
print gff
return True
def test_read_mir2genomic(self):
from mirtop.mirna import mapper
from mirtop.libs import logger
logger.initialize_logger("test_read_files", True, True)
map_mir = mapper.read_gtf_to_mirna("data/examples/annotate/hsa.gff3")
print(map_mir)
def test_read_hairpin_mirgenedb(self):
from mirtop.mirna import mapper
from mirtop.libs import logger
logger.initialize_logger("test_read_files", True, True)
map_mir = mapper.read_gtf_to_precursor("data/db/mirgenedb/hsa.gff")
print(map_mir)
help="File with mature sequences.", required=True)
parser.add_argument("-s", "--size", default=22,
help="Size of spike-ins to generate.")
parser.add_argument("-n", "--number", default=16,
help="Number of spike-ins to generate.")
parser.add_argument("-o", "--out", default="spikeins.fa",
help="Name used for output files.")
parser.add_argument("--seed", help="set up seed for reproducibility.",
default=42)
parser.add_argument("--universe", help="Set up universe sequences to avoid duplication.",
default=None)
args = parser.parse_args()
random.seed(args.seed)
mylog.initialize_logger(os.path.dirname(os.path.abspath(args.out)))
logger = mylog.getLogger(__name__)
# Read file to get all sequences longer than size - 2
size = args.size - 2
source = _read_fasta(args.fa, size)
logger.info("%s was read: %s sequences were loaded" % (args.fa, len(source)))
source = _update_ends(source)
logger.info("source updated with extended nts: %s" % source)
# Map all vs all with razers3
modified = _write_fasta(source, os.path.join(os.path.dirname(args.out), "modified.fa"))
sam = os.path.join(os.path.dirname(args.out), "modified.bam")
runner.run(("razers3 -i 75 -rr 80 -f -so 1 -o {output} {target} {query}").format(output=sam, target=modified, query=modified))
uniques = _parse_hits(sam, source)
print(uniques)
