def test_sistr(variables):
metadata = MetadataObject()
method.runmetadata.samples = list()
fasta = os.path.join(variables.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()
# Set the destination folder
outputdir = os.path.join(variables.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 == 'SAL_BA2732AA'
variable_update()
def test_sistr(variables):
metadata = MetadataObject()
method.runmetadata.samples = list()
fasta = os.path.join(variables.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()
# Set the destination folder
outputdir = os.path.join(variables.sequencepath, metadata.name)
make_path(outputdir)
# Add the output directory to the metadata
metadata.general.outputdirectory = outputdir
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 == 'SAL_BA2732AA'
variable_update()
def createobject(self):
# Grab any .fastq files in the path
fastqfiles = glob(os.path.join(self.path, '*.fastq*'))
# Extract the base name of the globbed name + path provided
fastqnames = map(lambda x: os.path.split(x)[1], filer(fastqfiles))
# Iterate through the names of the fastq files
for fastqname in sorted(fastqnames):
# Set the name
metadata = MetadataObject()
metadata.name = fastqname
# Set the destination folder
outputdir = os.path.join(self.path, fastqname)
# Make the destination folder
make_path(outputdir)
# Get the fastq files specific to the fastqname
specificfastq = glob(
os.path.join(self.path, '{}*.fastq*'.format(fastqname)))
# Make relative symlinks to the files in :self.path
try:
for fastq in specificfastq:
# Get the basename of the file
fastqfile = os.path.split(fastq)[-1]
# Set the destination fastq path as the base name plus the destination folder
destinationfastq = os.path.join(outputdir, fastqfile)
# Symlink the files
os.symlink('../{}'.format(fastqfile), destinationfastq)
# Except os errors
except OSError as exception:
# If there is an exception other than the file exists, raise it
if exception.errno != errno.EEXIST:
raise
# Initialise the general and run categories
metadata.general = GenObject()
metadata.run = GenObject()
# Populate the .fastqfiles category of :self.metadata
metadata.general.fastqfiles = [
fastq for fastq in glob(
os.path.join(outputdir, '{}*.fastq*'.format(fastqname)))
if 'trimmed' not in fastq
]
# Add the output directory to the metadata
metadata.general.outputdirectory = outputdir
metadata.run.outputdirectory = outputdir
metadata.general.bestassemblyfile = True
metadata.general.trimmedcorrectedfastqfiles = metadata.general.fastqfiles
metadata.general.logout = os.path.join(
metadata.general.outputdirectory, 'logout')
metadata.general.logerr = os.path.join(
metadata.general.outputdirectory, 'logerr')
# Initialise an attribute to store commands
metadata.commands = GenObject()
# Append the metadata to the list of samples
self.samples.append(metadata)
def setup(self):
"""
Set up the metadata object to be passed to Vtyper()
"""
from glob import glob
files = sorted(glob('{}*.fasta'.format(self.sequencepath)))
samples = list()
# Create the metadata for each file
for fasta in files:
# Create a metadata object to store all metadata associated with each strain
metadata = MetadataObject()
metadata.general = GenObject()
metadata.commands = GenObject()
# Set the name
metadata.name = os.path.basename(fasta).split('.')[0]
metadata.general.bestassemblyfile = fasta
metadata.general.stx = True
metadata.general.outputdirectory = self.path
metadata.general.filenoext = fasta.split('.')[0]
metadata.general.fastqfiles = list()
samples.append(metadata)
return samples
arguments.runmetadata.samples = list()
for fasta in fastas:
metadata = MetadataObject()
metadata.name = os.path.split(fasta)[1].split('.')[0]
# Initialise the general and run categories
metadata.general = GenObject()
metadata.run = GenObject()
# Set the destination folder
outputdir = os.path.join(arguments.sequencepath, metadata.name)
make_path(outputdir)
# Add the output directory to the metadata
metadata.general.outputdirectory = outputdir
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
arguments.runmetadata.samples.append(metadata)
arguments.cpus = multiprocessing.cpu_count()
arguments.reportpath = os.path.join(arguments.path, 'reports')
# Run the script
Sistr(arguments, 'sistr')
# Print a bold, green exit statement
print('\033[92m' + '\033[1m' + "\nElapsed Time: %0.2f seconds" %
(time.time() - arguments.starttime) + '\033[0m')