def cli():
# Import the argument parser from allele_finder.py
parent_parser = allele_finder.cli()
parser = ArgumentParser(parents=[parent_parser])
# Get the arguments into an object
arguments = parser.parse_args()
SetupLogging(debug=arguments.verbose)
# Run the allele-finding pipeline
finder = allele_finder.AlleleFinder(
path=arguments.path,
targetfile=arguments.targetfile,
analysis_type=arguments.blast,
fasta_path=arguments.fasta_path,
genesippr=arguments.genesippr,
metadata_file=arguments.metadatafile,
cutoff=arguments.cutoff,
target_alleles=arguments.no_target_alleles,
allele_hashing=arguments.allele_hashing,
amino_acid=arguments.amino_acid,
one_based=arguments.one_based)
finder.main()
# Extract the dictionary of records from the allele finding
records = finder.records
logging.info('Allele finding complete')
# Run the profiling pipeline
profiler = ProfileAlleles(path=arguments.path,
fasta_path=arguments.fasta_path,
records=records,
amino_acid=arguments.amino_acid)
profiler.main()
logging.info('Allele Profiling complete')
def cli():
# Parser for arguments
parser = ArgumentParser(
description='Translate allele files in nucleotide format to amino acid. '
'Remove duplicates. Keep notes.')
parser.add_argument('-p',
'--path',
required=True,
help='Specify path containing allele files.')
parser.add_argument(
'--profile',
action='store_true',
help=
'Optionally parse the nucleic acid profile, and create the corresponding reduced amino '
'acid profile')
parser.add_argument(
'-o',
'--one_based',
action='store_true',
help='Use 1-based indexing rather than the default 0-based')
# Get the arguments into an object
arguments = parser.parse_args()
SetupLogging(debug=True)
translate = Translate(path=arguments.path,
profile=arguments.profile,
one_based=arguments.one_based)
translate.main()
logging.info('Allele translation complete!')
def supremacy(args):
SetupLogging(debug=args.debug)
# Create supremacy object
finder = PrimerFinder(sequence_path=args.sequencepath,
primer_file=args.primerfile,
mismatches=args.mismatches,
kmer_length=args.kmerlength,
cpus=args.cpus,
analysistype='ePCR')
# Run the script
finder.main()
def ultimatum(args):
SetupLogging(debug=args.debug)
# Create metadata objects for the samples
args.runmetadata = MetadataObject()
args.runmetadata.samples = Filer.filer(args)
finder = Ultimatum(metadataobject=args.runmetadata.samples,
sequencepath=args.sequencepath,
reportpath=os.path.join(args.sequencepath, 'reports'),
primerfile=args.primerfile,
primer_format=args.primer_format,
mismatches=args.mismatches,
export_amplicons=args.export_amplicons)
finder.main()
def cli():
# Parser for arguments
parser = ArgumentParser(
description=
'Downloads and decompresses FASTA assemblies from the NCBI FTP')
parser.add_argument('-p',
'--path',
required=True,
help='Path to folder containing necessary tables')
parser.add_argument(
'-o',
'--outputpath',
help=
'Path in which files are to be downloaded. Default is "path/downloads"'
)
parser.add_argument(
'-a',
'--accessiontable',
default='pathogens.csv',
help=
'Name of metadata table from NCBI (must be in the supplied path). Generate the table '
'from NCBI pathogens '
'e.g. https://www.ncbi.nlm.nih.gov/pathogens/isolates/#/search/taxgroup_name:%22Salmonella'
'%20enterica%22 '
'Select Download: -> Data type: Metadata -> Download. Default name is pathogens.csv'
)
parser.add_argument(
'-n',
'--numthreads',
default=3,
type=int,
choices=[1, 2, 3, 4, 5, 6],
help='Number of concurrent downloads to perform. Default is 3')
parser.add_argument(
'-s',
'--sleeptime',
default=0,
type=int,
help=
'Amount of time in seconds you would like the script to sleep until it starts the '
'download. Default is 0. NOTE: There are 3600 seconds in an hour.')
arguments = parser.parse_args()
SetupLogging()
download = AssemblyDownload(path=arguments.path,
outputpath=arguments.outputpath,
accessiontable=arguments.accessiontable,
threads=arguments.numthreads,
sleeptime=arguments.sleeptime)
download.main()
logging.info('NCBI assembly download complete!')
def __init__(self, spectra_path, filename, start_time, outputpath, classic,
extensions):
"""
:param spectra_path: Path to .spa/.spc files
:param filename: Path to .xls(x) file with renaming information.
