def spa(args):
"""
%prog spa spafiles
Convert chromosome ordering from SPA to simple lists. First column is the
reference order.
"""
from jcvi.algorithms.graph import merge_paths
from jcvi.utils.cbook import uniqify
p = OptionParser(spa.__doc__)
p.add_option(
"--unmapped",
default=False,
action="store_true",
help="Include unmapped scaffolds in the list [default: %default]")
opts, args = p.parse_args(args)
if len(args) < 1:
sys.exit(not p.print_help())
spafiles = args
paths = []
mappings = []
missings = []
for spafile in spafiles:
fp = open(spafile)
path = []
mapping = []
missing = []
for row in fp:
if row[0] == '#' or not row.strip():
continue
atoms = row.rstrip().split('\t')
if len(atoms) == 2:
a, c2 = atoms
assert a == "unmapped"
missing.append(c2)
continue
c1, c2, orientation = atoms
path.append(c1)
mapping.append(c2)
paths.append(uniqify(path))
mappings.append(mapping)
missings.append(missing)
ref = merge_paths(paths)
print "ref", len(ref), ",".join(ref)
for spafile, mapping, missing in zip(spafiles, mappings, missings):
mapping = [x for x in mapping if "random" not in x]
mapping = uniqify(mapping)
if len(mapping) < 50 and opts.unmapped:
mapping = uniqify(mapping + missing)
print spafile, len(mapping), ",".join(mapping)
def spa(args):
"""
%prog spa spafiles
Convert chromosome ordering from SPA to simple lists. First column is the
reference order.
"""
from jcvi.algorithms.graph import merge_paths
from jcvi.utils.cbook import uniqify
p = OptionParser(spa.__doc__)
p.add_option("--unmapped", default=False, action="store_true",
help="Include unmapped scaffolds in the list [default: %default]")
opts, args = p.parse_args(args)
if len(args) < 1:
sys.exit(not p.print_help())
spafiles = args
paths = []
mappings = []
missings = []
for spafile in spafiles:
fp = open(spafile)
path = []
mapping = []
missing = []
for row in fp:
if row[0] == '#' or not row.strip():
continue
atoms = row.rstrip().split('\t')
if len(atoms) == 2:
a, c2 = atoms
assert a == "unmapped"
missing.append(c2)
continue
c1, c2, orientation = atoms
path.append(c1)
mapping.append(c2)
paths.append(uniqify(path))
mappings.append(mapping)
missings.append(missing)
ref = merge_paths(paths)
print "ref", len(ref), ",".join(ref)
for spafile, mapping, missing in zip(spafiles, mappings, missings):
mapping = [x for x in mapping if "random" not in x]
mapping = uniqify(mapping)
if len(mapping) < 50 and opts.unmapped:
mapping = uniqify(mapping + missing)
print spafile, len(mapping), ",".join(mapping)
def compilevcf(args):
"""
%prog compilevcf samples.csv
Compile vcf results into master spreadsheet.
"""
p = OptionParser(compilevcf.__doc__)
p.add_option("--db", default="hg38", help="Use these lobSTR db")
p.add_option(
"--nofilter",
default=False,
action="store_true",
help="Do not filter the variants",
)
p.set_home("lobstr")
p.set_cpus()
p.set_aws_opts(store="hli-mv-data-science/htang/str-data")
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
(samples, ) = args
workdir = opts.workdir
store = opts.output_path
cleanup = not opts.nocleanup
filtered = not opts.nofilter
dbs = opts.db.split(",")
cwd = os.getcwd()
mkdir(workdir)
os.chdir(workdir)
samples = op.join(cwd, samples)
stridsfile = "STR.ids"
if samples.endswith((".vcf", ".vcf.gz")):
vcffiles = [samples]
else:
vcffiles = [x.strip() for x in must_open(samples)]
if not op.exists(stridsfile):
ids = []
for db in dbs:
ids.extend(STRFile(opts.lobstr_home, db=db).ids)
uids = uniqify(ids)
logging.debug("Combined: {} Unique: {}".format(len(ids), len(uids)))
fw = open(stridsfile, "w")
print("\n".join(uids), file=fw)
fw.close()
run_args = [(x, filtered, cleanup, store) for x in vcffiles]
cpus = min(opts.cpus, len(run_args))
p = Pool(processes=cpus)
for _ in p.map_async(run_compile, run_args).get():
continue
def compile(args):
"""
%prog compile samples.csv
Compile vcf results into master spreadsheet.
