def main(argv: Optional[List[str]] = None,
logger: Optional[logging.Logger] = None):
"""Set up loggers, parsers and directories for retrieval of genomes from NCBI.
Then retrieve taxonomy data and GenBank files from NCBI.
Return GenBank (.gbff) files and dataframe of taxonomy data.
"""
if argv is None:
parser = build_parser()
args = parser.parse_args()
else:
parser = build_parser(argv)
args = parser.parse_args()
if logger is None:
config_logger(args)
logger = logging.getLogger(__name__)
logger.info("Run initated")
# Add users email address from parser
if args.user is None:
logger.error(
"No user email provided. Email MUST be provided. Terminating programme"
)
sys.exit(1)
else:
Entrez.email = args.user
# If specified output directory for genomic files, create output directory
if args.output is not sys.stdout:
make_output_directory(args.output, args.force, args.nodelete)
# Invoke main usage of programme
# Create dataframe storing genus, species and NCBI Taxonomy ID, called 'species_table'
species_table = parse_input_file(args.input_file, args.retries)
# Pull down accession numbers and GenBank files (if not disabled)
species_table["NCBI Accession Numbers"] = species_table.apply(
get_accession_numbers, args=(args, ), axis=1)
logger.info("Generated species table")
# Write out dataframe
if args.dataframe is not sys.stdout:
write_out_dataframe(species_table, args.dataframe, args.force)
else:
species_table.to_csv(args.dataframe)
# Program finished
logger.info("Program finished and exiting")
def main(argv: Optional[List[str]] = None,
logger: Optional[logging.Logger] = None):
"""Coordinate the retrieval of protein annotations from GenBank (.gbff) files.
Including building parser, logger and output directory.
Return dataframe of protein data.
"""
if argv is None:
parser = build_parser()
args = parser.parse_args()
else:
parser = build_parser(argv)
args = parser.parse_args()
if logger is None:
config_logger(args)
logger = logging.getLogger(__name__)
# If specified output directory, create output directory to write FASTA files too
if args.output is not sys.stdout:
make_output_directory(args.output, args.force, args.nodelete)
# Open input dataframe
logger.info("Opening input dataframe %s", args.input_df)
input_df = pd.read_csv(args.input_df, header=0, index_col=0)
# Build dataframe
protein_annotation_df = create_dataframe(input_df, args)
# Write out dataframe
if args.output_df is not None:
write_out_dataframe(protein_annotation_df, args.output_df, args.force)
# Write out FASTA files
index = 0
for index in tqdm(range(len(protein_annotation_df["Genus"])),
desc="Writing protein to FASTA"):
df_row = protein_annotation_df.iloc[index]
write_fasta(df_row, logger, args)
index += 1
logger.info("Programme finsihed. Terminating.")
def test_writing_df_f_false(testing_df, df_output_file):
"""Tests function for writing out created dataframe when force is false"""
file_io.write_out_dataframe(testing_df, df_output_file, False)
def test_writing_df_no_df(df_output_file):
"""Tests function for writing out created dataframe when no df is given"""
file_io.write_out_dataframe(None, df_output_file, False)