def _record_with_genes_only(reference):
gene_names = Transcript.query.with_entities(Transcript.gene). \
filter_by(reference_id=reference.id).all()
record = _bare_record(reference)
genes = []
for gene_name in gene_names:
gene = Gene(gene_name.gene)
version = gene.newLocusTag()
my_transcript = Locus(version)
my_transcript.mRNA = PList()
my_transcript.CDS = PList()
gene.transcriptList.append(my_transcript)
genes.append(gene)
record.geneList = genes
record.seq = Seq('', generic_dna)
return record
def _record_with_genes_only(reference):
gene_names = Transcript.query.with_entities(Transcript.gene). \
filter_by(reference_id=reference.id).all()
record = _bare_record(reference)
genes = []
for gene_name in gene_names:
gene = Gene(gene_name.gene)
version = gene.newLocusTag()
my_transcript = Locus(version)
my_transcript.mRNA = PList()
my_transcript.CDS = PList()
gene.transcriptList.append(my_transcript)
genes.append(gene)
record.geneList = genes
record.seq = Seq('', generic_dna)
return record
def _get_mutalyzer_record(reference, db_transcripts):
"""
Creates a Mutalyzer specific record from the transcript entries retrieved
from the gbparser database.
:param reference: A gbparser database reference entry.
:param db_transcripts:A gbparser database list of transcript.
:return: The Mutalyzer record.
"""
record = _bare_record(reference)
# Extracting the transcripts from the DB entries.
transcripts = []
for db_transcript in db_transcripts:
transcript = {
'gene':
db_transcript.gene,
'strand':
db_transcript.strand,
'transcript_start':
db_transcript.transcript_start,
'transcript_stop':
db_transcript.transcript_stop,
'transcript_product':
db_transcript.transcript_product,
'exons': [],
'exons_start':
db_transcript.exons_start,
'exons_stop':
db_transcript.exons_stop,
'transcriptID':
db_transcript.transcript_accession + '.' +
db_transcript.transcript_version,
}
if db_transcript.protein_accession is not None \
and db_transcript.protein_version is not None:
transcript['cds_start'] = db_transcript.cds_start
transcript['cds_stop'] = db_transcript.cds_stop
transcript['protein_product'] = db_transcript.protein_product
transcript['proteinID'] = '%s.%s' %\
(db_transcript.protein_accession,
db_transcript.protein_version)
transcript['linkMethod'] = 'ncbi'
starts = map(int, db_transcript.exons_start.split(',')) \
if db_transcript.exons_start else None
stops = map(int, db_transcript.exons_stop.split(',')) \
if db_transcript.exons_stop else None
if (starts and stops) and (len(starts) == len(stops)):
for start, stop in zip(starts, stops):
exon = {'start': start, 'stop': stop}
transcript['exons'].append(exon)
transcripts.append(transcript)
# Generating the actual record entries in the Mutalyzer format.
gene_dict = {}
for db_transcript in transcripts:
if db_transcript['gene'] in gene_dict:
gene = gene_dict[db_transcript['gene']]
else:
gene = Gene(db_transcript['gene'])
if db_transcript['strand'] == '+':
gene.orientation = 1
if db_transcript['strand'] == '-':
gene.orientation = -1
transcript = Locus(gene.newLocusTag())
transcript.mRNA = PList()
transcript.mRNA.location = [
db_transcript['transcript_start'], db_transcript['transcript_stop']
]
transcript.transcriptID = db_transcript['transcriptID']
transcript.exon = PList()
if db_transcript.get('exons') \
and isinstance(db_transcript.get('exons'), list):
exon_list = []
for exon in db_transcript['exons']:
exon_list.extend([exon['start'], exon['stop']])
transcript.exon.positionList = exon_list
else:
transcript.exon.positionList = transcript.mRNA.location
transcript.mRNA.positionList = transcript.exon.positionList
transcript.mRNA.positionList.sort()
if db_transcript.get('proteinID'):
transcript.CDS = PList()
transcript.CDS.location = [
db_transcript['cds_start'], db_transcript['cds_stop']
]
transcript.CDS.positionList = cds_position_list(
transcript.mRNA.positionList, transcript.CDS.location)
transcript.proteinID = db_transcript['proteinID']
transcript.transcriptProduct = db_transcript['transcript_product']
transcript.proteinProduct = db_transcript['protein_product']
transcript.linkMethod = 'ncbi'
transcript.transcribe = True
transcript.translate = True
else:
transcript.linkMethod = None
transcript.transcribe = True
transcript.translate = False
transcript.locusTag = ''
# transcript.molType = db_transcript['molType']
gene.transcriptList.append(transcript)
gene_dict[gene.name] = gene
record.geneList = list(gene_dict.values())