:param start_time: Time the analyses started
:param outputpath: Path to folder in which the renamed files are to be stored
:param classic: BOOL whether to use the "classic" method of file renaming.
:param extension: BOOL whether the file extension is .spc
"""
SetupLogging()
# Define variables based on supplied arguments
if spectra_path.startswith('~'):
self.spectra_path = os.path.abspath(
os.path.expanduser(os.path.join(spectra_path)))
else:
self.spectra_path = self.file = os.path.abspath(
os.path.join(spectra_path))
assert os.path.isdir(self.spectra_path), 'Supplied sequence path is not a valid directory {0!r:s}'\
.format(self.spectra_path)
if filename.startswith('~'):
self.file = os.path.abspath(
os.path.expanduser(os.path.join(filename)))
else:
self.file = os.path.abspath(os.path.join(filename))
# If the path to the file wasn't provided, check the spectra folder
if not os.path.isfile(self.file):
self.file = os.path.join(self.spectra_path, filename)
# If the file still can't be found, check the parental folder of the spectra folder
if not os.path.isfile(self.file):
self.file = os.path.join(os.path.dirname(self.spectra_path),
filename)
self.start = start_time
assert os.path.isfile(self.file), 'Cannot find the supplied Excel file ({0!r:s}) with the file information. ' \
'Please ensure that this file is in the path, and there\'s no spelling ' \
'mistakes'.format(self.file)
# Set the output path
self.outputpath = os.path.join(outputpath)
# Create the output path as required
make_path(self.outputpath)
# Determine the naming scheme
self.classic = classic
# Variable for extensions of files to rename
self.extensions = extensions
# Create class variable
self.metadata = list()
def main():
parser = ArgumentParser(description='Perform virus typing')
parser.add_argument(
'-db',
'--dbpath',
required=True,
help='Path of folder containing .gb database files to process.')
parser.add_argument(
'-d',
'--debug',
action='store_true',
help='Allow debug-level logging to be printed to the terminal')
# Get the arguments into an object
arguments = parser.parse_args()
SetupLogging(debug=arguments.debug)
virus_typer_db = VirusTypeDB(db_path=arguments.dbpath)
virus_typer_db.main()
def cli():
# Parser for arguments
parser = ArgumentParser(description='Determines profiles of strains against previously calculated allele database '
'and profile. Creates and/or updates both the database of allele definitions '
'and the profile based on novel alleles and/or profiles discovered')
parser.add_argument('-p', '--path',
required=True,
help='Specify path. Note that due to code reuse, the query sequence files must be in the '
'"query" sub-folder, the alleles must be in the "alleles" sub-folder')
parser.add_argument('-aa', '--amino_acid',
action='store_true',
help='The query sequences are protein.')
# Get the arguments into an object
arguments = parser.parse_args()
SetupLogging(debug=True)
# Run the profiling pipeline
updater = Updater(path=arguments.path,
amino_acid=arguments.amino_acid)
updater.main()
logging.info('Allele Updating complete')
def cli():
# Parser for arguments
parser = ArgumentParser(
description='Extract the genes of interest from a profile file')
parser.add_argument('-p',
'--profile',
required=True,
help='Name and path of profile file.')
parser.add_argument(
'-n',
'--names',
required=True,
help=
'Name and path to a file containing the gene names (one per line) to be extracted '
'from the profile')
# Get the arguments into an object
arguments = parser.parse_args()
SetupLogging(debug=True)
reduce = ProfileReduce(profile=arguments.profile, names=arguments.names)
reduce.main()
logging.info('Profile reduction complete!')
def cli():
# Parser for arguments
parser = ArgumentParser(
description='Downloads and compresses FASTQ files from SRA')
parser.add_argument('-p',
'--path',
required=True,
help='Path to folder containing necessary tables')
parser.add_argument(
'-r',
'--runinfotable',
default='SraRunInfo.csv',
help=
'Name of SRA accession table from NCBI (must be in the supplied path). Generate the table '
'from NCBI SRA '
'e.g. https://www.ncbi.nlm.nih.gov/sra?LinkName=bioproject_sra_all&from_uid=309770 '
'Select Send to: -> File -> RunInfo. Default is SraRunInfo.csv')
parser.add_argument(
'-n',
'--name',
choices=['Run', 'LibraryName', 'Sample', 'BioSample', 'SampleName'],
default='SampleName',
help=
'Column name to use for the final naming of the FASTQ files. Default is SampleName'
)
parser.add_argument(
'-t',
'--threads',
default=multiprocessing.cpu_count() - 1,
help=
'Number of threads. Default is the number of cores in the system minus one'
)
arguments = parser.parse_args()
SetupLogging()
download = SRAdownload(path=arguments.path,
runinfotable=arguments.runinfotable,
column_name=arguments.name,
threads=arguments.threads)
download.main()
logging.info('SRA download complete!')
