def main(unparsed_args_list):
"""Uses parsed_args to run the entirety of the pham align pipeline.
:param unparsed_args_list: Input a list of command line args.
:type unparsed_args_list: list[str]
"""
args = parse_pham_align(unparsed_args_list)
config = configfile.build_complete_config(args.config_file)
alchemist = pipelines_basic.build_alchemist(args.database, config=config)
values = pipelines_basic.parse_value_input(args.input)
execute_pham_align(alchemist,
folder_path=args.folder_path,
folder_name=args.folder_name,
values=values,
filters=args.filters,
groups=args.groups,
file_type=args.file_type,
mat_out=args.distmat_out,
tree_out=args.guidetree_out,
verbose=args.verbose,
dump=args.dump,
force=args.force,
threads=args.number_threads)
def main(unparsed_args_list):
"""
Run the get_db pipeline.
The database data can be retrieved from three places:
The server, which needs to be downloaded to a new folder.
A local file, in which no download and no new folder are needed.
The empty schema stored within pdm_utils, in which no download, new folder,
or local file are needed.
:param unparsed_args_list: list of arguments to run the pipeline unparsed
:type unparsed_args_list: list
"""
args = parse_args(unparsed_args_list)
# Set values that are shared between all three options.
config = configfile.build_complete_config(args.config_file)
alchemist = pipelines_basic.build_alchemist(None,
config=config,
ask_database=False)
if args.option == "file":
execute_get_file_db(alchemist,
args.database,
args.filename,
config_file=args.config_file,
schema_version=args.schema_version,
verbose=args.verbose)
elif args.option == "new":
execute_get_new_db(alchemist,
args.database,
args.schema_version,
config_file=args.config_file,
verbose=args.verbose)
else:
url = args.url
if url is None:
server_creds = config["download_server"]
url = server_creds.get("url")
if url is None:
url = DEFAULT_SETTINGS["url"]
execute_get_server_db(alchemist,
args.database,
url,
folder_path=args.output_folder,
db_name=args.db_name,
config_file=args.config_file,
verbose=args.verbose,
subdirectory=args.remote_directory,
download_only=args.download_only,
get_version=args.get_version,
force_pull=args.force_pull,
schema_version=args.schema_version)
def main(unparsed_args_list):
args = parse_make_db(unparsed_args_list)
alchemist = pipelines_basic.build_alchemist(args.database)
values = pipelines_basic.parse_value_input(args.input)
execute_make_db(alchemist, args.db_type, folder_path=args.folder_path,
folder_name=args.folder_name, values=values,
verbose=args.verbose, filters=args.filters,
groups=args.groups, db_name=args.database_name,
threads=args.threads, use_mpi=args.use_mpi)
def main(unparsed_args_list):
"""Run main get_gb_records pipeline."""
# Parse command line arguments
args = parse_args(unparsed_args_list)
# Create config object with data obtained from file and/or defaults.
config = configfile.build_complete_config(args.config_file)
alchemist = pipelines_basic.build_alchemist(args.database, config=config)
mysqldb.check_schema_compatibility(alchemist.engine,
"the get_gb_records pipeline")
values = pipelines_basic.parse_value_input(args.input)
execute_get_gb_records(alchemist, args.file_type,
folder_path=args.folder_path,
folder_name=args.folder_name,
config=config,
values=values, verbose=args.verbose,
filters=args.filters, groups=args.groups)
def main(unparsed_args_list):
"""Uses parsed args to run the entirety of the file export pipeline.
:param unparsed_args_list: Input a list of command line args.
:type unparsed_args_list: list[str]
"""
# Returns after printing appropriate error message from parsing/connecting.
args = parse_export(unparsed_args_list)
config = configfile.build_complete_config(args.config_file)
alchemist = pipelines_basic.build_alchemist(args.database, config=config)
# Exporting as a SQL file is not constricted by schema version.
if args.pipeline != "sql":
mysqldb.check_schema_compatibility(alchemist.engine, "export")
values = None
if args.pipeline in FILTERABLE_PIPELINES:
values = pipelines_basic.parse_value_input(args.input)
if not values:
values = None
if args.pipeline not in PIPELINES:
print("ABORTED EXPORT: Unknown pipeline option discrepency.\n"
"Pipeline parsed from command line args is not supported")
sys.exit(1)
if args.pipeline != "I":
execute_export(alchemist, args.pipeline, folder_path=args.folder_path,
folder_name=args.folder_name, table=args.table,
values=values, filters=args.filters, groups=args.groups,
sort=args.sort, include_columns=args.include_columns,
exclude_columns=args.exclude_columns,
sequence_columns=args.sequence_columns,
raw_bytes=args.raw_bytes,
concatenate=args.concatenate, db_name=args.db_name,
verbose=args.verbose, dump=args.dump, force=args.force,
threads=args.number_processes, phams_out=args.phams_out)
else:
pass
def main(unparsed_args):
"""Uses parsed args to run the entirety of the find primers pipeline.
:param unparsed_args: Input a list of command line args.
