# load options from the config file
PARAMS = P.get_parameters([
"%s/pipeline.yml" % os.path.splitext(__file__)[0], "../pipeline.yml",
"pipeline.yml"
])
# add configuration values from associated pipelines
#
# 1. pipeline_annotations: any parameters will be added with the
# prefix "annotations_". The interface will be updated with
# "annotations_dir" to point to the absolute path names.
PARAMS.update(
P.peek_parameters(PARAMS["annotations_dir"],
'genesets',
prefix="annotations_",
update_interface=True,
restrict_interface=True))
PARAMS["project_src"] = os.path.dirname(__file__)
# if necessary, update the PARAMS dictionary in any modules file.
# e.g.:
#
# import CGATPipelines.PipelineGeneset as PipelineGeneset
# PipelineGeneset.PARAMS = PARAMS
#
# Note that this is a hack and deprecated, better pass all
# parameters that are needed by a function explicitely.
RnaSeq.PARAMS = PARAMS
# load options from the config file
PARAMS = P.get_parameters([
"%s/pipeline.yml" % os.path.splitext(__file__)[0], "../pipeline.yml",
"pipeline.yml"
])
# add configuration values from associated pipelines
#
# 1. pipeline_genesets: any parameters will be added with the
# prefix "annotations_". The interface will be updated with
# "annotations_dir" to point to the absolute path names.
PARAMS.update(
P.peek_parameters(PARAMS["annotations_dir"],
"pipeline_genesets.py",
"genesets",
on_error_raise=__name__ == "__main__",
prefix="annotations_",
update_interface=True))
# ---------------------------------------------------
# Specific pipeline tasks
@transform(("pipeline.yml", ), regex("(.*)\.(.*)"), r"\1.counts")
def count_words(infile, outfile):
'''count the number of words in the pipeline configuration files.'''
# the command line statement we want to execute
statement = '''awk 'BEGIN { printf("word\\tfreq\\n"); }
{for (i = 1; i <= NF; i++) freq[$i]++}
END { for (word in freq) printf "%%s\\t%%d\\n", word, freq[word] }'
< %(infile)s > %(outfile)s'''
###################################################
###################################################
###################################################
# Pipeline configuration
###################################################
from CGATCore import Pipeline as P
P.get_parameters([
"%s/pipeline.yml" % os.path.splitext(__file__)[0], "../pipeline.yml",
"pipeline.yml"
],
defaults={'annotations_dir': ""})
PARAMS = P.PARAMS
PARAMS_ANNOTATIONS = P.peek_parameters(PARAMS["annotations_dir"], "genesets")
###################################################################
###################################################################
###################################################################
# Helper functions mapping tracks to conditions, etc
###################################################################
# load all tracks - exclude input/control tracks
Sample = PipelineTracks.Sample
TRACKS = PipelineTracks.Tracks(Sample).loadFromDirectory(
glob.glob("*.bed.gz"), "(\S+).bed.gz")
TRACKS_BEDFILES = ["%s.bed.gz" % x for x in TRACKS]