def list_projects(self):
if not self._check_pargs(["flowcell"]):
return
url = self.pargs.url if self.pargs.url else self.app.config.get("db", "url")
if not url:
self.app.log.warn("Please provide a valid url: got {}".format(url))
return
if not validate_fc_directory_format(self.pargs.flowcell):
self.app.log.warn(
"Path '{}' does not conform to bcbio flowcell directory format; aborting".format(self.pargs.flowcell)
)
return
out_data = [[self.pargs.flowcell]]
s = self.pargs.flowcell.split("_")
fcid = "_".join([s[0], s[-1]])
self.log.debug("Establishing FlowcellRunMetricsConnection")
fc_con = FlowcellRunMetricsConnection(dbname=self.app.config.get("db", "flowcells"), **vars(self.app.pargs))
self.log.debug("Establishing ProjectSummaryConnection")
p_con = ProjectSummaryConnection(dbname=self.app.config.get("db", "projects"), **vars(self.app.pargs))
self.log.debug("Fetching flowcell metric document for flowcell {}".format(fcid))
fc = fc_con.get_entry(fcid)
if fc is None:
self.log.warn("No flowcell metric document for flowcell {}".format(fcid))
return
self.log.debug("Fetching csv samplesheet data for flowcell {}".format(fcid))
ssheet_data = self._get_samplesheet_sample_data(fc)
if len(ssheet_data) == 0:
self.log.warn("No csv samplesheet data for flowcell {}".format(fcid))
return
self.log.debug("Fetch runParameter data for flowcell {}".format(fcid))
run_data = self._get_run_parameter_data(fc)
if len(run_data) == 0:
self.log.warn("No runParameter data for flowcell {}".format(fcid))
out_data = [
[self.pargs.flowcell, run_data.get("InstrumentType", "HiSeq2000"), run_data.get("RunMode", "High Output")]
]
# Extract the project names
projects = set([proj[0].replace("__", ".") for data in ssheet_data.values() for proj in data.values()])
# Extract application for each project
for project in projects:
self.log.debug("Fetching project data document for project {}".format(project))
pdoc = p_con.get_entry(project)
if pdoc is None:
self.log.warn("No project data document for project {}".format(project))
pdoc = {}
application = pdoc.get("application", "N/A")
out_data.append([project, application])
self.app._output_data["stdout"].write("\n".join(["\t".join([str(r) for r in row]) for row in out_data]))
def list_projects(self):
if not self._check_pargs(["flowcell"]):
return
url = self.pargs.url if self.pargs.url else self.app.config.get("db", "url")
if not url:
self.app.log.warn("Please provide a valid url: got {}".format(url))
return
if not validate_fc_directory_format(self.pargs.flowcell):
self.app.log.warn("Path '{}' does not conform to bcbio flowcell directory format; aborting".format(self.pargs.flowcell))
return
out_data = [[self.pargs.flowcell]]
s = self.pargs.flowcell.split("_")
fcid = "_".join([s[0],s[-1]])
self.log.debug("Establishing FlowcellRunMetricsConnection")
fc_con = FlowcellRunMetricsConnection(dbname=self.app.config.get("db", "flowcells"), **vars(self.app.pargs))
self.log.debug("Establishing ProjectSummaryConnection")
p_con = ProjectSummaryConnection(dbname=self.app.config.get("db", "projects"), **vars(self.app.pargs))
self.log.debug("Fetching flowcell metric document for flowcell {}".format(fcid))
fc = fc_con.get_entry(fcid)
if fc is None:
self.log.warn("No flowcell metric document for flowcell {}".format(fcid))
return
self.log.debug("Fetching csv samplesheet data for flowcell {}".format(fcid))
ssheet_data = self._get_samplesheet_sample_data(fc)
if len(ssheet_data) == 0:
self.log.warn("No csv samplesheet data for flowcell {}".format(fcid))
return
self.log.debug("Fetch runParameter data for flowcell {}".format(fcid))
run_data = self._get_run_parameter_data(fc)
if len(run_data) == 0:
self.log.warn("No runParameter data for flowcell {}".format(fcid))
out_data = [[self.pargs.flowcell,
run_data.get("InstrumentType","HiSeq2000"),
run_data.get("RunMode","High Output")]]
# Extract the project names
projects = set([proj[0].replace("__",".") for data in ssheet_data.values() for proj in data.values()])
# Extract application for each project
for project in projects:
self.log.debug("Fetching project data document for project {}".format(project))
pdoc = p_con.get_entry(project)
if pdoc is None:
self.log.warn("No project data document for project {}".format(project))
pdoc = {}
