def finish(self):
# Once executed, alignment is converted into relaxed
# interleaved phylip format. Both files, fasta and phylip,
# remain accessible.
# Set Task specific attributes
main_job = self.jobs[0]
fasta_path = pjoin(main_job.jobdir, "clean.alg.fasta")
alg = SeqGroup(fasta_path)
if len(alg) != self.size:
log.warning(
"Trimming was to aggressive and it tried"
" to remove one or more sequences."
" Alignment trimming will be disabled for this dataset.")
self.clean_alg_fasta_file = db.register_task_data(
self.taskid, DATATYPES.clean_alg_fasta, self.alg_fasta_file)
self.clean_alg_phylip_file = db.register_task_data(
self.taskid, DATATYPES.clean_alg_phylip, self.alg_phylip_file)
else:
for line in open(self.jobs[0].stdout_file):
line = line.strip()
if line.startswith("#ColumnsMap"):
kept_columns = map(int, line.split("\t")[1].split(","))
fasta = alg.write(format="fasta")
phylip = alg.write(format="iphylip_relaxed")
AlgCleanerTask.store_data(self, fasta, phylip, kept_columns)
def finish(self):
# Once executed, alignment is converted into relaxed
# interleaved phylip format. Both files, fasta and phylip,
# remain accessible.
# Set Task specific attributes
main_job = self.jobs[0]
fasta_path = pjoin(main_job.jobdir, "clean.alg.fasta")
alg = SeqGroup(fasta_path)
if len(alg) != self.size:
log.warning("Trimming was to aggressive and it tried"
" to remove one or more sequences."
" Alignment trimming will be disabled for this dataset."
)
self.clean_alg_fasta_file = db.register_task_data(self.taskid, DATATYPES.clean_alg_fasta, self.alg_fasta_file)
self.clean_alg_phylip_file = db.register_task_data(self.taskid, DATATYPES.clean_alg_phylip, self.alg_phylip_file)
else:
for line in open(self.jobs[0].stdout_file):
line = line.strip()
if line.startswith("#ColumnsMap"):
kept_columns = map(int, line.split("\t")[1].split(","))
fasta = alg.write(format="fasta")
phylip = alg.write(format="iphylip_relaxed")
AlgCleanerTask.store_data(self, fasta, phylip, kept_columns)
