def setUp(self):
self.epo_records = []
for i, (t, q) in enumerate(cigar_pairs):
gab_pair = (toCigar("homo_sapiens", i, t), toCigar("mus_musculus", i, q))
A = EPOitem._strfactory(gab_pair[0])
B = EPOitem._strfactory(gab_pair[1])
if A and B:
self.epo_records.append((A, B))
def test_rem_dash(self):
# ****--****-------**** 4M2D4M7D4M
# *******-------******* 7M7D7M
# has 4 dash columns and should become
# ****--****---**** 4M2D4M3D4M
# *******---******* 7M3D7M
for i in range(100):
dash_cols = random.randint(0, 10)
tStart = random.randint(0, 1000)
qStart = random.randint(0, 1000)
epo_pair = (
EPOitem._strfactory("homo_sapiens\t0\t1\t%d\t%d\t1\t%s" % (tStart, tStart+12-1, "4M2D4M%dD4M" % (dash_cols+3))),
EPOitem._strfactory("mus_musculus\t0\t1\t%d\t%d\t1\t%s" % (qStart, qStart+14-1, "7M%dD7M" % (dash_cols+3))))
chain = Chain._make_from_epo(epo_pair[0], epo_pair[1], {"chr1": 500}, {"chr1": 800})
ti = epo_pair[0].intervals(False)
qi = epo_pair[1].intervals(False)
assert ti[2][0] - ti[1][1] - dash_cols == chain[2][1]
assert qi[1][0] - qi[0][1] - dash_cols == chain[2][1]
# ----*****
# *-------*
# has 3 dash cols and should become
# *
# *
# with the qStart += 1 and tStart += 4
for i in range(100):
dash_cols = random.randint(0, 10)
tm = random.randint(6, 10)
qm = random.randint(1, 5)
tStart = random.randint(0, 1000)
qStart = random.randint(0, 1000)
epo_pair = (
EPOitem._strfactory("homo_sapiens\t0\t1\t%d\t%d\t1\t%s" % (tStart, tStart+tm-1, "%dD%dM" % (dash_cols+1, tm))),
EPOitem._strfactory("mus_musculus\t0\t1\t%d\t%d\t1\t%s" % (qStart, qStart+qm+1-1, "M%dD%dM" % (dash_cols+tm-qm, qm))))
chain = Chain._make_from_epo(epo_pair[0], epo_pair[1], {"chr1": 500}, {"chr1": 800})
if chain[1][-1] != qm:
pdb.set_trace()
assert chain[1][-1] == qm
# correct also for coordinate interpretation differences between UCSC and EPO
assert (qStart + 1) - 1 == chain[0].qStart, "%d != %d" % (qStart + 1, chain[0].qStart)
parser = argparse.ArgumentParser(description="""EPO alignments (.out) to .chain converter.""",
epilog="Olgert Denas (Taylor Lab)",
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument("input", help="File to process.")
parser.add_argument("--species", nargs=2, default=["homo_sapiens", "mus_musculus"],
help="Names of target and query species (respectively) in the alignment.")
parser.add_argument("--chrsizes", nargs=2, required=True,
help="Chromosome sizes for the given species.")
parser.add_argument("-o", '--output', metavar="FILE", default='stdout', type=outFile, help="Output file")
opt = parser.parse_args()
log.info("loading sizes ...")
tsizes = loadChrSizes(opt.chrsizes[0])
qsizes = loadChrSizes(opt.chrsizes[1])
log.info("loading alignments ...")
data = EPOitem._parse_epo(opt.input)
log.info("dumping ...")
for k in data:
components = data[k]
trg_comp = filter(lambda c: c.species == opt.species[0], components)
qr_comp = filter(lambda c: c.species == opt.species[1], components)
convert_action(trg_comp, qr_comp, tsizes, qsizes, opt)
default=["homo_sapiens", "mus_musculus"],
help=
"Names of target and query species (respectively) in the alignment.")
parser.add_argument("--chrsizes",
nargs=2,
required=True,
help="Chromosome sizes for the given species.")
parser.add_argument("-o",
'--output',
metavar="FILE",
default='stdout',
type=outFile,
help="Output file")
opt = parser.parse_args()
log.info("loading sizes ...")
tsizes = loadChrSizes(opt.chrsizes[0])
qsizes = loadChrSizes(opt.chrsizes[1])
log.info("loading alignments ...")
data = EPOitem._parse_epo(opt.input)
log.info("dumping ...")
for k in data:
components = data[k]
trg_comp = filter(lambda c: c.species == opt.species[0], components)
qr_comp = filter(lambda c: c.species == opt.species[1], components)
convert_action(trg_comp, qr_comp, tsizes, qsizes, opt)
default=["homo_sapiens", "mus_musculus"],
help=
"Names of target and query species (respectively) in the alignment.")
parser.add_argument("--chrsizes",
nargs=2,
required=True,
help="Chromosome sizes for the given species.")
parser.add_argument("-o",
'--output',
metavar="FILE",
default='stdout',
type=outFile,
help="Output file")
opt = parser.parse_args()
log.info("loading sizes ...")
tsizes = loadChrSizes(opt.chrsizes[0])
qsizes = loadChrSizes(opt.chrsizes[1])
log.info("loading alignments ...")
data = OrderedDict(sorted(EPOitem._parse_epo(opt.input).items()))
log.info("dumping ...")
for k in data:
components = data[k]
trg_comp = [c for c in components if c.species == opt.species[0]]
qr_comp = [c for c in components if c.species == opt.species[1]]
convert_action(trg_comp, qr_comp, tsizes, qsizes, opt)
log.warning("skipping chromosome/contig (%s, %s)" % (a.chrom, b.chrom))
if __name__ == '__main__':
parser = argparse.ArgumentParser(description="""EPO alignments (.out) to .chain converter.""",
epilog="Olgert Denas (Taylor Lab)",
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument("input", help="File to process.")
parser.add_argument("--species", nargs=2, default=["homo_sapiens", "mus_musculus"],
help="Names of target and query species (respectively) in the alignment.")
parser.add_argument("--chrsizes", nargs=2, required=True,
help="Chromosome sizes for the given species.")
parser.add_argument("-o", '--output', metavar="FILE", default='stdout', type=outFile, help="Output file")
opt = parser.parse_args()
log.info("loading sizes ...")
tsizes = loadChrSizes(opt.chrsizes[0])
qsizes = loadChrSizes(opt.chrsizes[1])
log.info("loading alignments ...")
data = OrderedDict(sorted(EPOitem._parse_epo(opt.input).items()))
log.info("dumping ...")
for k in data:
components = data[k]
trg_comp = [c for c in components if c.species == opt.species[0]]
qr_comp = [c for c in components if c.species == opt.species[1]]
convert_action(trg_comp, qr_comp, tsizes, qsizes, opt)