def search_for_new(config, amqp_config, process_msg, store_msg, qseq, fastq):
"""Search for any new directories that have not been reported.
"""
reported = _read_reported(config["msg_db"])
for dname in _get_directories(config):
if os.path.isdir(dname) and dname not in reported:
if _is_finished_dumping(dname):
log.info(
"The instrument has finished dumping on directory %s" %
dname)
_update_reported(config["msg_db"], dname)
ss_file = samplesheet.run_has_samplesheet(dname, config)
if ss_file:
out_file = os.path.join(dname, "run_info.yaml")
log.info("CSV Samplesheet %s found, converting to %s" %
(ss_file, out_file))
samplesheet.csv2yaml(ss_file, out_file)
if qseq:
log.info("Generating qseq files for %s" % dname)
_generate_qseq(get_qseq_dir(dname), config)
if fastq:
log.info("Generating fastq files for %s" % dname)
_generate_fastq(dname, config)
store_files, process_files = _files_to_copy(dname)
if process_msg:
finished_message(config["msg_process_tag"], dname,
process_files, amqp_config)
if store_msg:
finished_message(config["msg_store_tag"], dname,
store_files, amqp_config)
def search_for_new(config, amqp_config, process_msg, store_msg, qseq, fastq):
"""Search for any new directories that have not been reported.
"""
reported = _read_reported(config["msg_db"])
for dname in _get_directories(config):
if os.path.isdir(dname) and dname not in reported:
if _is_finished_dumping(dname):
log.info("The instrument has finished dumping on directory %s" % dname)
_update_reported(config["msg_db"], dname)
ss_file = samplesheet.run_has_samplesheet(dname, config)
if ss_file:
out_file = os.path.join(dname, "run_info.yaml")
log.info("CSV Samplesheet %s found, converting to %s" %
(ss_file, out_file))
samplesheet.csv2yaml(ss_file, out_file)
if qseq:
log.info("Generating qseq files for %s" % dname)
_generate_qseq(get_qseq_dir(dname), config)
if fastq:
log.info("Generating fastq files for %s" % dname)
_generate_fastq(dname, config)
store_files, process_files = _files_to_copy(dname)
if process_msg:
finished_message(config["msg_process_tag"], dname,
process_files, amqp_config)
if store_msg:
finished_message(config["msg_store_tag"], dname,
store_files, amqp_config)
def _process_samplesheets(dname, config):
"""Process Illumina samplesheets into YAML files for post-processing.
"""
ss_file = samplesheet.run_has_samplesheet(dname, config)
if ss_file:
out_file = os.path.join(dname, "run_info.yaml")
log.info("CSV Samplesheet %s found, converting to %s" % (ss_file, out_file))
samplesheet.csv2yaml(ss_file, out_file)
def _process_samplesheets(dname, config):
"""Process Illumina samplesheets into YAML files for post-processing.
"""
ss_file = samplesheet.run_has_samplesheet(dname, config)
if ss_file:
out_file = os.path.join(dname, "run_info.yaml")
logger2.info("CSV Samplesheet %s found, converting to %s" %
(ss_file, out_file))
samplesheet.csv2yaml(ss_file, out_file)
def toyaml(self, ssheet):
self.out_file = samplesheet.csv2yaml(ssheet)
assert os.path.exists(self.out_file)
with open(self.out_file) as in_handle:
info = yaml.load(in_handle)
in_handle.close()
return info
def toyaml(self, ssheet):
self.out_file = samplesheet.csv2yaml(ssheet)
assert os.path.exists(self.out_file)
with open(self.out_file) as in_handle:
info = yaml.load(in_handle)
in_handle.close()
return info
def test_toyaml(self):
"""Convert CSV Illumina SampleSheet to YAML.
"""
out_file = samplesheet.csv2yaml(self.ss_file)
assert os.path.exists(out_file)
with open(out_file) as in_handle:
info = yaml.load(in_handle)
assert info[0]['lane'] == '1'
assert info[0]['multiplex'][0]['barcode_id'] == 5
os.remove(out_file)
def test_toyaml(self):
"""Convert CSV Illumina SampleSheet to YAML.
"""
out_file = samplesheet.csv2yaml(self.ss_file)
assert os.path.exists(out_file)
with open(out_file) as in_handle:
info = yaml.load(in_handle)
assert info[0]['lane'] == '1'
assert info[0]['multiplex'][0]['barcode_id'] == 5
os.remove(out_file)
#!/usr/bin/env python
"""Convert Illumina SampleSheet CSV files to the run_info.yaml input file.
This allows running the analysis pipeline without Galaxy, using CSV input
files from Illumina SampleSheet or Genesifter.