# Get the sequence.
seq_path = settings.SEQ_PATH + reference.checksum_sequence + '.sequence'
try:
seq = Seq(_get_sequence_mmap(seq_path, 1, reference.length + 1),
generic_dna)
except IOError:
return None
else:
record.seq = seq
return record
def _get_mutalyzer_record(reference, db_transcripts):
"""
Creates a Mutalyzer specific record from the transcript entries retrieved
from the gbparser database.
:param reference: A gbparser database reference entry.
:param db_transcripts:A gbparser database list of transcript.
:return: The Mutalyzer record.
"""
record = _bare_record(reference)
# Extracting the transcripts from the DB entries.
transcripts = []
for db_transcript in db_transcripts:
transcript = {
'gene': db_transcript.gene,
'strand': db_transcript.strand,
'transcript_start': db_transcript.transcript_start,
'transcript_stop': db_transcript.transcript_stop,
'transcript_product': db_transcript.transcript_product,
'exons': [],
'exons_start': db_transcript.exons_start,
'exons_stop': db_transcript.exons_stop,
'transcriptID': db_transcript.transcript_accession + '.' +
db_transcript.transcript_version,
}
if db_transcript.protein_accession is not None \
and db_transcript.protein_version is not None:
transcript['cds_start'] = db_transcript.cds_start
transcript['cds_stop'] = db_transcript.cds_stop
transcript['protein_product'] = db_transcript.protein_product
transcript['proteinID'] = '%s.%s' %\
(db_transcript.protein_accession,
db_transcript.protein_version)
transcript['linkMethod'] = 'ncbi'
starts = map(int, db_transcript.exons_start.split(',')) \
if db_transcript.exons_start else None
stops = map(int, db_transcript.exons_stop.split(',')) \
if db_transcript.exons_stop else None
if (starts and stops) and (len(starts) == len(stops)):
for start, stop in zip(starts, stops):
exon = {'start': start,
'stop': stop}
transcript['exons'].append(exon)
transcripts.append(transcript)
# Generating the actual record entries in the Mutalyzer format.
gene_dict = {}
for db_transcript in transcripts:
if db_transcript['gene'] in gene_dict:
gene = gene_dict[db_transcript['gene']]
else:
gene = Gene(db_transcript['gene'])
if db_transcript['strand'] == '+':
gene.orientation = 1
if db_transcript['strand'] == '-':
gene.orientation = -1
transcript = Locus(gene.newLocusTag())
transcript.mRNA = PList()
transcript.mRNA.location = [db_transcript['transcript_start'],
db_transcript['transcript_stop']]
transcript.transcriptID = db_transcript['transcriptID']
transcript.exon = PList()
if db_transcript.get('exons') \
and isinstance(db_transcript.get('exons'), list):
exon_list = []
for exon in db_transcript['exons']:
exon_list.extend([exon['start'], exon['stop']])
transcript.exon.positionList = exon_list
else:
transcript.exon.positionList = transcript.mRNA.location
transcript.mRNA.positionList = transcript.exon.positionList
transcript.mRNA.positionList.sort()
if db_transcript.get('proteinID'):
transcript.CDS = PList()
transcript.CDS.location = [db_transcript['cds_start'],
db_transcript['cds_stop']]
transcript.CDS.positionList = cds_position_list(
transcript.mRNA.positionList,
transcript.CDS.location)
transcript.proteinID = db_transcript['proteinID']
transcript.transcriptProduct = db_transcript['transcript_product']
transcript.proteinProduct = db_transcript['protein_product']
transcript.linkMethod = 'ncbi'
transcript.transcribe = True
transcript.translate = True
else:
transcript.linkMethod = None
transcript.transcribe = True
transcript.translate = False
transcript.locusTag = ''
# transcript.molType = db_transcript['molType']
gene.transcriptList.append(transcript)
gene_dict[gene.name] = gene
record.geneList = list(gene_dict.values())