"""
from multiprocessing import Pool
p = OptionParser(compile.__doc__)
p.add_option("--db", default="hg38,hg38-named",
help="Use these lobSTR db")
p.set_home("lobstr")
p.set_cpus()
p.set_aws_opts(store="hli-mv-data-science/htang/str")
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
samples, = args
workdir = opts.workdir
dbs = opts.db.split(",")
mkdir(workdir)
os.chdir(workdir)
stridsfile = "STR.ids"
vcffiles = [x.strip() for x in must_open(samples)]
if not op.exists(stridsfile):
ids = []
for db in dbs:
ids.extend(STRFile(opts.lobstr_home, db=db).ids)
uids = uniqify(ids)
logging.debug("Combined: {} Unique: {}".format(len(ids), len(uids)))
fw = open(stridsfile, "w")
print >> fw, "\n".join(uids)
fw.close()
# Generate two alleles
dipuids = []
for uid in uids:
dipuids.extend([uid + ".1", uid + ".2"])
fw = open("header.ids", "w")
print >> fw, ",".join(dipuids)
fw.close()
p = Pool(processes=opts.cpus)
run_args = [(x, opts.store, opts.cleanup) for x in vcffiles]
#run(run_args[0])
for res in p.map_async(run, run_args).get():
continue
def compilevcf(args):
"""
%prog compilevcf samples.csv
Compile vcf results into master spreadsheet.
"""
p = OptionParser(compilevcf.__doc__)
p.add_option("--db", default="hg38", help="Use these lobSTR db")
p.add_option("--nofilter", default=False, action="store_true",
help="Do not filter the variants")
p.set_home("lobstr")
p.set_cpus()
p.set_aws_opts(store="hli-mv-data-science/htang/str-data")
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
samples, = args
workdir = opts.workdir
store = opts.output_path
cleanup = not opts.nocleanup
filtered = not opts.nofilter
dbs = opts.db.split(",")
cwd = os.getcwd()
mkdir(workdir)
os.chdir(workdir)
samples = op.join(cwd, samples)
stridsfile = "STR.ids"
if samples.endswith((".vcf", ".vcf.gz")):
vcffiles = [samples]
else:
vcffiles = [x.strip() for x in must_open(samples)]
if not op.exists(stridsfile):
ids = []
for db in dbs:
ids.extend(STRFile(opts.lobstr_home, db=db).ids)
uids = uniqify(ids)
logging.debug("Combined: {} Unique: {}".format(len(ids), len(uids)))
fw = open(stridsfile, "w")
print >> fw, "\n".join(uids)
fw.close()
run_args = [(x, filtered, cleanup, store) for x in vcffiles]
cpus = min(opts.cpus, len(run_args))
p = Pool(processes=cpus)
for res in p.map_async(run_compile, run_args).get():
continue
def compile(args):
"""
%prog compile samples.csv
Compile vcf results into master spreadsheet.
"""
p = OptionParser(compile.__doc__)
p.add_option("--db", default="hg38", help="Use these lobSTR db")
p.set_home("lobstr")
p.set_cpus()
p.set_aws_opts(store="hli-mv-data-science/htang/str-data")
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
samples, = args
workdir = opts.workdir
store = opts.output_path
cleanup = not opts.nocleanup
dbs = opts.db.split(",")
cwd = os.getcwd()
mkdir(workdir)
os.chdir(workdir)
samples = op.join(cwd, samples)
stridsfile = "STR.ids"
vcffiles = [x.strip() for x in must_open(samples)]
if not op.exists(stridsfile):
ids = []
for db in dbs:
ids.extend(STRFile(opts.lobstr_home, db=db).ids)
uids = uniqify(ids)
logging.debug("Combined: {} Unique: {}".format(len(ids), len(uids)))
fw = open(stridsfile, "w")
print >> fw, "\n".join(uids)
fw.close()
p = Pool(processes=opts.cpus)
run_args = [(x, store, cleanup) for x in vcffiles]
for res in p.map_async(run, run_args).get():
continue