def execute(conn, process_id, selection_id, prop):
pipeline_name = default_attributes.get_attribute_value(
conn, 'pipeline_name', process_id)
sequencing_platform = default_attributes.get_attribute_value(
conn, 'instrument_platform', process_id)
#jobids=None
#pipeline_content=None
print(pipeline_name, process_id)
if pipeline_name.upper() == 'DTU_CGE':
jobids, pipeline_content = execute_dtu_cge(process_id, selection_id,
prop)
elif pipeline_name.upper() == 'EMC_SLIM':
jobids, pipeline_content = execute_emc_slim(process_id, selection_id,
prop)
elif pipeline_name.upper() == 'UANTWERP_BACPIPE':
jobids, pipeline_content = execute_uantwerp_bacpipe(
process_id, selection_id, prop)
elif pipeline_name.upper() == 'RIVM_JOVIAN':
jobids, pipeline_content = execute_rivm_jovian(process_id,
selection_id, prop)
print('*' * 100)
print("Pipeline name is:{}".format(pipeline_name.upper()))
print('*' * 100)
return jobids, pipeline_content
def execute_uantwerp_bacpipe (process_id, selection_id, prop):
workdir = prop.workdir + process_id + "/"
sample_accession = default_attributes.get_attribute_value(conn, 'sample_accession', process_id)
pair = default_attributes.get_attribute_value(conn, 'pair', process_id)
print("Test:" + workdir)
pair = default_attributes.get_attribute_value(conn, 'pair', process_id)
library_layout = 'paired' if pair =='True' else 'single'
config = UAntwerpBacpipe.config
config['directories']['reads'] = workdir
config['directories']['output'] = workdir
config['trim_galore']['reads_type'] = library_layout
config['spades']['Mode'] = library_layout
bacpipe_config = workdir + process_id + '.yaml'
try:
with open(bacpipe_config, 'w') as config_file:
yaml.safe_dump(config, config_file, default_style=None, default_flow_style=False)
except yaml.YAMLError as exc:
print(exc)
print('*'*100)
print("Bacpipe Config file:\n{}".format(bacpipe_config))
print(prop.uantwerp_bacpipe_program)
print(prop.nproc)
print(prop.prokka_program)
print('*'*100)
bacpipe = UAntwerpBacpipe(workdir, bacpipe_config, prop, sample_accession,pair)
jobids = bacpipe.execute()
return jobids, bacpipe
def get_datahub_names(conn, process_id):
"""
Extract the datahub name from SELECTADB_PRODUCTION
:param conn: PostGreSQL connection
:param process_id: process_id
:return: datahub names
"""
value = default_attributes.get_attribute_value(conn, 'datahub', process_id)
return value
def execute_emc_slim(process_id, selection_id, prop):
fq1 = os.path.basename(
default_attributes.get_attribute_value(conn, 'fastq1', process_id))
fq2 = os.path.basename(
default_attributes.get_attribute_value(conn, 'fastq2', process_id))
pair = default_attributes.get_attribute_value(conn, 'pair', process_id)
sequencing_platform = default_attributes.get_attribute_value(
conn, 'instrument_platform', process_id)
run_accession = default_attributes.get_attribute_value(
conn, 'run_accession', process_id)
sample_accession = default_attributes.get_attribute_value(
conn, 'sample_accession', process_id)
# TODO: not sure needed by SLIM
workdir = prop.workdir + process_id + "/"
print("Test:" + workdir)
# TODO: sequencing_machine shall be available in the parameters
""" Sequencing machine should be named in the metadata file."""
sequencing_machine = get_sequencing_machine(sequencing_platform)
slim = EmcSlim(fq1, fq2, prop.emc_slim_property_file, workdir,
sequencing_machine, pair, run_accession,
prop.emc_slim_program, prop, sequencing_platform,
sample_accession)
print(slim.fq1, slim.fq2, slim.emc_slim_property_file, slim.workdir,
slim.sequencing_machine, slim.sample_accession, slim.pair,
slim.run_accession, slim.emc_slim_program, prop.lsf, prop.rmem,
prop.lmem)
jobids = slim.execute()
return jobids, slim
def get_file_names(conn, process_id):
"""
Get the fastq file names from process_attributes table
:param conn: mysql connection
:param process_id:
:return: fastq files
"""
value = default_attributes.get_attribute_value(conn, 'fastq_files',
process_id)
files = list()
if ";" in value:
files = value.split(";")
else:
files.append(value)
return files
def execute_rivm_jovian(process_id, selection_id, prop): fq1 = os.path.basename(default_attributes.get_attribute_value(conn, 'fastq1', process_id)) fq2 = os.path.basename(default_attributes.get_attribute_value(conn, 'fastq2', process_id)) pair = default_attributes.get_attribute_value(conn, 'pair', process_id) sequencing_platform = default_attributes.get_attribute_value(conn, 'instrument_platform', process_id) run_accession = default_attributes.get_attribute_value(conn, 'run_accession', process_id) sample_accession = default_attributes.get_attribute_value(conn, 'sample_accession', process_id) database_dir = prop.dtu_cge_databases workdir = prop.workdir + process_id + "/" sequencing_machine = get_sequencing_machine(sequencing_platform) jovian = RivmJovian(fq1, fq2, workdir, pair, run_accession, prop, sample_accession) print(jovian.fq1, jovian.fq2, jovian.workdir, jovian.pair, jovian.run_accession, jovian.prop, jovian.sample_accession) jobids = jovian.execute() return jobids, jovian
def execute_dtu_cge(process_id, selection_id, prop):
fq1 = os.path.basename(default_attributes.get_attribute_value(conn, 'fastq1', process_id))
fq2 = os.path.basename(default_attributes.get_attribute_value(conn, 'fastq2', process_id))
pair = default_attributes.get_attribute_value(conn, 'pair', process_id)
sequencing_platform = default_attributes.get_attribute_value(conn, 'instrument_platform', process_id)
run_accession = default_attributes.get_attribute_value(conn, 'run_accession', process_id)
sample_accession = default_attributes.get_attribute_value(conn, 'sample_accession', process_id)
database_dir = prop.dtu_cge_databases
workdir = prop.workdir + process_id + "/"
print("Test:" + workdir)
sequencing_machine = get_sequencing_machine(sequencing_platform)
cge = DtuCge(fq1, fq2, database_dir, workdir, sequencing_machine, pair, run_accession, prop, sequencing_platform, sample_accession)
print(cge.fq1, cge.fq2, cge.database_dir, cge.workdir, cge.sequencing_machine, cge.pair, cge.sample_accession)
#gzip_file, tab_file, error_message , jobids = cge.execute()
jobids = cge.execute()
return jobids, cge