def identity(args):
SetupLogging(debug=args.debug)
# Create metadata objects for the samples
args.runmetadata = MetadataObject()
args.runmetadata.samples = Filer.filer(args)
if args.analysistype == 'vtyper':
epcr = VtyperIP(metadataobject=args.runmetadata.samples,
analysistype=args.analysistype,
reportpath=os.path.join(args.sequencepath, 'reports'))
epcr.vtyper()
else:
epcr = CustomIP(metadataobject=args.runmetadata.samples,
sequencepath=args.sequencepath,
reportpath=os.path.join(args.sequencepath, 'reports'),
primerfile=args.primerfile,
min_amplicon_size=args.minampliconsize,
max_amplicon_size=args.maxampliconsize,
primer_format=args.primer_format,
mismatches=args.mismatches,
export_amplicons=args.export_amplicons,
contigbreaks=args.contigbreaks)
epcr.main()
def legacy(args):
# Prep the args object to be used in the legacy script
SetupLogging(debug=args.debug)
args.reportpath = os.path.join(args.sequencepath, 'reports')
args.runmetadata = MetadataObject()
# Create metadata objects for the samples
args.runmetadata.samples = Filer.filer(args)
if args.analysistype == 'vtyper':
# Perform vtx typing
vtyper = Vtyper(inputobject=args,
analysistype='vtyper_legacy',
mismatches=args.mismatches)
vtyper.vtyper()
else:
epcr = Custom(inputobject=args,
analysistype='custom_epcr',
primerfile=args.primerfile,
ampliconsize=args.maxampliconsize,
mismatches=args.mismatches,
primer_format=args.primer_format,
export_amplicons=args.export_amplicons)
epcr.main()
def main():
parser = ArgumentParser(description='Perform virus typing')
parser.add_argument(
'-s',
'--sequencepath',
required=True,
help='Path of folder containing .ab1 files to process.')
parser.add_argument('-r',
'--reportpath',
required=True,
help='Path in which reports are to be created')
parser.add_argument(
'-d',
'--debug',
action='store_true',
help='Allow debug-level logging to be printed to the terminal')
# Get the arguments into an object
arguments = parser.parse_args()
SetupLogging(debug=arguments.debug)
virus_typer = VirusTyping(sequencepath=arguments.sequencepath,
reportpath=arguments.reportpath)
virus_typer.main()
def __init__(self, start, sequencepath, referencefilepath, scriptpath,
debug):
"""
:param start:
:param sequencepath:
:param referencefilepath:
:param scriptpath:
"""
self.debug = debug
SetupLogging(self.debug)
logging.info('Welcome to the CFIA bacterial typing pipeline {}'.format(
__version__))
# Define variables from the arguments - there may be a more streamlined way to do this
self.sequencepath = os.path.join(sequencepath)
self.path = self.sequencepath
self.targetpath = os.path.join(referencefilepath)
self.reffilepath = self.targetpath
# Define the start time
self.starttime = start
self.start = self.starttime
# Use the argument for the number of threads to use, or default to the number of cpus in the system
self.cpus = multiprocessing.cpu_count() - 1
# Assertions to ensure that the provided variables are valid
assert os.path.isdir(self.sequencepath), 'Supplied path location is not a valid directory {0!r:s}'\
.format(self.sequencepath)
self.reportpath = os.path.join(self.sequencepath, 'reports')
assert os.path.isdir(self.targetpath), 'Reference file path is not a valid directory {0!r:s}'\
.format(self.targetpath)
self.commit = __version__
self.homepath = scriptpath
self.analysistype = 'assembly_typing'
self.genus_specific = False
self.logfile = os.path.join(self.sequencepath, 'logfile')
self.pipeline = True
# Initialise the metadata object
self.metadata = list()
self.runmetadata = MetadataObject()
def cli():
# Parser for arguments
parser = ArgumentParser(
description=
'Finds the target sequences in allele files. Useful if you have an allele '
'database, and want to attribute subtypes e.g. STEC subtyping to your newly '
'expanded alleles')
parser.add_argument(
'-a',
'--allelepath',
required=True,
help='Name and path of folder containing generated allele files')
parser.add_argument(
'-t',
'--targetpath',
required=True,
help='Name and path of folder containing sequencing target sequences')
parser.add_argument(
'-r',
'--reportpath',
required=True,
help='Name and path of folder in which reports are to be created')
parser.add_argument('-g',
'--gene',
required=True,
choices=['stx1A', 'stx1B', 'stx2A', 'stx2B'],
help='Name of gene being profiled')
SetupLogging()
arguments = parser.parse_args()
# Run the pipeline
attributer = Attribute(allelepath=arguments.allelepath,
targetpath=arguments.targetpath,
reportpath=arguments.reportpath,
gene=arguments.gene)
attributer.main()
logging.info('Allele Attribution complete!')
