from cgatcore import pipeline as P
from rpy2.robjects import r as R
#########################################################################
#########################################################################
#########################################################################
# load options from the config file
P.getParameters([
"%s/pipeline.ini" % os.path.splitext(__file__)[0], "../pipeline.ini",
"pipeline.ini"
])
PARAMS = P.PARAMS
PARAMS_ANNOTATIONS = P.peekParameters(PARAMS["annotations_dir"],
"pipeline_annotations.py")
PipelineMedip.PARAMS = PARAMS
###################################################################
###################################################################
###################################################################
# Helper functions mapping tracks to conditions, etc
###################################################################
# load all tracks - exclude input/control tracks
Sample = PipelineTracks.Sample3
suffixes = ["export.txt.gz", "sra", "fastq.gz", "cfastq.1.gz", "csfasta.gz"]
TRACKS = sum(
itertools.chain([
import cgatcore.database as Database
import cgat.GTF as GTF
import cgatPipelines.PipelineTracks as PipelineTracks
# load options from the config file
P.getParameters([
"%s/pipeline.ini" % os.path.splitext(__file__)[0], "../pipeline.ini",
"pipeline.ini"
])
PARAMS = P.PARAMS
USECLUSTER = True
# link up with annotations
PARAMS_ANNOTATIONS = P.peekParameters(PARAMS["annotations_dir"],
"pipeline_annotations.py")
# link up with ancestral repeats
PARAMS_ANCESTRAL_REPEATS = P.peekParameters(PARAMS["ancestral_repeats_dir"],
"pipeline_ancestral_repeats.py")
###################################################################
###################################################################
# Helper functions mapping tracks to conditions, etc
###################################################################
# collect sra nd fastq.gz tracks
TRACKS = PipelineTracks.Tracks(PipelineTracks.Sample).loadFromDirectory(
glob.glob("*.gtf.gz"),
"(\S+).gtf.gz",
exclude=("repeats.gtf.gz", "introns.gtf.gz", "merged.gtf.gz"))
###################################################
###################################################
###################################################
# Pipeline configuration
###################################################
# load options from the config file
from cgatcore import pipeline as P
PARAMS = P.getParameters(
["%s/pipeline.ini" % os.path.splitext(__file__)[0],
"../pipeline.ini",
"pipeline.ini"])
PARAMS.update(P.peekParameters(
PARAMS["annotations_dir"],
"pipeline_annotations.py",
prefix="annotations_",
update_interface=True))
# Update the PARAMS dictionary in any PipelineModules
# e.g.:
# import cgatPipelines.PipelineGeneset as PipelineGeneset
# PipelineGeneset.PARAMS = PARAMS
def connect():
'''connect to database.
Use this method to connect to additional databases.
from cgatcore import pipeline as Pipeline
import cgatPipelines.PipelineTracks as PipelineTracks
###################################################################
###################################################################
# parameterization
EXPORTDIR = P.get('calling_exportdir', P.get('exportdir', 'export'))
DATADIR = P.get('calling_datadir', P.get('datadir', '.'))
DATABASE = P.get('calling_backend',
P.get('report_sql_backend', 'sqlite:///./csvdb'))
###################################################################
# cf. pipeline_chipseq.py
# This should be automatically gleaned from pipeline_chipseq.py
###################################################################
PARAMS_PIPELINE = Pipeline.peekParameters(".", "pipeline_chipseq.py")
Sample = PipelineTracks.Sample3
suffixes = ["export.txt.gz", "sra", "fastq.gz", "fastq.1.gz", "csfasta.gz"]
TRACKS = sum(
itertools.chain([
PipelineTracks.Tracks(Sample).loadFromDirectory([
x for x in glob.glob("%s/*.%s" % (DATADIR, s)) if "input" not in x
], "%s/(\S+).%s" % (DATADIR, s)) for s in suffixes
]), PipelineTracks.Tracks(Sample))
Sample.setDefault("asTable")
ALL = PipelineTracks.Aggregate(TRACKS)