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 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 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_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_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 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 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_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_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_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
import mirtop.libs.logger as mylog
logger = mylog.getLogger(__name__)
def create(reads, database, sample, fn, header):
"""Read https://github.com/miRTop/mirtop/issues/9"""
seen = set()
lines = []
seen_ann = {}
# print >>out_handle, "seq\tname\tfreq\tchrom\tstart\tend\tmism\tadd\tt5\tt3\ts5\ts3\tDB\tprecursor\tambiguity\tName"
out_handle = open(fn, 'w')
print >> out_handle, header
filter_precursor = 0
filter_score = 0
for r, read in reads.iteritems():
hits = set()
[
hits.add(mature.mirna) for mature in read.precursors.values()
if mature.mirna
]
hits = len(hits)
for p, iso in read.precursors.iteritems():
if len(iso.subs) > 3 or not iso.mirna:
continue
filter_precursor += 1
if (r, iso.mirna) not in seen:
seen.add((r, iso.mirna))
chrom = iso.mirna
if not chrom:
chrom = p
# count = _get_freq(r)
from Bio import pairwise2
from Bio.Seq import Seq
from collections import defaultdict
from mirtop.mirna.keys import CODE2NT, NT2CODE
import mirtop.libs.logger as mylog
logger = mylog.getLogger(__name__)
class hits:
""""Class with alignment information."""
def __init__(self):
self.sequence = ""
self.idseq = ""
self.precursors = defaultdict(isomir)
self.score = []
self.best_hits = [] # maybe sam object?
self.counts = 0
def set_sequence(self, seq):
self.sequence = seq
self.idseq = make_id(seq)
def set_precursor(self, precursor, isomir):
self.precursors[precursor] = isomir
def remove_precursor(self, precursor):
del self.precursors[precursor]