def cli():
# Parser for arguments
parser = ArgumentParser(add_help=False)
parser.add_argument('-p', '--path', required=True, help='Specify path.')
parser.add_argument(
'-t',
'--targetfile',
required=True,
help=
'Name of file containing probe sequence to search. The file can be a multi-FASTA. The '
'header for each sequence must be unique, as it will be used as the name of the gene.'
'This file must be located in the supplied path folder.')
parser.add_argument('-f',
'--fasta_path',
help='Path to folder containing local files to BLAST.')
parser.add_argument(
'-g',
'--genesippr',
action='store_true',
help=
'Enable mode to specifically create alleles for the defined set of genes used in '
'the GeneSippr analysis')
parser.add_argument(
'-m',
'--metadatafile',
help=
'Name of combined metadata file used to parse the genus of each local assembly. This '
'file must be located in the supplied path folder. NOTE: This is only required if '
'performing the "GeneSippr-specific" analysis')
parser.add_argument(
'-b',
'--blast',
choices=['local', 'remote', 'both'],
default='local',
help=
'Choose whether to run either local or remote BLAST, or both. Default is local'
)
parser.add_argument('-v',
'--verbose',
action='store_true',
help='Enable verbose mode')
parser.add_argument(
'-c',
'--cutoff',
default=80,
type=int,
help='Percent identity cutoff to use when parsing BLAST outputs')
parser.add_argument(
'-n',
'--no_target_alleles',
action='store_false',
help=
'Do not include the target alleles in the output allele. If the alleles are stored, they '
'will be the first allele in the multi-FASTA file (allele_0 or '
'allele_COMPUTED_HASH - see below)')
parser.add_argument(
'-a',
'--allele_hashing',
action='store_true',
help=
'Use the first eight digits of the computed hash of the allele sequence as the allele '
'identifier (e.g. _503e35061a) rather than the arbitrary _0, _1, etc.')
parser.add_argument(
'-aa',
'--amino_acid',
choices=['targets_nt', 'targets_aa'],
help=
'Find the amino acid sequence of alleles. The target alleles supplied can either be '
'nucleotide or amino acid. Default is nucleotide')
parser.add_argument(
'-o',
'--one_based',
action='store_true',
help='Use 1-based indexing rather than the default 0-based')
arg_parser = ArgumentParser(parents=[parser])
# Get the arguments into an object
arguments = arg_parser.parse_args()
SetupLogging(debug=arguments.verbose)
# Run the pipeline
pipeline = AlleleFinder(path=arguments.path,
targetfile=arguments.targetfile,
analysis_type=arguments.blast,
fasta_path=arguments.fasta_path,
genesippr=arguments.genesippr,
metadata_file=arguments.metadatafile,
cutoff=arguments.cutoff,
target_alleles=arguments.no_target_alleles,
allele_hashing=arguments.allele_hashing,
amino_acid=arguments.amino_acid,
one_based=arguments.one_based)
pipeline.main()
logging.info('Allele finding complete')
return parser
.format(tf=self.test_folder)
self.assembly_typer = assembly_typer
self.validate_pass = False
if __name__ == '__main__':
# Parser for arguments
parser = ArgumentParser(description='Run integration tests on COWBAT pipeline')
parser.add_argument('-r', '--reference_folder',
required=True,
help='Path to reference folder with CSV reports with expected results.')
parser.add_argument('-t', '--test_folder',
required=True,
help='Path to test folder with CSV reports with observed results .')
parser.add_argument('-a', '--assembly',
action='store_true',
help='The assembly typing pipeline was used to process the run, rather than full COWBAT')
# Get the arguments into an object
args = parser.parse_args()
# Pretty logging!
SetupLogging()
# Test the reports.
validate_outputs = ValidateCowbat(reference_folder=args.reference_folder,
test_folder=args.test_folder,
assembly_typer=args.assembly)
validate_outputs.validate_cowbat()
if validate_outputs.validate_pass:
logging.info('COWBAT successfully validated! :D')
else:
logging.error('COWBAT not successfully validated.')