Usage:
convert_samplesheet_config.py <input csv>
"""
import sys
from bcbio.solexa import samplesheet
if __name__ == "__main__":
samplesheet.csv2yaml(sys.argv[1])
def main(run_id, config_file, run_info_file=None, dryrun=False):
assert run_id, \
"No run id was specified"
assert os.path.exists(config_file), \
"The configuration file, {}, could not be found".format(config_file)
config = load_config(config_file)
assert "gdocs_upload" in config, \
"The configuration file, {}, has no section specifying the Google docs details".format(config_file)
analysis_cfg = config.get("analysis", {})
if "store_dir" in analysis_cfg:
archive_dir = os.path.join(analysis_cfg["store_dir"], run_id)
else:
archive_dir = os.getcwd()
analysis_dir = None
if "base_dir" in analysis_cfg:
analysis_dir = os.path.join(analysis_cfg["base_dir"], run_id)
if analysis_dir is None or not os.path.exists(analysis_dir):
analysis_dir = tempfile.mkdtemp()
dirs = {
"work": os.path.normpath(analysis_dir),
"flowcell": os.path.normpath(archive_dir)
}
assert os.path.exists(dirs["flowcell"]), \
"The flowcell directory, {}, could not be found".format(dirs["flowcell"])
assert os.path.exists(dirs["work"]), \
"The work directory, {}, could not be found".format(dirs["work"])
if run_info_file is None:
run_info_file = os.path.join(dirs["flowcell"], "run_info.yaml")
if not os.path.exists(run_info_file):
# Locate the samplesheet and convert to yaml
samplesheet = _find_samplesheet(dirs["flowcell"])
assert samplesheet, \
"Could not locate samplesheet in {}, aborting..".format(dirs["flowcell"])
fh, run_info_file = tempfile.mkstemp()
os.close(fh)
run_info_file = ssheet.csv2yaml(samplesheet, run_info_file)
assert os.path.exists(run_info_file), \
"The run info configuration file, {}, could not be found".format(run_info_file)
fc_name, fc_date = fc.get_flowcell_info(dirs["flowcell"])
# If we have no bc_metrics files in the workdir, we may be looking at a Casava run.
# In that case, attempt to parse the Demultiplex_Stats.htm file and create bc_metrics files
metric_files = glob.glob(
os.path.join(dirs["work"], "*_barcode", "*bc[_.]metrics")) + glob.glob(
os.path.join(dirs["work"], "*bc[_.]metrics"))
if len(metric_files) == 0:
casava_report = _find_casava_report(dirs["flowcell"])
assert len(casava_report) > 0, \
"Could not locate CASAVA demultiplex report in {}, aborting..".format(dirs["flowcell"])
metric_files = _casava_report_to_metrics(run_info_file, casava_report,
dirs)
assert len(metric_files) > 0, \
"Could not locate or create required metric files, aborting.."
print(
"A report will be created on Google Docs based on the demultiplexed data in {}"
.format(dirs["work"]))
print("The configuration file is {0} and the run info file is {1}".format(
config_file, run_info_file))
print("The run was started on {0} and has flowcell id {1}".format(
fc_date, fc_name))
if not dryrun:
create_report_on_gdocs(fc_date, fc_name, run_info_file, dirs, config)
else:
print("DRY-RUN: nothing uploaded")
def main(run_id, config_file, run_info_file=None, dryrun=False):
assert run_id, \
"No run id was specified"
assert os.path.exists(config_file), \
"The configuration file, {}, could not be found".format(config_file)
config = load_config(config_file)
assert "gdocs_upload" in config, \
"The configuration file, {}, has no section specifying the Google docs details".format(config_file)
analysis_cfg = config.get("analysis",{})
if "store_dir" in analysis_cfg:
archive_dir = os.path.join(analysis_cfg["store_dir"], run_id)
else:
archive_dir = os.getcwd()
analysis_dir = None
if "base_dir" in analysis_cfg:
analysis_dir = os.path.join(analysis_cfg["base_dir"], run_id)
if analysis_dir is None or not os.path.exists(analysis_dir):
analysis_dir = tempfile.mkdtemp()
dirs = {"work": os.path.normpath(analysis_dir),
"flowcell": os.path.normpath(archive_dir)}
assert os.path.exists(dirs["flowcell"]), \
"The flowcell directory, {}, could not be found".format(dirs["flowcell"])
assert os.path.exists(dirs["work"]), \
"The work directory, {}, could not be found".format(dirs["work"])
if run_info_file is None:
run_info_file = os.path.join(dirs["flowcell"], "run_info.yaml")
if not os.path.exists(run_info_file):
# Locate the samplesheet and convert to yaml
samplesheet = _find_samplesheet(dirs["flowcell"])
assert samplesheet, \
"Could not locate samplesheet in {}, aborting..".format(dirs["flowcell"])
fh, run_info_file = tempfile.mkstemp()
os.close(fh)
run_info_file = ssheet.csv2yaml(samplesheet,run_info_file)
assert os.path.exists(run_info_file), \
"The run info configuration file, {}, could not be found".format(run_info_file)
fc_name, fc_date = fc.get_flowcell_info(dirs["flowcell"])
# If we have no bc_metrics files in the workdir, we may be looking at a Casava run.
# In that case, attempt to parse the Demultiplex_Stats.htm file and create bc_metrics files
metric_files = glob.glob(os.path.join(dirs["work"], "*_barcode", "*bc[_.]metrics")) + glob.glob(os.path.join(dirs["work"], "*bc[_.]metrics"))
if len(metric_files) == 0:
casava_report = _find_casava_report(dirs["flowcell"])
assert len(casava_report) > 0, \
"Could not locate CASAVA demultiplex report in {}, aborting..".format(dirs["flowcell"])
metric_files = _casava_report_to_metrics(run_info_file, casava_report, dirs)
assert len(metric_files) > 0, \
"Could not locate or create required metric files, aborting.."
print("A report will be created on Google Docs based on the demultiplexed data in {}".format(dirs["work"]))
print("The configuration file is {0} and the run info file is {1}".format(config_file, run_info_file))
print("The run was started on {0} and has flowcell id {1}".format(fc_date, fc_name))
if not dryrun:
create_report_on_gdocs(fc_date, fc_name, run_info_file, dirs, config)
else:
print("DRY-RUN: nothing uploaded")
