import sys
from subprocess import Popen, PIPE
import shutil
import django
django.setup()
from osqpipe.models import Restrictome, Genome, Program
from osqutil.cluster import ClusterJobSubmitter
from osqutil.utilities import write_to_remote_file, transfer_file, checksum_file
from osqutil.config import Config
from osqutil.setup_logs import configure_logging
from logging import INFO, DEBUG
LOGGER = configure_logging('hicup')
class HiCUP(object):
def __init__(self, fq1, genome=None, enzyme=None, fq2=None):
self.fq1 = fq1
self.fq2 = fq2
self.genome = genome
self.genome_index = None
self.enzyme = enzyme
self.restriction_file = None
self._check_file(fq1)
self._check_file(fq2)
import time
import datetime
import re
from subprocess import Popen, PIPE
from shutil import copy2
from django.db import transaction
from ..models import ArchiveLocation, Lanefile, Alnfile, \
QCfile, AlnQCfile, Peakfile, MergedAlnfile, Datafile
from osqutil.utilities import checksum_file, bash_quote
from osqutil.config import Config
from osqutil.setup_logs import configure_logging
LOGGER = configure_logging('archive')
CONFIG = Config()
################################################################################
def _archive_file_via_scp(fobj, attempts=1, sleeptime=2):
'''
A wrapper for scp allowing multiple attempts for the transfer in case
of recoverable error.
'''
unrecoverable = [
'No such file or directory',
'Failed to add the host to the list of known hosts',
'Operation not permitted'
]
md5sums = None
if ARGS.md5arguments:
fnames = []
md5sums = []
fname = True
for s in ARGS.files:
if fname:
fnames.append(s)
fname = False
else:
md5sums.append(s)
fname = True
if len(fnames) == len(md5sums):
ARGS.files = fnames
LOGGER = configure_logging(level=DEBUG)
django.setup()
HND = RepoFileHandler()
if ARGS.summary_file is not None:
HND.add_lane_summary(ARGS.summary_file)
if len(ARGS.files):
if ARGS.qcfile:
HND.add_qc_files(ARGS.files, ARGS.program_name, md5sums=md5sums)
else:
HND.run(ARGS.files,
md5files=ARGS.md5files,
archive=ARGS.archive,
md5sums=md5sums)
# The osqpipe python package is distributed in the hope that it will # be useful, but WITHOUT ANY WARRANTY; without even the implied # warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. # See the GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with the osqpipe python package. If not, see # <http://www.gnu.org/licenses/>. import sys import os # set up logger from osqutil.setup_logs import configure_logging from logging import WARNING LOGGER = configure_logging(level=WARNING) # import config from osqutil.config import Config # For insertion of lane info: import django from osqpipe.models import Lane, Library, ExternalRecord # set up config DBCONF = Config() django.setup() def check_ena_submission_integrity(code):
'''Script to fetch fastq files from the LIMS.'''
import sys
import os
import os.path
import re
from osqutil.utilities import build_incoming_fastq_name, unzip_file, \
set_file_permissions, checksum_file
from .upstream_lims import Lims
from ..models import Library, Lane
from osqutil.config import Config
from osqutil.setup_logs import configure_logging
from logging import INFO, DEBUG
LOGGER = configure_logging('fetch_fastq')
###############################################################################
class FQFileFetcher(object):
'''Class used to query the LIMS for fastq files associated with a
given flowcell and download them to a destination directory.'''
__slots__ = ('destination', 'lims', 'targets', 'test_mode', 'conf',
'unprocessed_only', 'force_download')
def __init__(self,
destination,
lims=None,
test_mode=False,
'''Module providing functions used to retrieve MGA file information
from the Genologics LIMS.'''
import sys
import os
import os.path
from .upstream_lims import Lims
from osqutil.utilities import call_subprocess, CalledProcessError
from osqutil.config import Config
from osqutil.setup_logs import configure_logging
from logging import INFO, DEBUG
CONFIG = Config()
LOGGER = configure_logging('fetch_mga')
TEST_MODE = False
def fetch_mga(flowcell, flowlane, destination, nameprefix, lims_fc=None):
"""Fetches MGA report from Genologics LIMS. Returns PDF report."""
mgafiles = []
flowlane = int(flowlane)
# start logging
if TEST_MODE:
LOGGER.setLevel(DEBUG)
else:
LOGGER.setLevel(INFO)
'''Given a set of metadata on the command-line, create a new row in
the library repository table.'''
import sys
import re
import copy
from osqutil.config import Config
from ..models import Factor, Genome, Antibody, Strain, Sex, Tissue, \
Library, Libtype, Project, Adapter, Linkerset, Sample, Source, \
Condition
from django.db import transaction
from osqutil.setup_logs import configure_logging
LOGGER = configure_logging()
CONFIG = Config()
######################################################################
class AnnotationMismatchError(ValueError):
'''
Custom exception class used to signal a mismatch between input and database.