application = pdoc.get("application","N/A")
type = pdoc.get("type","Check GPL")
out_data.append([project,application,type])
self.app._output_data['stdout'].write("\n".join(["\t".join([str(r) for r in row]) for row in out_data]))
def upload_qc(self):
if not self._check_pargs(['flowcell']):
return
url = self.pargs.url if self.pargs.url else self.app.config.get(
"db", "url")
if not url:
self.app.log.warn("Please provide a valid url: got {}".format(url))
return
if not validate_fc_directory_format(self.pargs.flowcell):
self.app.log.warn(
"Path '{}' does not conform to bcbio flowcell directory format; aborting"
.format(self.pargs.flowcell))
return
runinfo_csv = os.path.join(os.path.abspath(self.pargs.flowcell),
"{}.csv".format(fc_id(self.pargs.flowcell)))
runinfo_yaml = os.path.join(os.path.abspath(self.pargs.flowcell),
"run_info.yaml")
(fc_date, fc_name) = fc_parts(self.pargs.flowcell)
if int(fc_date) < 120815:
self.log.info(
"Assuming pre-casava based file structure for {}".format(
fc_id(self.pargs.flowcell)))
qc_objects = self._collect_pre_casava_qc()
else:
self.log.info("Assuming casava based file structure for {}".format(
fc_id(self.pargs.flowcell)))
qc_objects = self._collect_casava_qc()
if len(qc_objects) == 0:
self.log.info("No out-of-date qc objects for {}".format(
fc_id(self.pargs.flowcell)))
return
else:
self.log.info("Retrieved {} updated qc objects".format(
len(qc_objects)))
s_con = SampleRunMetricsConnection(dbname=self.app.config.get(
"db", "samples"),
**vars(self.app.pargs))
fc_con = FlowcellRunMetricsConnection(dbname=self.app.config.get(
"db", "flowcells"),
**vars(self.app.pargs))
p_con = ProjectSummaryConnection(dbname=self.app.config.get(
"db", "projects"),
**vars(self.app.pargs))
for obj in qc_objects:
if self.app.pargs.debug:
self.log.debug("{}: {}".format(str(obj), obj["_id"]))
if isinstance(obj, FlowcellRunMetricsDocument):
dry("Saving object {}".format(repr(obj)), fc_con.save(obj))
if isinstance(obj, SampleRunMetricsDocument):
project_sample = p_con.get_project_sample(
obj.get("sample_prj", None), obj.get("barcode_name", None),
self.pargs.extensive_matching)
if project_sample:
obj["project_sample_name"] = project_sample['sample_name']
dry("Saving object {}".format(repr(obj)), s_con.save(obj))
def upload_qc(self):
if not self._check_pargs(["flowcell"]):
return
url = self.pargs.url if self.pargs.url else self.app.config.get("db", "url")
if not url:
self.app.log.warn("Please provide a valid url: got {}".format(url))
return
if not validate_fc_directory_format(self.pargs.flowcell):
self.app.log.warn(
"Path '{}' does not conform to bcbio flowcell directory format; aborting".format(self.pargs.flowcell)
)
return
runinfo_csv = os.path.join(os.path.abspath(self.pargs.flowcell), "{}.csv".format(fc_id(self.pargs.flowcell)))
runinfo_yaml = os.path.join(os.path.abspath(self.pargs.flowcell), "run_info.yaml")
(fc_date, fc_name) = fc_parts(self.pargs.flowcell)
if int(fc_date) < 120815:
self.log.info("Assuming pre-casava based file structure for {}".format(fc_id(self.pargs.flowcell)))
qc_objects = self._collect_pre_casava_qc()
else:
self.log.info("Assuming casava based file structure for {}".format(fc_id(self.pargs.flowcell)))
qc_objects = self._collect_casava_qc()
if len(qc_objects) == 0:
self.log.info("No out-of-date qc objects for {}".format(fc_id(self.pargs.flowcell)))
return
else:
self.log.info("Retrieved {} updated qc objects".format(len(qc_objects)))
s_con = SampleRunMetricsConnection(dbname=self.app.config.get("db", "samples"), **vars(self.app.pargs))
fc_con = FlowcellRunMetricsConnection(dbname=self.app.config.get("db", "flowcells"), **vars(self.app.pargs))
p_con = ProjectSummaryConnection(dbname=self.app.config.get("db", "projects"), **vars(self.app.pargs))
for obj in qc_objects:
if self.app.pargs.debug:
self.log.debug("{}: {}".format(str(obj), obj["_id"]))
if isinstance(obj, FlowcellRunMetricsDocument):
dry("Saving object {}".format(repr(obj)), fc_con.save(obj))
if isinstance(obj, SampleRunMetricsDocument):
project_sample = p_con.get_project_sample(
obj.get("sample_prj", None), obj.get("barcode_name", None), self.pargs.extensive_matching
)
if project_sample:
obj["project_sample_name"] = project_sample["sample_name"]
dry("Saving object {}".format(repr(obj)), s_con.save(obj))