:type unparsed_args: list[str]
"""
args = parse_find_primers(unparsed_args)
config = configfile.build_complete_config(args.config_file)
alchemist = pipelines_basic.build_alchemist(args.database, config=config)
values = pipelines_basic.parse_value_input(args.input)
execute_find_primers(alchemist,
folder_path=args.folder_path,
folder_name=args.folder_name,
values=values,
filters=args.filters,
groups=args.groups,
verbose=args.verbose,
threads=args.threads,
prc=args.prc,
minD=args.minD,
maxD=args.maxD,
hpn_min=args.hpn_min,
ho_min=args.ho_min,
het_min=args.het_min,
GC_max=args.GC,
len_oligomer=args.oligomer_length,
tm_min=args.tm_min,
tm_max=args.tm_max,
tm_gap=args.tm_gap,
ta_min=args.ta_min,
ta_max=args.ta_max,
mode=args.mode,
soft_cap=args.soft_cap,
phams_in=args.phams_in,
fwd_in=args.fwd_in,
rvs_in=args.rvs_in)
def main(unparsed_args_list):
"""Uses parsed args to run the entirety of the pham_finder pipeline.
:param unparsed_args_list: Input a list of command line args.
:type unparsed_args_list: list[str]
"""
args = parse_pham_finder(unparsed_args_list)
config = configfile.build_complete_config(args.config_file)
alchemist = pipelines_basic.build_alchemist(None, ask_database=False,
config=config)
values = None
if args.input:
values = pipelines_basic.parse_value_input(args.input)
execute_pham_finder(alchemist, args.folder_path, args.folder_name,
args.adatabase, args.bdatabase, values=values,
filters=args.filters, groups=args.groups,
sort=args.sort, show_per=args.show_percentages,
use_locus=args.use_locus, verbose=args.verbose)
def main(unparsed_args_list):
args = parse_build_pan(unparsed_args_list)
config = configfile.build_complete_config(args.config_file)
alchemist = pipelines_basic.build_alchemist(args.database, config=config)
values = pipelines_basic.parse_value_input(args.input)
execute_build_pan(alchemist,
hhdb_path=args.hhsuite_database,
folder_path=args.folder_path,
folder_name=args.folder_name,
values=values,
verbose=args.verbose,
filters=args.filters,
groups=args.groups,
threads=args.number_threads,
M=args.min_percent_gaps,
aD=args.avg_distance,
mD=args.min_distance,
B=args.DB_stiffness,
PANgraph_out=args.PANgraph_out)
def main(unparsed_args_list):
args = parse_cluster_db(unparsed_args_list)
config = configfile.build_complete_config(args.config_file)
alchemist = pipelines_basic.build_alchemist(args.database, config=config)
values = pipelines_basic.parse_value_input(args.input)
execute_cluster_db(alchemist,
folder_path=args.folder_path,
folder_name=args.folder_name,
values=values, verbose=args.verbose,
filters=args.filters, groups=args.groups,
threads=args.number_threads, kmer=args.kmer_size,
sketch=args.sketch_size,
gcs=args.gene_content_similarity_min,
ani=args.average_nucleotide_identity_min,
gcsmax=args.gene_content_similarity_max,
animax=args.average_nucleotide_identity_max,
gcsS=args.gcsS, gcsM=args.gcsM, aniS=args.aniS,
aniM=args.aniM, evaluate=args.dump_evaluation,
mat_out=args.distmat_out, subcluster=args.subcluster,
cluster_prefix=args.cluster_prefix)
def main(unparsed_args_list):
"""Uses parsed args to run the entirety of the pham_review pipeline.
:param unparsed_args_list: Input a list of command line args.
:type unparsed_args_list: list[str]
"""
args = parse_pham_review(unparsed_args_list)
config = configfile.build_complete_config(args.config_file)
alchemist = pipelines_basic.build_alchemist(args.database, config=config)
values = pipelines_basic.parse_value_input(args.input)
if not args.all_reports:
gr_reports = args.gene_reports
s_report = args.summary_report
psr_reports = args.pham_summary_reports
else:
gr_reports = True
s_report = True
psr_reports = True
execute_pham_review(alchemist,
folder_path=args.folder_path,
folder_name=args.folder_name,
no_review=args.no_review,
values=values,
force=args.force,
filters=args.filters,
groups=args.groups,
sort=args.sort,
s_report=s_report,
gr_reports=gr_reports,
production=args.production,
psr_reports=psr_reports,
verbose=args.verbose)
def main(unparsed_args_list):
"""Uses parsed args to run the entirety of the revise pipeline.
:param unparsed_args_list: Input a list of command line args.
:type unparsed_args_list: list[str]
"""
args = parse_revise(unparsed_args_list)
config = configfile.build_complete_config(args.config_file)
alchemist = pipelines_basic.build_alchemist(args.database, config=config)
if args.pipeline == "local":
execute_local_revise(alchemist,
args.revisions_file,
folder_path=args.folder_path,
folder_name=args.folder_name,
config=config,
input_type=args.input_type,
output_type=args.output_type,
filters=args.filters,
groups=args.groups,
verbose=args.verbose,
force=args.force,
production=args.production)
elif args.pipeline == "remote":
values = pipelines_basic.parse_value_input(args.input)
execute_remote_revise(alchemist,
folder_path=args.folder_path,
folder_name=args.folder_name,
config=config,
values=values,
filters=args.filters,
groups=args.groups,
verbose=args.verbose,
output_type=args.output_type,
force=args.force)