# Get the sequence.
seq_path = settings.SEQ_PATH + reference.checksum_sequence + '.sequence'
try:
seq = Seq(_get_sequence_mmap(seq_path, 1, reference.length + 1),
generic_dna)
except IOError:
return None
else:
record.seq = seq
return record
def _get_mutalyzer_record(reference, db_transcripts):
"""
Creates a Mutalyzer specific record from the transcript entries retrieved
from the gbparser database.
:param reference: A gbparser database reference entry.
:param db_transcripts:A gbparser database list of transcript.
:return: The Mutalyzer record.
"""
record = _bare_record(reference)
# Extracting the transcripts from the DB entries.
transcripts = []
for transcript in db_transcripts:
my_transcript = {
'gene': transcript.gene,
'strand': transcript.strand,
'transcript_start': transcript.transcript_start,
'transcript_stop': transcript.transcript_stop,
'cds_start': transcript.cds_start,
'cds_stop': transcript.cds_stop,
'exons': [],
'exons_start': transcript.exons_start,
'exons_stop': transcript.exons_stop,
'transcriptID': transcript.transcript_accession + '.' +
transcript.transcript_version,
'proteinID':
transcript.protein_accession + '.' + transcript.protein_version,
'linkMethod': 'ncbi'
}
# if transcript.exons_start:
# starts = transcript.exons_start.split(',')
# if transcripts.exons_stop:
# stops = transcript.exons_stopts.split(',')
starts = map(int, transcript.exons_start.split(
',')) if transcript.exons_start else None
stops = map(int, transcript.exons_stop.split(
',')) if transcript.exons_stop else None
if (starts and stops) and (len(starts) == len(stops)):
for start, stop in zip(starts, stops):
exon = {'start': start, 'stop': stop}
my_transcript['exons'].append(exon)
# if transcript.exons and isinstance(transcript.exons, list):
# for exon in transcript.exons:
# exon = {'start': exon.start,
# 'stop': exon.stop}
# my_transcript['exons'].append(exon)
transcripts.append(my_transcript)
# Generating the actual record entries in the Mutalyzer format.
gene_dict = {}
for transcript in transcripts:
if transcript['gene'] in gene_dict:
gene = gene_dict[transcript['gene']]
else:
gene = Gene(transcript['gene'])
if transcript['strand'] == '+':
gene.orientation = 1
if transcript['strand'] == '-':
gene.orientation = -1
my_transcript = Locus(gene.newLocusTag())
my_transcript.mRNA = PList()
my_transcript.mRNA.location = [
transcript['transcript_start'], transcript['transcript_stop']
]
my_transcript.CDS = PList()
my_transcript.CDS.location = [
transcript['cds_start'], transcript['cds_stop']
]
my_transcript.exon = PList()
if transcript.get('exons') and isinstance(transcript.get('exons'),
list):
exon_list = []
for exon in transcript['exons']:
exon_list.extend([exon['start'], exon['stop']])
my_transcript.exon.positionList = exon_list
else:
my_transcript.exon.positionList = my_transcript.mRNA.location
my_transcript.mRNA.positionList = my_transcript.exon.positionList
my_transcript.mRNA.positionList.sort()
my_transcript.CDS.positionList = cds_position_list(
my_transcript.mRNA.positionList, my_transcript.CDS.location)
my_transcript.transcriptID = transcript['transcriptID']
my_transcript.proteinID = transcript['proteinID']
my_transcript.linkMethod = 'ncbi'
my_transcript.transcribe = True
my_transcript.translate = True
gene.transcriptList.append(my_transcript)
gene_dict[gene.name] = gene
record.geneList = list(gene_dict.values())
# Get the sequence.
seq_path = settings.SEQ_PATH + reference.checksum_sequence + '.sequence'
try:
seq = Seq(_get_sequence_mmap(seq_path, 1, reference.length + 1),
generic_dna)
except IOError:
return None
else:
record.seq = seq
return record