def summarize_rpf_counts(inputfiles, outputfile):
filemapping = ' '.join('%s:%s' % (s, Paths.cds_read_count_table(s))
for s in Options.SHORTTAG_SAMPLES)
pairs = ' '.join('%s:%s:%s' % (grpname, polya, rpf)
for grpname, (rpf, polya) in Options.RPF_PAIRS)
runproc("""
$SUMMARIZE_RPF_COUNTS "$filemapping" "$pairs" > $outputfile""",
outputfile)
def summarize_rpf_counts(inputfiles, outputfile):
filemapping = ' '.join('%s:%s' % (s, Paths.cds_read_count_table(s))
for s in Options.SHORTTAG_SAMPLES)
pairs = ' '.join('%s:%s:%s' % (grpname, polya, rpf)
for grpname, (rpf, polya) in Options.RPF_PAIRS)
runproc(
"""
$SUMMARIZE_RPF_COUNTS "$filemapping" "$pairs" > $outputfile""",
outputfile)
def clip_refseq_enrichment_statistics(inputfiles, outputfile):
inputfilesarg = ' '.join('%s:%s' % (
smp, Paths.genomespace_refseq_counts(smp))
for smp in Options.ALLCLIP_SAMPLES)
refsample = Options.CLIPCTL_SAMPLES[0] # XXX fix this to support multiple controls
clipsamples = ','.join(Options.CLIP_SAMPLES)
runproc("""
$STATS_CLIP_NRREFSEQ_ENRICHED \
$nr_refseq_db $refsample $clipsamples $inputfilesarg \
> $outputfile""", outputfile)
def clip_refseq_enrichment_statistics(inputfiles, outputfile):
inputfilesarg = ' '.join('%s:%s' %
(smp, Paths.genomespace_refseq_counts(smp))
for smp in Options.ALLCLIP_SAMPLES)
refsample = Options.CLIPCTL_SAMPLES[
0] # XXX fix this to support multiple controls
clipsamples = ','.join(Options.CLIP_SAMPLES)
runproc(
"""
$STATS_CLIP_NRREFSEQ_ENRICHED \
$nr_refseq_db $refsample $clipsamples $inputfilesarg \
> $outputfile""", outputfile)
# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
# OTHER DEALINGS IN THE SOFTWARE.
#
from ruffus import *
import os
from rnarry.nrclip import (Paths, Options, DerivedDatabaseBuilding,
SequenceAnnotation, ContaminantFilter,
SequenceProcessing)
from rnarry.nrclip.PipelineControl import *
@files([
Paths.genomespace_refseq_counts(sample)
for sample in Options.ALLCLIP_SAMPLES
], Paths.clip_enrichment_summary)
@follows(DerivedDatabaseBuilding.quantitate_refseq_in_gspace)
def clip_refseq_enrichment_statistics(inputfiles, outputfile):
inputfilesarg = ' '.join('%s:%s' %
(smp, Paths.genomespace_refseq_counts(smp))
for smp in Options.ALLCLIP_SAMPLES)
refsample = Options.CLIPCTL_SAMPLES[
0] # XXX fix this to support multiple controls
clipsamples = ','.join(Options.CLIP_SAMPLES)
runproc(
"""