'''
pass
######################################################################
class LibraryHandler(object):
'''Class encapsulating the creation of new library records.'''
import re
import tarfile
from tempfile import mkdtemp
from shutil import rmtree, move, copy
from pkg_resources import Requirement, resource_filename
from django.db import transaction, models
from ..models import Program, LaneQC, QCfile, Filetype, Lanefile, DataProvenance, Datafile, DataProcess
from osqutil.progsum import ProgramSummary
from osqutil.utilities import checksum_file, call_subprocess, rezip_file, set_file_permissions, transfer_file
from osqutil.config import Config
from osqutil.setup_logs import configure_logging
CONFIG = Config()
LOGGER = configure_logging('laneqc')
class QCReport(object):
'''
Abstract superclass handling all QC reports. Note that this is
implemented as a context manager, so you would typically use
subclasses in the following way::
with LaneFastQCReport(target=l, program_name='fastqc') as rep:
rep.insert_into_repository()
'''
__slots__ = ('target', 'workdir', 'output_files', 'program_name', 'path',
'program_params', '_dbprog', '_delete_workdir', 'output_md5s',
'move_files')
from django.db import transaction
from ..models import Alnfile, Library, Alignment, MergedAlnfile, Genome, Lane
from osqutil.samtools import count_bam_reads
from osqutil.utilities import call_subprocess, checksum_file, \
sanitize_samplename
from osqutil.config import Config
from .bwa_runner import ClusterJobManager
import xml.etree.ElementTree as ET
from tempfile import NamedTemporaryFile
from pysam import AlignmentFile
from shutil import move
from osqutil.setup_logs import configure_logging
LOGGER = configure_logging('gatk')
CONFIG = Config()
################################################################################
# A handful of utility functions.
def retrieve_readgroup_alignment(rgroup, genome=None, bamfilter=False):
'''
Simply returns the osqpipe Alignment object for a given read group,
a list of which is returned by this call:
pysam.AlignmentFile.header.get('RG', []).
'''
alns = Alignment.objects.filter(lane__library__code=rgroup.get('LB'),
lane__facility__code=rgroup.get('CN'),
lane__lanenum=rgroup.get('PU'))
from pipes import quote
from distutils import spawn
from socket import getfqdn, socket, AF_UNIX, SOCK_STREAM, gethostname
from getpass import getuser
from tempfile import NamedTemporaryFile
from osqutil.utilities import bash_quote, sanitize_samplename, \
BamPostProcessor
from osqutil.progsum import ProgramSummary
from osqutil.cluster import make_bam_name_without_extension, \
ClusterJobRunner, ClusterJobSubmitter, DesktopJobSubmitter
from osqutil.config import Config
from osqutil.setup_logs import configure_logging
LOGGER = configure_logging('bwa_runner')
##############################################################################
def genome_fasta_path(genome, genomedir, indexdir=None):
'''
Returns the expected path to the fasta file for a given genome
index. If a specific fasta index directory is specified
(e.g. bwa-0.6.1), the path points to a fasta file in that
subdirectory.
'''
sciname = genome.species.scientific_name
sciname = sciname.replace(" ", "_")
sciname = sciname.lower()
if indexdir is not None:
import re
import os.path
import weakref
from datetime import date, timedelta
from time import sleep
import xml.etree.ElementTree as ET
import requests
from osqutil.config import Config
from osqutil.utilities import munge_cruk_emails
from ..models import LibraryNameMap, User
from osqutil.setup_logs import configure_logging
from logging import INFO, DEBUG
LOGGER = configure_logging('lims')
CONFIG = Config()
###############################################################################
def http_download_file(url, local_filename, params=None):
'''
Download a remote file URL to a local filename. Returns the local
filename on success.
'''
# See http://stackoverflow.com/a/16696317 for the original source.
if params is None:
params = {}
# Read large files in chunks using stream = True parameter
import re
from osqutil.utilities import checksum_file, \
build_incoming_fastq_name, parse_incoming_fastq_name, call_subprocess, set_file_permissions, \
munge_cruk_emails, unzip_file, rezip_file, is_zipped
from .upstream_lims import Lims
from osqutil.config import Config
from ..models import Library, Lane, Status, LibraryNameMap, User, Adapter, Facility, Machine
from osqpipe.pipeline.smtp import send_email
from .fetch_fastq import FQFileFetcher
from osqutil.setup_logs import configure_logging
from logging import INFO, DEBUG
LOGGER = configure_logging('flowcell')
###############################################################################
def demux_code(code):
'''Split a comma-separated list of library codes into a list.'''
return [x.strip() for x in code.split(",")]
###############################################################################
class FlowCellProcess(object):
'''Main class used for processing flowcells.'''
