def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
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("--task",
dest="task",
type="string",
help="analysis task to be executed")
parser.add_option("--infile",
dest="infile",
type="string",
help="input file path")
parser.add_option("--method",
dest="method",
type="choice",
choices=("replicate", "resample"),
help="whether to use replicate or resample "
"for consensus clustering.")
parser.add_option("--cluster-algorithm",
dest="cluster",
type="string",
help="hierarchical clustering algorithm")
parser.add_option("--expression-file",
dest="express",
type="string",
help="matching expression data from input"
" distance matrix")
parser.add_option("--cluster-file",
dest="clustfile",
type="string",
help="file to output cluster labels to")
parser.add_option("--output-file",
dest="outfile",
type="string",
help="output file to write to")
parser.add_option("--cut-height",
dest="cutHeight",
type="string",
help="threshold at which to define consensus clusters"
"as valid")
parser.add_option("--split-clusters",
dest="split",
action="store_true",
help="switch for using deepSplit in tree cutting")
parser.add_option("--cluster-size",
dest="cluster_size",
type="int",
help="minimum cluster size for tree cutting. Clusters "
"with fewer than this many objects will be merged with "
"nearest cluster. Default=30")
parser.add_option("--image-dir",
dest="images_dir",
type="string",
help="directory to write plots/figures to")
(options, args) = E.Start(parser, argv=argv)
infile = argv[-1]
parser.set_defaults(cutHeight=0,
conditions=None,
split=False,
cluster_size=30)
if options.task == "cluster":
data_frame = TS.treeCutting(infile=infile,
expression_file=options.express,
cluster_file=options.clustfile,
cluster_algorithm=options.cluster,
deepsplit=options.split)
elif options.task == "clustagree":
if options.method == "resample":
data_frame = TS.clusterAgreement(infile)
elif options.method == "replicate":
file_list = infile.split(",")
data_frame = TS.clusterAverage(file_list)
elif options.task == "consensus-cluster":
min_size = int(options.cluster_size)
data_frame = TS.consensusClustering(infile=infile,
cutHeight=float(options.cutHeight),
cluster_algorithm=options.cluster,
min_size=min_size,
deepsplit=options.split)
elif options.task == "pca":
files = infile.split(",")
infile = files[1]
cluster_file = files[0]
data_frame = TS.clusterPCA(infile=infile,
cluster_file=cluster_file,
image_dir=options.images_dir)
else:
pass
data_frame.to_csv(options.stdout,
sep="\t",
header=True,
index_label="gene_id")
# 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 argv is None:
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("--task", dest="task", type="string",
help="analysis task to be executed")
parser.add_option("--infile", dest="infile", type="string",
help="input file path")
parser.add_option("--method", dest="method", type="choice",
choices=("replicate", "resample"),
help="whether to use replicate or resample "
"for consensus clustering.")
parser.add_option("--cluster-algorithm", dest="cluster", type="string",
help="hierarchical clustering algorithm")
parser.add_option("--expression-file", dest="express", type="string",
help="matching expression data from input"
" distance matrix")
parser.add_option("--cluster-file", dest="clustfile", type="string",
help="file to output cluster labels to")
parser.add_option("--output-file", dest="outfile", type="string",
help="output file to write to")
parser.add_option("--cut-height", dest="cutHeight", type="string",
help="threshold at which to define consensus clusters"
"as valid")
parser.add_option("--split-clusters", dest="split", action="store_true",
help="switch for using deepSplit in tree cutting")
parser.add_option("--cluster-size", dest="cluster_size", type="int",
help="minimum cluster size for tree cutting. Clusters "
"with fewer than this many objects will be merged with "
"nearest cluster. Default=30")
parser.add_option("--image-dir", dest="images_dir", type="string",
help="directory to write plots/figures to")
# add common options (-h/--help, ...) and parse command line
(options, args) = E.Start(parser, argv=argv)
infile = argv[-1]
parser.set_defaults(cutHeight=0,
conditions=None,
split=False,
cluster_size=30)
if options.task == "cluster":
data_frame = TS.treeCutting(infile=infile,
expression_file=options.express,
cluster_file=options.clustfile,
cluster_algorithm=options.cluster,
deepsplit=options.split)
elif options.task == "clustagree":
if options.method == "resample":
data_frame = TS.clusterAgreement(infile)
elif options.method == "replicate":
file_list = infile.split(",")
data_frame = TS.clusterAverage(file_list)
elif options.task == "consensus-cluster":
min_size = int(options.cluster_size)
data_frame = TS.consensusClustering(infile=infile,
cutHeight=float(options.cutHeight),
cluster_algorithm=options.cluster,
min_size=min_size,
deepsplit=options.split)
elif options.task == "pca":
files = infile.split(",")
infile = files[1]
cluster_file = files[0]
data_frame = TS.clusterPCA(infile=infile,
cluster_file=cluster_file,
image_dir=options.images_dir)
else:
pass
data_frame.to_csv(options.stdout,
sep="\t",
header=True,
index_label="gene_id")
# Write footer and output benchmark information.
E.Stop()