def cli():
# Import the argument parser from allele_finder.py
parent_parser = allele_finder.cli()
parser = ArgumentParser(parents=[parent_parser])
parser.add_argument('-min',
'--min',
default=20,
type=int,
help='Minimum size of probe to create')
parser.add_argument('-max',
'--max',
default=50,
type=int,
help='Maximum size of probe to create')
parser.add_argument(
'-c',
'--cutoff',
default=70,
help='Cutoff percent identity of a nucleotide location to use')
parser.add_argument('-gc',
'--percentgc',
default=50,
type=int,
help='Desired percent GC of the probe')
parser.add_argument(
'-r',
'--runblast',
action='store_true',
help=
'Run BLAST analyses on the supplied target file. If not enabled, then the program assumes '
'that the supplied file includes all the desired alleles to use to create the probe'
)
parser.add_argument(
'-aa',
'--amino_acid',
choices=['targets_nt', 'targets_aa'],
help=
'Find the amino acid sequence of alleles. The target alleles supplied can either be '
'nucleotide or amino acid. Default is nucleotide')
parser.add_argument(
'-o',
'--one_based',
action='store_true',
help='Use 1-based indexing rather than the default 0-based')
# Get the arguments into an object
arguments = parser.parse_args()
SetupLogging(debug=arguments.verbose)
if arguments.runblast:
# Run the allele-finding pipeline
finder = allele_finder.AlleleFinder(
path=arguments.path,
targetfile=arguments.targetfile,
analysis_type=arguments.blast,
fasta_path=arguments.fasta_path,
genesippr=arguments.genesippr,
metadata_file=arguments.metadatafile,
cutoff=arguments.cutoff,
amino_acid=arguments.amino_acid,
one_based=arguments.one_based)
finder.main()
# Run the pipeline
probes = Probes(path=arguments.path,
targetfile=arguments.targetfile,
min_length=arguments.min,
max_length=arguments.max,
cutoff=arguments.cutoff,
perc_gc=arguments.percentgc,
blast=arguments.runblast,
one_based=arguments.one_based)
probes.main()
logging.info('Probe finding complete')
def __init__(self, args):
"""
Initialises the variables required for this class
:param args: list of arguments passed to the script
"""
self.debug = args.debug
SetupLogging(self.debug)
logging.info(
'Welcome to the CFIA OLC Workflow for Bacterial Assembly and Typing (COWBAT) version {version}'
.format(version=__version__))
# Define variables from the arguments - there may be a more streamlined way to do this
self.args = args
if args.sequencepath.startswith('~'):
self.path = os.path.abspath(
os.path.expanduser(os.path.join(args.sequencepath)))
else:
self.path = os.path.abspath(os.path.join(args.sequencepath))
self.sequencepath = self.path
if args.referencefilepath.startswith('~'):
self.reffilepath = os.path.expanduser(
os.path.abspath(os.path.join(args.referencefilepath)))
else:
self.reffilepath = os.path.abspath(
os.path.join(args.referencefilepath))
self.numreads = args.numreads
self.preprocess = args.preprocess
# Define the start time
self.starttime = args.startingtime
if args.customsamplesheet:
if args.customsamplesheet.startswith('~'):
self.customsamplesheet = os.path.expanduser(
os.path.abspath(os.path.join(self.customsamplesheet)))
else:
self.customsamplesheet = os.path.abspath(
os.path.join(args.customsamplesheet))
else:
self.customsamplesheet = args.customsamplesheet
if self.customsamplesheet:
assert os.path.isfile(self.customsamplesheet), 'Cannot find custom sample sheet as specified {css}' \
.format(css=self.customsamplesheet)
self.basicassembly = args.basicassembly
if not self.customsamplesheet and not os.path.isfile(
os.path.join(self.path, 'SampleSheet.csv')):
self.basicassembly = True
logging.warning(
'Could not find a sample sheet. Performing basic assembly (no run metadata captured)'
)
# Use the argument for the number of threads to use, or default to the number of cpus in the system
self.cpus = args.threads if args.threads else multiprocessing.cpu_count(
) - 1
# Assertions to ensure that the provided variables are valid
make_path(self.path)
assert os.path.isdir(
self.path
), 'Supplied path location is not a valid directory {0!r:s}'.format(
self.path)
self.reportpath = os.path.join(self.path, 'reports')
make_path(self.reportpath)
assert os.path.isdir(self.reffilepath), 'Reference file path is not a valid directory {0!r:s}' \
.format(self.reffilepath)
self.commit = __version__
self.homepath = args.homepath
self.logfile = os.path.join(self.path, 'logfile')
self.runinfo = str()
self.pipeline = True
self.qualityobject = MetadataObject()
# Initialise the metadata object
self.runmetadata = MetadataObject()