def _run_toplevel(config, config_file, work_dir, parallel,
fc_dir=None, run_info_yaml=None):
"""
Run toplevel analysis, processing a set of input files.
config_file -- Main YAML configuration file with system parameters
fc_dir -- Directory of fastq files to process
run_info_yaml -- YAML configuration file specifying inputs to process
"""
parallel = log.create_base_logger(config, parallel)
log.setup_local_logging(config, parallel)
fastq_dir, galaxy_dir, config_dir = _get_full_paths(get_fastq_dir(fc_dir)
if fc_dir else None,
config, config_file)
config_file = os.path.join(config_dir, os.path.basename(config_file))
dirs = {"fastq": fastq_dir, "galaxy": galaxy_dir,
"work": work_dir, "flowcell": fc_dir, "config": config_dir}
samples = run_info.organize(dirs, config, run_info_yaml)
pipelines = _pair_lanes_with_pipelines(samples)
final = []
with utils.curdir_tmpdir() as tmpdir:
tempfile.tempdir = tmpdir
for pipeline, pipeline_items in pipelines.items():
pipeline_items = _add_provenance(pipeline_items, dirs, parallel, config)
versioncheck.testall(pipeline_items)
for xs in pipeline.run(config, config_file, parallel, dirs, pipeline_items):
if len(xs) == 1:
upload.from_sample(xs[0])
final.append(xs[0])
def _run_toplevel(config,
config_file,
work_dir,
parallel,
fc_dir=None,
run_info_yaml=None):
"""
Run toplevel analysis, processing a set of input files.
config_file -- Main YAML configuration file with system parameters
fc_dir -- Directory of fastq files to process
run_info_yaml -- YAML configuration file specifying inputs to process
"""
parallel = log.create_base_logger(config, parallel)
log.setup_local_logging(config, parallel)
dirs = setup_directories(work_dir, fc_dir, config, config_file)
config_file = os.path.join(dirs["config"], os.path.basename(config_file))
samples = run_info.organize(dirs, config, run_info_yaml)
pipelines = _pair_samples_with_pipelines(samples)
final = []
with tx_tmpdir(config) as tmpdir:
tempfile.tempdir = tmpdir
for pipeline, pipeline_items in pipelines.items():
pipeline_items = _add_provenance(pipeline_items, dirs, parallel,
config)
versioncheck.testall(pipeline_items)
for xs in pipeline.run(config, config_file, parallel, dirs,
pipeline_items):
if len(xs) == 1:
upload.from_sample(xs[0])
final.append(xs[0])
def _run_toplevel(config, config_file, work_dir, parallel,
fc_dir=None, run_info_yaml=None):
"""
Run toplevel analysis, processing a set of input files.
config_file -- Main YAML configuration file with system parameters
fc_dir -- Directory of fastq files to process
run_info_yaml -- YAML configuration file specifying inputs to process
"""
parallel = log.create_base_logger(config, parallel)
log.setup_local_logging(config, parallel)
fastq_dir, galaxy_dir, config_dir = _get_full_paths(get_fastq_dir(fc_dir)
if fc_dir else None,
config, config_file)
config_file = os.path.join(config_dir, os.path.basename(config_file))
dirs = {"fastq": fastq_dir, "galaxy": galaxy_dir,
"work": work_dir, "flowcell": fc_dir, "config": config_dir}
run_items = run_info.organize(dirs, config, run_info_yaml)
run_parallel = parallel_runner(parallel, dirs, config, config_file)
# process each flowcell lane
lane_items = lane.process_all_lanes(run_items, run_parallel)
pipelines = _pair_lanes_with_pipelines(lane_items)
final = []
with utils.curdir_tmpdir() as tmpdir:
tempfile.tempdir = tmpdir
for pipeline, pipeline_items in pipelines.items():
pipeline_items = _add_provenance(pipeline_items, dirs, run_parallel, parallel, config)
versioncheck.testall(pipeline_items)
for xs in pipeline.run(config, config_file, run_parallel, parallel, dirs, pipeline_items):
if len(xs) == 1:
upload.from_sample(xs[0])
final.append(xs[0])
def _run_toplevel(config, config_file, work_dir, parallel,
fc_dir=None, run_info_yaml=None, samples=None):
"""
Run toplevel analysis, processing a set of input files.
config_file -- Main YAML configuration file with system parameters
fc_dir -- Directory of fastq files to process
run_info_yaml -- YAML configuration file specifying inputs to process
samples -- Pre-processed samples, useful if run inside of docker containers.
"""
parallel = log.create_base_logger(config, parallel)
log.setup_local_logging(config, parallel)
dirs = run_info.setup_directories(work_dir, fc_dir, config, config_file)
config_file = os.path.join(dirs["config"], os.path.basename(config_file))
if samples:
dockerized = True
else:
dockerized = False
samples = run_info.organize(dirs, config, run_info_yaml)
pipelines = _pair_samples_with_pipelines(samples)
final = []
with tx_tmpdir(config) as tmpdir:
tempfile.tempdir = tmpdir
for pipeline, pipeline_items in pipelines.items():
pipeline_items = _add_provenance(pipeline_items, dirs, parallel, config)
if not dockerized:
versioncheck.testall(pipeline_items)
for xs in pipeline.run(config, config_file, parallel, dirs, pipeline_items):
if len(xs) == 1:
upload.from_sample(xs[0])
final.append(xs[0])
def _add_provenance(items, dirs, config):
p = programs.write_versions(dirs, config)
versioncheck.testall(items)
p_db = diagnostics.initialize(dirs)
out = []
for item in items:
entity_id = diagnostics.store_entity(item)
item["config"]["resources"]["program_versions"] = p
item["provenance"] = {"programs": p, "entity": entity_id, "db": p_db}
out.append([item])
return out
def _add_provenance(items, dirs, config):
p = programs.write_versions(dirs, config=config)
versioncheck.testall(items)
p_db = diagnostics.initialize(dirs)
out = []
for item in items:
entity_id = diagnostics.store_entity(item)
item["config"]["resources"]["program_versions"] = p
item["provenance"] = {"programs": p, "entity": entity_id,
"db": p_db}
out.append([item])
return out