def orf_prodigal_train(self):
"""Runs PRODIGAL to find open reading frames using a training file from complete genomes references."""
training_file = os.path.join(self.training_file)
if os.path.exists(training_file):
quality = " -t {} ".format(training_file)
filename = os.path.basename(self.input_file)
stdout = "2> /dev/null"
cmd = "prodigal -q -m -a {trans_file} -i {input_file} -o {output_file} -d {nuc_file} -s {potential_genes} {quality} {stdout}" \
.format(
trans_file=os.path.join(self.working_directory, "{}.temp.contig.fsa".format(filename)),
input_file=self.input_file,
output_file=os.path.join(self.working_directory, "{}.temp.draft".format(filename)),
quality=quality,
stdout=stdout,
nuc_file= os.path.join(self.working_directory, "{}.temp.contigToORF.fsa".format(filename)),
potential_genes= os.path.join(self.working_directory, "{}.temp.potentialGenes".format(filename))
)
# logger.debug(cmd)
os.system(cmd)
if self.clean == True:
os.remove(
os.path.join(self.working_directory,
"{}.temp.draft".format(filename)))
else:
logger.error("Missing training file: {} ".format(training_file))
exit()
def worker(self, input_fasta):
o_f_path, o_f_name = os.path.split(os.path.abspath(input_fasta))
cmd = "prodigal -p meta -q -m -i {input_fasta} -d {wd}/{tmp_name}.temp.contigToORF.fsa \
-a {wd}/{tmp_name}.temp.contig.fsa \
-o {wd}/{tmp_name}.temp.draft \
-s {wd}/{tmp_name}.temp.potentialGenes 2> /dev/null".format(
input_fasta=input_fasta,
wd=self.working_directory,
tmp_name=o_f_name)
# logger.debug(cmd)
os.system(cmd)
def orf_prodigal(self):
"""Runs PRODIGAL to find open reading frames."""
quality = "-n -p single"
minimum_sequence_length, maximum_sequence_length, number_of_sequences = self.min_max_sequence_length(
)
logger.info(
"minimum sequence length: {}, maximun sequence length {}, number of sequences: {}"
.format(minimum_sequence_length, maximum_sequence_length,
number_of_sequences))
if number_of_sequences > 1 and self.split_prodigal_jobs == True:
# TODO validate if fasta file doesn't contain gaps
self.orf_prodigal_multi()
else:
if self.low_quality == True or minimum_sequence_length < 20000:
quality = "-p meta"
filename = os.path.basename(self.input_file)
stdout = "2> /dev/null"
cmd = "prodigal -q -m -a {trans_file} -i {input_file} -o {output_file} -d {nuc_file} -s {potential_genes} {quality} {stdout}" \
.format(
trans_file=os.path.join(self.working_directory, "{}.temp.contig.fsa".format(filename)),
input_file=self.input_file,
output_file=os.path.join(self.working_directory, "{}.temp.draft".format(filename)),
quality=quality,
stdout=stdout,
nuc_file= os.path.join(self.working_directory, "{}.temp.contigToORF.fsa".format(filename)),
potential_genes= os.path.join(self.working_directory, "{}.temp.potentialGenes".format(filename))
)
# logger.debug(cmd)
os.system(cmd)
# format the contig file headers to remove space
#format_fasta_headers(working_directory+"/"+filename+".contig.fsa")
if self.clean == True:
os.remove(
os.path.join(self.working_directory,
"{}.temp.draft".format(filename)))
def orf_prodigal(self):
"""Runs PRODIGAL to find open reading frames."""
quality = "-n -p single"
_min, _max = self.min_max_sequence_length()
logger.info(
"minimum sequence length: {}, maximun sequence length {}".format(
_min, _max))
if self.low_quality == True or _min < 20000:
quality = "-p meta"
filename = os.path.basename(self.input_file)
stdout = "2> /dev/null"
cmd = "prodigal -q -m -a {trans_file} -i {input_file} -o {output_file} -d {nuc_file} -s {potential_genes} {quality} {stdout}" \
.format(
trans_file=os.path.join(self.working_directory, "{}.temp.contig.fsa".format(filename)),
input_file=self.input_file,
output_file=os.path.join(self.working_directory, "{}.temp.draft".format(filename)),
quality=quality,
stdout=stdout,
nuc_file= os.path.join(self.working_directory, "{}.temp.contigToORF.fsa".format(filename)),
potential_genes= os.path.join(self.working_directory, "{}.temp.potentialGenes".format(filename))
)
logger.info(cmd)
os.system(cmd)
# format the contig file headers to remove space
#format_fasta_headers(working_directory+"/"+filename+".contig.fsa")
if self.clean == True:
os.remove(
os.path.join(self.working_directory,
"{}.temp.draft".format(filename)))