def get_analysis_projects(self, pattern=None):
"""
Return the analysis projects in a list
By default returns all projects within the analysis
directory which are listed in the 'projects.info'
metadata file (and 'undetermined', which is not).
If the 'pattern' is not None then it should be a simple
pattern used to match against available names to select
a subset of projects (see bcf_utils.name_matches).
If any project in 'projects.info' doesn't have an
associated analysis directory then it will be omitted
from the results.
Arguments:
pattern (str): optional pattern to select a subset
of projects (default: select all projects)
Returns:
List: list of AnalysisProject instances.
"""
project_metadata = self.load_project_metadata(
self.params.project_metadata)
projects = []
if pattern is None:
pattern = '*'
# Get matching projects from metadata file
for line in project_metadata:
name = line['Project']
if name.startswith('#'):
# Ignore commented project
continue
if not bcf_utils.name_matches(name, pattern):
# Name failed to match, ignore
continue
# Look for a matching project directory
project_dir = os.path.join(self.analysis_dir, name)
if os.path.exists(project_dir):
projects.append(AnalysisProject(project_dir))
else:
logging.warning("Matching project '%s': no associated "
"directory" % name)
# Deal with undetermined
if bcf_utils.name_matches('undetermined', pattern):
undetermined_analysis = self.undetermined()
if undetermined_analysis is not None and \
'undetermined' not in [p.name for p in projects]:
projects.append(undetermined_analysis)
return projects
def get_projects(seq_data,pattern=None):
"""Get list of projects
Returns a list of IlluminaProject objects from the supplied
IlluminaData object.
"""
projects = []
for p in seq_data.projects:
if bcf_utils.name_matches(p.name,pattern):
projects.append(p)
return projects
def get_samples(seq_data,project_pattern=None,sample_pattern=None):
"""Get list of samples
Returns a list of IlluminaSample objects from the supplied
IlluminaData object.
"""
samples = []
for p in get_projects(seq_data,pattern=project_pattern):
for s in p.samples:
if bcf_utils.name_matches(s.name,sample_pattern):
samples.append(s)
return samples
def get_samples(self, pattern):
"""Return list of sample matching pattern
Arguments:
pattern: simple 'glob' style pattern
Returns:
Python list of samples with names matching the supplied
pattern (or an empty list if no names match).
"""
samples = []
for sample in self.samples:
if bcf_utils.name_matches(sample.name, pattern):
samples.append(sample)
return samples
def get_analysis_projects_from_dirs(self, pattern=None, strict=False):
"""
Return a list of AnalysisProjects in the analysis directory
Tests each of the subdirectories in the top-level of the
analysis directory and rejects any that appear to be
CASVAVA/bcl2fastq outputs or which don't successfully load
as AnalysisProject instances.
Unlike the `get_analysis_projects` method, no checking
against the project metadata (typically in 'projects.info')
is performed.
If the 'pattern' is not None then it should be a simple
pattern used to match against available names to select
a subset of projects (see bcf_utils.name_matches).
Arguments:
pattern (str): optional pattern to select a subset
of projects (default: select all projects)
strict (bool): if True then apply strict checks on
each discovered project directory before adding it
to the list (default: don't apply strict checks)
Returns:
List: list of AnalysisProject instances.
"""
logging.debug("Testing subdirectories to determine analysis projects")
projects = []
if pattern is None:
pattern = '*'
# Try loading each subdirectory as a project
for dirn in bcf_utils.list_dirs(self.analysis_dir):
# Test for bcl2fastq output
try:
IlluminaData.IlluminaData(self.analysis_dir,
unaligned_dir=dirn)
logging.debug("* %s: rejected" % dirn)
continue
except IlluminaData.IlluminaDataError:
pass
except Exception as ex:
logging.debug("Exception when attempting to load "
"subdir '%s' as CASAVA/bcl2fastq output "
"(ignored): %s" % (dirn, ex))
# Try loading as a project
test_project = AnalysisProject(
dirn, os.path.join(self.analysis_dir, dirn))
if strict:
# Apply strict checks
if not test_project.is_analysis_dir:
logging.debug("* %s: rejected (failed strict checks)" %
dirn)
continue
else:
# Basic check: are there any samples?
if not len(test_project.samples):
logging.debug("* %s: rejected (no samples)" % dirn)
continue
# Passed checks
logging.debug("* %s: analysis directory" % dirn)
if bcf_utils.name_matches(test_project.name, pattern):
projects.append(test_project)
return projects
print "%s\t%s\t%d" % (fastq, bcf_utils.format_file_size(fsize),
nreads)
# Copy fastq.gz files to the current directory
if options.copy_pattern is not None:
# Extract project and sample names/patterns
try:
project_pattern, sample_pattern = options.copy_pattern.split("/")
print "Copy: look for samples matching pattern %s" % options.copy_pattern
print "Data files will be copied to %s" % os.getcwd()
except ValueError:
logging.error("ERROR invalid pattern '%s'" % options.copy_pattern)
sys.exit(1)
# Loop through projects and samples looking for matches
for project in illumina_data.projects:
if bcf_utils.name_matches(project.name, project_pattern):
# Loop through samples
for sample in project.samples:
if bcf_utils.name_matches(sample.name, sample_pattern):
for fastq in sample.fastq:
fastq_file = os.path.join(sample.dirn, fastq)
print "\tCopying .../%s" % os.path.basename(
fastq_file)
dst = os.path.abspath(os.path.basename(fastq_file))
if os.path.exists(dst):
logging.error(
"File %s already exists! Skipped" % dst)
else:
shutil.copy(fastq_file, dst)
# Verify against sample sheet
bcf_utils.format_file_size(fsize),
nreads)
# Copy fastq.gz files to the current directory
if options.copy_pattern is not None:
# Extract project and sample names/patterns
try:
project_pattern,sample_pattern = options.copy_pattern.split("/")
print "Copy: look for samples matching pattern %s" % options.copy_pattern
print "Data files will be copied to %s" % os.getcwd()
except ValueError:
logging.error("ERROR invalid pattern '%s'" % options.copy_pattern)
sys.exit(1)
# Loop through projects and samples looking for matches
for project in illumina_data.projects:
if bcf_utils.name_matches(project.name,project_pattern):
# Loop through samples
for sample in project.samples:
if bcf_utils.name_matches(sample.name,sample_pattern):
for fastq in sample.fastq:
fastq_file = os.path.join(sample.dirn,fastq)
print "\tCopying .../%s" % os.path.basename(fastq_file)
dst = os.path.abspath(os.path.basename(fastq_file))
if os.path.exists(dst):
logging.error("File %s already exists! Skipped" % dst)
else:
shutil.copy(fastq_file,dst)
# Verify against sample sheet
if options.sample_sheet is not None:
if IlluminaData.verify_run_against_sample_sheet(illumina_data,options.sample_sheet):
