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 run_blast(self):
"""
BLAST the alleles against the genomes
"""
logging.info('BLASTing alleles against sequence files')
for query_file in self.query_files:
# Create a metadata object to store all the sample-specific information
sample = MetadataObject()
sample.alleles = GenObject()
local_db = os.path.splitext(query_file)[0]
sample.name = os.path.basename(local_db)
# Set the name of the BLAST output file
sample.alleles.blast_report = os.path.join(
self.reportpath, '{seq_id}.tsv'.format(seq_id=sample.name))
# Update the list of metadata objects with this sample
self.runmetadata.samples.append(sample)
self.blast_reports.append(sample.alleles.blast_report)
# Run the appropriate BLAST command: BLASTn for nt; tBLASTn for aa against translated nt
if self.amino_acid:
blast = NcbitblastnCommandline(db=local_db,
query=self.target_file,
num_alignments=100000000,
evalue=0.001,
num_threads=self.cpus,
task='tblastn',
outfmt=self.outfmt,
word_size=3,
out=sample.alleles.blast_report)
else:
blast = NcbiblastnCommandline(db=local_db,
query=self.target_file,
num_alignments=100000000,
evalue=0.001,
num_threads=self.cpus,
task='blastn',
outfmt=self.outfmt,
out=sample.alleles.blast_report)
if not os.path.isfile(sample.alleles.blast_report):
# Run BLAST - supply the record sequence as stdin, so BLAST doesn't look for an input file
try:
blast()
# BLAST can have issues with genomes that have very large contigs. Retry the analysis using only one
# thread
except ApplicationError:
os.remove(sample.alleles.blast_report)
blast = NcbitblastnCommandline(
db=local_db,
query=self.target_file,
num_alignments=100000000,
evalue=0.001,
num_threads=1,
task='tblastn',
outfmt=self.outfmt,
word_size=3,
out=sample.alleles.blast_report)
blast()