def query_prep(self):
"""
Create metadata objects for each sample
"""
logging.info('Preparing query files')
# Find all the sequence files in the path
fastas = sorted(glob(os.path.join(self.query_path, '*.fasta')))
for fasta in fastas:
name = os.path.splitext(os.path.basename(fasta))[0]
if name != 'combinedtargets':
# Create a metadata object for each sample
metadata = MetadataObject()
metadata.samples = list()
# Populate the metadata object with the required attributes
metadata.name = name
metadata.general = GenObject()
metadata.commands = GenObject()
metadata.alleles = GenObject()
metadata.alleles.outputdirectory = os.path.join(self.query_path, metadata.name)
# Set the name of the BLAST output file
metadata.alleles.blast_report = os.path.join(metadata.alleles.outputdirectory,
'{seq_id}.tsv'.format(seq_id=metadata.name))
try:
os.remove(metadata.alleles.blast_report)
except FileNotFoundError:
pass
make_path(metadata.alleles.outputdirectory)
metadata.general.bestassemblyfile = relative_symlink(src_file=fasta,
output_dir=metadata.alleles.outputdirectory,
export_output=True)
metadata.samples.append(metadata)
self.runmetadata.samples.append(metadata)
def test_sistr_seqsero():
metadata = MetadataObject()
method.runmetadata.samples = list()
fasta = os.path.join(var.sequencepath, 'NC_003198.fasta')
metadata.name = os.path.split(fasta)[1].split('.')[0]
# Initialise the general and run categories
metadata.general = GenObject()
metadata.run = GenObject()
metadata.general.fastqfiles = list()
metadata.general.trimmedcorrectedfastqfiles = [
os.path.join(var.sequencepath, 'seqsero',
'2014-SEQ-1049_seqsero.fastq.gz')
]
# Set the destination folder
outputdir = os.path.join(var.sequencepath, metadata.name)
make_path(outputdir)
# Add the output directory to the metadata
metadata.general.outputdirectory = outputdir
metadata.general.logout = os.path.join(outputdir, 'out')
metadata.general.logerr = os.path.join(outputdir, 'err')
metadata.run.outputdirectory = outputdir
metadata.general.bestassemblyfile = True
# Initialise an attribute to store commands
metadata.commands = GenObject()
# Assume that all samples are Salmonella
metadata.general.referencegenus = 'Salmonella'
# Set the .fasta file as the best assembly
metadata.general.bestassemblyfile = fasta
method.runmetadata.samples.append(metadata)
method.sistr()
for sample in method.runmetadata.samples:
assert sample.sistr.cgmlst_genome_match == 'ERR586739' or sample.sistr.cgmlst_genome_match == 'SAL_BA2732AA'
method.seqsero()
for sample in method.runmetadata.samples:
assert sample.seqsero.predicted_serotype == '- 9:f,g,t:-'
variable_update()