####################################################################################
# ControlledVocab management. Primarily concerned with handling
# phonetic ("fuzzy") searches. We only support fuzzy searching on
# filter, not get (since a fuzzy search may return multiple hits
# anyway).
from django.db import models
from django.db.models import Max
import re
import os
from osqutil.utilities import get_filename_libcode
from osqutil.setup_logs import configure_logging
LOGGER = configure_logging('models')
from osqutil.config import Config
CONFIG = Config()
class ControlledVocabManager(models.Manager):
# This will become a dict of dicts. N.B. deactivated as the caching mechanism currently creates more problems than it solves.
# _fuzzyCache = {}
_fuzzy_re = re.compile('(.*)__fuzzy$')
def filter(self, **kwargs):
kwargs = self._map_controlled_field(kwargs)
(fuzzy_args,
'''Code to test for new, previously unseen FlowCell IDs in the
SolexaLIMS back-end MySQL database. Original version shamelessly
stolen from Gord Brown's runNotifier script.'''
from osqutil.utilities import munge_cruk_emails
from .upstream_lims import Lims, get_lims_run_history
from osqutil.config import Config
from ..models import Lane, Library, Status, Facility, User
################################################################################
from osqutil.setup_logs import configure_logging
from logging import INFO, DEBUG
LOGGER = configure_logging('lims_watcher')
################################################################################
class LimsWatcher(object):
'''Class used to poll the Genologics LIMS REST API and retrieve a
list of Run IDs ready for downstream processing. The associated
lanes are created in the repository (assuming that the libraries are
available), and returned to the caller. Note that typically the
caller will want to re-query to retrieve all ready lanes, not just
those found in the last sweep.'''
__slots__ = ('conf', 'missing_libraries', 'user_emails', 'lims')
def __init__(self, lims=None, debug=False):
import os
import re
from tempfile import NamedTemporaryFile
from shutil import move
from django.db import transaction
from ..models import Program, AlignmentQC, AlnQCfile, Filetype, Alnfile, DataProvenance
from .laneqc import QCReport
from osqutil.progsum import ProgramSummary
from osqutil.utilities import checksum_file, call_subprocess, rezip_file, set_file_permissions
from osqutil.config import Config
from osqutil.setup_logs import configure_logging
CONFIG = Config()
LOGGER = configure_logging('alignmentqc')
class AlignmentQCReport(QCReport):
'''
Abstract class handling all alignment-based QC Reports.
'''
data_process = AlignmentQC
target_name = 'alignment'
data_file = AlnQCfile
file_target_name = 'alignmentqc'
class AlignmentCrossCorrReport(AlignmentQCReport):
'''
Concrete AlignmentQCReport subclass implementing cross-correlation
analysis plots. See the superclass for usage notes.
'''
__version__ = "0.1" __credits__ = "Exploits cs_* libraries implemented by Gordon Brown." ## Dependencies: # # - Password free login to target scp server # - scp # - sed # - /home/fnc-odompipe/software/external/bin/wkhtmltopdf-amd64 import sys import getopt from osqutil.setup_logs import configure_logging from logging import INFO LOGGER = configure_logging(level=INFO) # New in Django 1.7 and above. import django django.setup() from osqpipe.pipeline.fetch_mga import fetch_mga TEST_MODE = False def usage(fname): """Prints usage """ print "" print "Program: %s (fetches MGA reports from Solexa LIMS)" % (fname,) print "Version: %s" % __version__ print "Usage: %s [-t/--test] <flowcell> <lane> <dest> [filename prefix] " % (fname,)
# along with the osqpipe python package. If not, see
# <http://www.gnu.org/licenses/>.
'''
Code tools used to manipulate bam files from within python. This is
intended to be a pure-python implementation for improved
maintainability.
'''
import os
import re
import pysam
from contextlib import contextmanager
from logging import INFO
from osqutil.setup_logs import configure_logging
LOGGER = configure_logging('bampy', level=INFO)
class Bamfile(pysam.AlignmentFile):
'''
Subclass of pysam.AlignmentFile with a few convenience methods of our own.
'''
# Note that while it might be nice to have a Bamfile class which
# correctly auto-generates its own index, this is not going to be
# easily maintainable due to the implementation of
# pysam.AlignmentFile. Rather than coding ourselves into knots, we have
# opted for a context manager approach (see open_bamfile).
def read_refname(self, read):
'''
