def export_active_sequences(self):
"""
Export RNA sequences with active cross-references.
"""
try:
previous_upi = ''
iupac_chars = re.compile('^[ABCDGHKMNRSTVWXYU]+$', re.IGNORECASE)
with cursor() as cur:
cur.execute(self.get_active_sequences_sql())
for counter, result in enumerate(cur):
if self.test and counter >= self.test_entries:
return
if result['upi'] == previous_upi:
continue
else:
previous_upi = result['upi']
rna = Rna(upi=result['upi'],
seq_short=result['seq_short'],
seq_long=result['seq_long'])
fasta = rna.get_sequence_fasta()
self.filehandles['seq_active'].write(fasta)
if counter < self.examples:
self.filehandles['seq_example'].write(fasta)
if iupac_chars.match(rna.get_sequence()):
self.filehandles['nhmmer_db'].write(fasta)
else:
self.filehandles['nhmmer_db_excluded'].write(fasta)
# species specific identifiers
sequence = re.sub(r'^>.+?\n', '',
fasta) # delete first line
template = ">{upi}_{taxid} {description}\n{sequence}"
queryset = rna.xrefs.filter(deleted='N')
for taxid in set(queryset.values_list('taxid', flat=True)):
description = rna.get_description(taxid=taxid)
species_specific_fasta = template.format(
upi=result['upi'],
taxid=taxid,
sequence=sequence,
description=description)
self.filehandles['species_specific'].write(
species_specific_fasta)
except psycopg2.Error as exc:
self.log_database_error(exc)
sys.exit(1)
def export_active_sequences(self):
"""
Export RNA sequences with active cross-references.
"""
try:
previous_upi = ''
iupac_chars = re.compile('^[ABCDGHKMNRSTVWXYU]+$', re.IGNORECASE)
with cursor() as cur:
cur.execute(self.get_active_sequences_sql())
for counter, result in enumerate(cur):
if self.test and counter >= self.test_entries:
return
if result['upi'] == previous_upi:
continue
else:
previous_upi = result['upi']
rna = Rna(upi=result['upi'],
seq_short=result['seq_short'],
seq_long=result['seq_long'])
fasta = rna.get_sequence_fasta()
self.filehandles['seq_active'].write(fasta)
if counter < self.examples:
self.filehandles['seq_example'].write(fasta)
if iupac_chars.match(rna.get_sequence()):
self.filehandles['nhmmer_db'].write(fasta)
else:
self.filehandles['nhmmer_db_excluded'].write(fasta)
# species specific identifiers
sequence = re.sub(r'^>.+?\n', '', fasta) # delete first line
template = ">{upi}_{taxid} {description}\n{sequence}"
queryset = rna.xrefs.filter(deleted='N')
for taxid in set(queryset.values_list('taxid', flat=True)):
description = rna.get_description(taxid=taxid)
species_specific_fasta = template.format(upi=result['upi'],
taxid=taxid,
sequence=sequence,
description=description)
self.filehandles['species_specific'].write(species_specific_fasta)
except psycopg2.Error as exc:
self.log_database_error(exc)
sys.exit(1)
def process_inactive_sequences():
"""
Create inactive.fasta file.
"""
counter = 0
previous_upi = ''
for row in self.cursor:
if self.test and counter > self.test_entries:
return
result = self.row_to_dict(row)
if result['upi'] == previous_upi:
continue
else:
previous_upi = result['upi']
rna = Rna(upi=result['upi'],
seq_short=result['seq_short'],
seq_long=read_lob(result['seq_long']))
fasta = rna.get_sequence_fasta()
self.filehandles['seq_inactive'].write(fasta)
counter += 1
def process_inactive_sequences():
"""
Create inactive.fasta file.
"""
counter = 0
previous_upi = ''
for row in self.cursor:
if self.test and counter > self.test_entries:
return
result = self.row_to_dict(row)
if result['upi'] == previous_upi:
continue
else:
previous_upi = result['upi']
rna = Rna(upi=result['upi'],
seq_short=result['seq_short'],
seq_long=read_lob(result['seq_long']))
fasta = rna.get_sequence_fasta()
self.filehandles['seq_inactive'].write(fasta)
counter += 1
def export_inactive_sequences(self):
"""
Export RNA sequences without active cross-references.
"""
try:
previous_upi = ''
with cursor() as cur:
cur.execute(self.get_inactive_sequences_sql())
for counter, result in enumerate(cur):
if self.test and counter > self.test_entries:
return
if result['upi'] == previous_upi:
continue
else:
previous_upi = result['upi']
rna = Rna(upi=result['upi'],
seq_short=result['seq_short'],
seq_long=result['seq_long'])
fasta = rna.get_sequence_fasta()
self.filehandles['seq_inactive'].write(fasta)
except psycopg2.Error as exc:
self.log_database_error(exc)
sys.exit(1)
def export_inactive_sequences(self):
"""
Export RNA sequences without active cross-references.
"""
try:
previous_upi = ''
with cursor() as cur:
cur.execute(self.get_inactive_sequences_sql())
for counter, result in enumerate(cur):
if self.test and counter > self.test_entries:
return
if result['upi'] == previous_upi:
continue
else:
previous_upi = result['upi']
rna = Rna(upi=result['upi'],
seq_short=result['seq_short'],
seq_long=result['seq_long'])
fasta = rna.get_sequence_fasta()
self.filehandles['seq_inactive'].write(fasta)
except psycopg2.Error as exc:
self.log_database_error(exc)
sys.exit(1)
def process_active_sequences():
"""
Create the active.fasta file and the example.fasta file.
"""
counter = 0
previous_upi = ''
valid_chars = re.compile('^[ABCDGHKMNRSTVWXYU]+$', re.IGNORECASE) # IUPAC
for row in self.cursor:
if self.test and counter >= self.test_entries:
return
result = self.row_to_dict(row)
if result['upi'] == previous_upi:
continue
else:
previous_upi = result['upi']
rna = Rna(upi=result['upi'],
seq_short=result['seq_short'],
seq_long=read_lob(result['seq_long']))
fasta = rna.get_sequence_fasta()
self.filehandles['seq_active'].write(fasta)
if counter < self.examples:
self.filehandles['seq_example'].write(fasta)
if valid_chars.match(rna.get_sequence()):
self.filehandles['nhmmer_db'].write(fasta)
else:
self.filehandles['nhmmer_db_excluded'].write(fasta)
# species specific identifiers
sequence = re.sub(r'^>.+?\n', '', fasta) # delete first line
template = ">{upi}_{taxid} {description}\n{sequence}"
queryset = rna.xrefs.filter(deleted='N')
for taxid in set(queryset.values_list('taxid', flat=True)):
species_specific_fasta = template.format(upi=result['upi'],
taxid=taxid, sequence=sequence, description=rna.get_description(taxid=taxid))
self.filehandles['species_specific'].write(species_specific_fasta)
counter += 1
def get_description():
"""
Get species-specific entry description.
"""
rna = Rna(upi=row['upi'])
return rna.get_description(taxid=row['taxid'])