$STATS_CLIP_NRREFSEQ_ENRICHED \
$nr_refseq_db $refsample $clipsamples $inputfilesarg \
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
# OTHER DEALINGS IN THE SOFTWARE.
#
from ruffus import *
import os
from rnarry.nrclip import (
Paths, Options, DerivedDatabaseBuilding, SequenceAnnotation,
ContaminantFilter, SequenceProcessing)
from rnarry.nrclip.PipelineControl import *
@files([Paths.genomespace_refseq_counts(sample)
for sample in Options.ALLCLIP_SAMPLES],
Paths.clip_enrichment_summary)
@follows(DerivedDatabaseBuilding.quantitate_refseq_in_gspace)
def clip_refseq_enrichment_statistics(inputfiles, outputfile):
inputfilesarg = ' '.join('%s:%s' % (
smp, Paths.genomespace_refseq_counts(smp))
for smp in Options.ALLCLIP_SAMPLES)
refsample = Options.CLIPCTL_SAMPLES[0] # XXX fix this to support multiple controls
clipsamples = ','.join(Options.CLIP_SAMPLES)
runproc("""
$STATS_CLIP_NRREFSEQ_ENRICHED \
$nr_refseq_db $refsample $clipsamples $inputfilesarg \
> $outputfile""", outputfile)
from rnarry.nrclip.PipelineControl import *
@files(for_each([Paths.nr_refseq_db, Paths.tspace_read_database],
Paths.cds_read_count_table,
Options.SHORTTAG_SAMPLES))
@follows(DataPreparation.build_nonredundant_refseq_database)
@follows(TranscriptomeAnalysis.build_tspace_read_database)
def count_cds_reads(inputfiles, outputfile, sample):
nr_refseq_db, tspace = inputfiles
runproc("""
$TSPACE_COUNT_CDS $nr_refseq_db $tspace > $outputfile""", outputfile)
@files([Paths.cds_read_count_table(s) for s in Options.SHORTTAG_SAMPLES],
Paths.rpf_summarized_table)
@follows(count_cds_reads)
def summarize_rpf_counts(inputfiles, outputfile):
filemapping = ' '.join('%s:%s' % (s, Paths.cds_read_count_table(s))
for s in Options.SHORTTAG_SAMPLES)
pairs = ' '.join('%s:%s:%s' % (grpname, polya, rpf)
for grpname, (rpf, polya) in Options.RPF_PAIRS)
runproc("""
$SUMMARIZE_RPF_COUNTS "$filemapping" "$pairs" > $outputfile""",
outputfile)
def tasks():
return [
@files(for_each(Paths.genomespace_read_database,
Paths.genomespace_refseq_counts,
Paths.ALL_SAMPLES))
@follows(build_genomespace_read_database)
@follows(DataPreparation.build_nonredundant_refseq_database)
def quantitate_refseq_in_gspace(inputfile, outputfile, sample):
gspacedir = os.path.dirname(inputfile)
runproc(
'$COUNT_REFSEQ_IN_GSPACE $outputfile $nr_refseq_db $gspacedir',
outputfile)
@files([Paths.nr_refseq_list] +
[Paths.genomespace_refseq_counts(sample)
for sample in Paths.ALL_SAMPLES],
Paths.genomespace_all_expressed_transcripts)
@follows(quantitate_refseq_in_gspace)
def make_list_of_expressed_transcripts(inputfiles, outputfile):
inputlist = ' '.join(inputfiles)
runproc("""
$ENV MINDEPTH=$GSPACE_STATS_MINIMUM_RAW_READS \
$REFSEQCNT_PICK_EXPRESSED $inputlist > $outputfile""", outputfile)
@files([Paths.nr_refseq_db, Paths.genomespace_all_expressed_transcripts,
Paths.genome_fasta,
Paths.genomespace_read_database(Options.SNPREF_SAMPLE)],
[Paths.reftranscriptome_sequences, Paths.reftranscriptome_cds_anno])
accession_pat = re.compile('ACC.*ID="([^"]*)";')
with DeleteOnError(outputfile, gzip.open) as output:
for line in urllib.urlopen(Paths.MIRBASE_URL):
if line.startswith('#'):
continue
fields = line[:-1].split('\t')
name = accession_pat.findall(fields[8])[0]
print >> output, '\t'.join([
'chr'+fields[0], str(int(fields[3])-1), fields[4],
'miRNA|%s|%s' % (name, name), '.', fields[6]
])
@files([(None, Paths.repeatmasker_original(chrom), chrom)
for chrom in Options.UCSC_REPEATMASKER_CHROMOSOMES])
@jobs_limit(Options.MAX_PARALLEL_DOWNLOADING, 'download')
def download_repeatmasker_catalogs(inputfile, outputfile, chrom):
import urllib
url = Paths.REPEATMASKER_URL % (Options.GENOME, chrom)
print 'Downloading %s ...' % url
urllib.urlretrieve(url, outputfile)
@files([Paths.repeatmasker_original(chrom)
for chrom in Options.UCSC_REPEATMASKER_CHROMOSOMES],
Paths.repeatmasker_catalog)
@follows(download_repeatmasker_catalogs)
def merge_repeatmasker_catalogs(inputfiles, outputfile):
@files(
for_each([Paths.nr_refseq_db, Paths.tspace_read_database],
Paths.cds_read_count_table, Options.SHORTTAG_SAMPLES))
@follows(DataPreparation.build_nonredundant_refseq_database)
@follows(TranscriptomeAnalysis.build_tspace_read_database)
def count_cds_reads(inputfiles, outputfile, sample):
nr_refseq_db, tspace = inputfiles
runproc(
"""
$TSPACE_COUNT_CDS $nr_refseq_db $tspace > $outputfile""", outputfile)
@files([Paths.cds_read_count_table(s) for s in Options.SHORTTAG_SAMPLES],
Paths.rpf_summarized_table)
@follows(count_cds_reads)
def summarize_rpf_counts(inputfiles, outputfile):
filemapping = ' '.join('%s:%s' % (s, Paths.cds_read_count_table(s))
for s in Options.SHORTTAG_SAMPLES)
pairs = ' '.join('%s:%s:%s' % (grpname, polya, rpf)
for grpname, (rpf, polya) in Options.RPF_PAIRS)
runproc(
"""
$SUMMARIZE_RPF_COUNTS "$filemapping" "$pairs" > $outputfile""",
outputfile)
def tasks():