def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-t",
"--test",
dest="test",
type="string",
help="supply help")
parser.add_option("--k",
dest="k",
type="int",
default=0,
help="value of k to adjust adaptive tuning function")
parser.add_option("--out",
dest="outfile",
type="string",
help="output file name")
parser.add_option("--expression-file",
dest="expr",
type="string",
help="file containing expression data")
parser.add_option("--parallel",
dest="parallel",
action="store_true",
default=False,
help="switches on parallel, will"
" split distance matrix into relevant number of"
" slices. Start-end positions are defined by"
" the file name.")
parser.add_option("--distance-metric",
dest="dist_metric",
type="string",
help="distance metric to use for dissimilarity of time "
"series objects. Choices: dtw, cross-correlate, "
"temporal-correlate. Default=dtw")
parser.add_option("--lag",
dest="lag",
type="string",
help="cross correlation lag to report")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.start(parser, argv=argv)
infile = args[-1]
parser.set_defaults(lag=0, k=0)
if options.parallel:
datfile = options.expr
else:
datfile = infile
data = pd.read_table(datfile, sep="\t", index_col=0, header=0)
# data should already be sorted in time-series order
# the time and replicate columns needs to be dropped to ensure only the
# gene data is passed into the DTW function
# drop header line(s) and non-numerical rows
try:
data.drop(['times'], inplace=True, axis=0)
data.drop(['replicates'], inplace=True, axis=0)
except ValueError:
pass
genes = data.index
data = data.convert_objects(convert_numeric=True)
# iterate over the genes list in nested loops to get
# all pair-wise combinations.
if options.dist_metric == "dtw":
if options.parallel:
start_idx = int(infile.split("-")[3].split("_")[0])
end_idx = int(infile.split("-")[3].split("_")[1])
slice_idx = genes[start_idx:end_idx]
df_ = TS.dtwWrapper(data=data,
rows=genes,
columns=slice_idx,
k=options.k)
else:
df_ = TS.dtwWrapper(data=data,
rows=genes,
columns=genes,
k=options.k)
elif options.dist_metric == "cross-correlate":
if options.lag is None:
options.lag = 0
else:
pass
if options.parallel:
start_idx = int(infile.split("/")[-1].split("-")[3].split("_")[0])
end_idx = int(infile.split("/")[-1].split("-")[3].split("_")[1])
slice_idx = genes[start_idx:end_idx]
df_ = TS.correlateDistanceMetric(data=data,
rows=genes,
columns=slice_idx,
method=options.dist_metric,
lag=int(options.lag))
else:
df_ = TS.correlateDistanceMetric(data=data,
rows=genes,
columns=genes,
method=options.dist_metric,
lag=int(options.lag))
elif options.dist_metric == "temporal-correlate":
if options.parallel:
start_idx = int(infile.split("/")[-1].split("-")[3].split("_")[0])
end_idx = int(infile.split("/")[-1].split("-")[3].split("_")[1])
slice_idx = genes[start_idx:end_idx]
df_ = TS.correlateDistanceMetric(data=data,
rows=genes,
columns=slice_idx,
method=options.dist_metric)
else:
df_ = TS.correlateDistanceMetric(data=data,
rows=genes,
columns=genes,
method=options.dist_metric)
if not options.outfile:
df_.to_csv(options.stdout, sep="\t")
else:
df_.to_csv(options.outfile, sep="\t")
# write footer and output benchmark information
E.stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if not argv:
argv = sys.argv
# setup command line parser
parser = E.OptionParser(version="%prog version: $Id$",
usage=globals()["__doc__"])
parser.add_option("-t", "--test", dest="test", type="string",
help="supply help")
parser.add_option("--k", dest="k", type="int", default=0,
help="value of k to adjust adaptive tuning function")
parser.add_option("--out", dest="outfile", type="string",
help="output file name")
parser.add_option("--expression-file", dest="expr", type="string",
help="file containing expression data")
parser.add_option("--parallel", dest="parallel", action="store_true",
default=False, help="switches on parallel, will"
" split distance matrix into relevant number of"
" slices. Start-end positions are defined by"
" the file name.")
parser.add_option("--distance-metric", dest="dist_metric", type="string",
help="distance metric to use for dissimilarity of time "
"series objects. Choices: dtw, cross-correlate, "
"temporal-correlate. Default=dtw")
parser.add_option("--lag", dest="lag", type="string",
help="cross correlation lag to report")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
infile = args[-1]
parser.set_defaults(lag=0,
k=0)
if options.parallel:
datfile = options.expr
else:
datfile = infile
data = pd.read_table(datfile,
sep="\t",
index_col=0,
header=0)
# data should already be sorted in time-series order
# the time and replicate columns needs to be dropped to ensure only the
# gene data is passed into the DTW function
# drop header line(s) and non-numerical rows
try:
data.drop(['times'], inplace=True, axis=0)
data.drop(['replicates'], inplace=True, axis=0)
except ValueError:
pass
genes = data.index
data = data.convert_objects(convert_numeric=True)
# iterate over the genes list in nested loops to get
# all pair-wise combinations.
if options.dist_metric == "dtw":
if options.parallel:
start_idx = int(infile.split("-")[3].split("_")[0])
end_idx = int(infile.split("-")[3].split("_")[1])
slice_idx = genes[start_idx:end_idx]
df_ = TS.dtwWrapper(data=data,
rows=genes,
columns=slice_idx,
k=options.k)
else:
df_ = TS.dtwWrapper(data=data,
rows=genes,
columns=genes,
k=options.k)
elif options.dist_metric == "cross-correlate":
if options.lag is None:
options.lag = 0
else:
pass
if options.parallel:
start_idx = int(infile.split("/")[-1].split("-")[3].split("_")[0])
end_idx = int(infile.split("/")[-1].split("-")[3].split("_")[1])
slice_idx = genes[start_idx:end_idx]
df_ = TS.correlateDistanceMetric(data=data,
rows=genes,
columns=slice_idx,
method=options.dist_metric,
lag=int(options.lag))
else:
df_ = TS.correlateDistanceMetric(data=data,
rows=genes,
columns=genes,
method=options.dist_metric,
lag=int(options.lag))
elif options.dist_metric == "temporal-correlate":
if options.parallel:
start_idx = int(infile.split("/")[-1].split("-")[3].split("_")[0])
end_idx = int(infile.split("/")[-1].split("-")[3].split("_")[1])
slice_idx = genes[start_idx:end_idx]
df_ = TS.correlateDistanceMetric(data=data,
rows=genes,
columns=slice_idx,
method=options.dist_metric)
else:
df_ = TS.correlateDistanceMetric(data=data,
rows=genes,
columns=genes,
method=options.dist_metric)
if not options.outfile:
df_.to_csv(options.stdout, sep="\t")
else:
df_.to_csv(options.outfile, sep="\t")
# write footer and output benchmark information
E.Stop()
