"*.csfasta.F3.gz",
)
SEQUENCEFILES = tuple(
[os.path.join(DATADIR, suffix_name) for suffix_name in SEQUENCESUFFIXES])
SEQUENCEFILES_REGEX = regex(
r"(\S+)-(\S+)-(\S+).(?P<suffix>fastq.1.gz|fastq.gz|sra)")
Sample = PipelineTracks.AutoSample
Sample.attributes = ('tissue', 'condition', 'replicate')
TRACKS = PipelineTracks.Tracks(Sample).loadFromDirectory(
[y for x in SEQUENCESUFFIXES for y in glob.glob(x)],
"(\S+).(fastq.1.gz|fastq.gz|sra)")
EXPERIMENTS = PipelineTracks.Aggregate(TRACKS, labels=("tissue", "condition"))
CONDITIONS = PipelineTracks.Aggregate(TRACKS, labels=("condition", ))
REPLICATES = PipelineTracks.Aggregate(TRACKS, labels=("replicate", ))
#########################################################################
# summarise read 3'
#########################################################################
@follows(mkdir("sequence_characteristics.dir"))
@transform(SEQUENCEFILES, SEQUENCEFILES_REGEX,
r"sequence_characteristics.dir/\1-\2-\3.\g<suffix>_start.tsv")
def summariseReadStart(infile, outfile):
# this only works for fastq files. Fails with .sra files
# this function and the next section should be replaced with a call to
# fastq-dump if the file ends with .sra and then use the functions of
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)
EXPERIMENTS = PipelineTracks.Aggregate(TRACKS, labels=("condition", "tissue"))
CONDITIONS = PipelineTracks.Aggregate(TRACKS, labels=("condition", ))
TISSUES = PipelineTracks.Aggregate(TRACKS, labels=("tissue", ))
############################################################################
# The folllowing need to be parameterized in a config file
# TISSUES=["GM00855", "GM00861" ]
# CONDITIONS=["D3", "unstim" ]
# REPLICATES=["R1", "R2" ]
TAG_UNSTIM = PARAMS_PIPELINE["tracks_unstimulated"]
UCSC_GENOME = PARAMS_PIPELINE["genome"]
if "motifs_plot" in P and P["motifs_plot"]:
MOTIFS = [x.strip() for x in P["motifs_plot"].split(",")]
else:
from cgatcore import pipeline as P
P.getParameters(
["%s/pipeline.ini" % os.path.splitext(__file__)[0],
"../pipeline.ini",
"pipeline.ini"])
PARAMS = P.PARAMS
###################################################################
# Helper functions mapping tracks to conditions, etc
GENESETS = PipelineTracks.Tracks(PipelineTracks.Sample).loadFromDirectory(
glob.glob("*.gtf.gz"),
"(\S+).gtf.gz")
TRACKS3 = PipelineTracks.Tracks(PipelineTracks.Sample3)
TRACKS = TRACKS3.loadFromDirectory(glob.glob("*.bam"), "(\S+).bam")
REPLICATE = PipelineTracks.Aggregate(TRACKS, labels=("replicate", ))
TIME = PipelineTracks.Aggregate(TRACKS, labels=("condition", "tissue"))
def connect():
'''connect to database.
Use this method to connect to additional databases.
Returns a database connection.
'''
dbh = sqlite3.connect(PARAMS["database_name"])
statement = '''ATTACH DATABASE '%s' as annotations''' % (
PARAMS["annotations_database"])
cc = dbh.cursor()