def load_transcripts(sequence,
sample_id=None,
group_id=None,
source=None,
threshold=None):
"""Process a sequence of exon lines.
Args:
sequence (sequence): list of chanjo bed lines
sample_id (Optional[str]): unique sample id, else auto-guessed
grouip_id (Optional[str]): id to group samples
source (Optional[str]): path to coverage source (BAM/Sambamba)
threshold (Optional[int]): completeness level to disqualify exons
Returns:
Result: iterators of `Transcript`, transcripts processed, sample model
"""
exons = sambamba.depth_output(sequence)
transcripts = groupby_tx(exons, sambamba=True)
raw_stats = ((tx_id, tx_stat(tx_id, exons, threshold=threshold))
for tx_id, exons in iteritems(transcripts))
if sample_id is None:
sample_id = next(iter(itervalues(transcripts)))[0]['sampleName']
sample_obj = Sample(id=sample_id, group_id=group_id, source=source)
models = (make_model(sample_obj, tx_id, raw_stat)
for tx_id, raw_stat in raw_stats)
return Result(models=models, count=len(transcripts), sample=sample_obj)
def load_transcripts(sequence, sample_id=None, group_id=None, source=None,
threshold=None):
"""Process a sequence of exon lines.
Args:
sequence (sequence): list of chanjo bed lines
sample_id (Optional[str]): unique sample id, else auto-guessed
grouip_id (Optional[str]): id to group samples
source (Optional[str]): path to coverage source (BAM/Sambamba)
threshold (Optional[int]): completeness level to disqualify exons
Returns:
Result: iterators of `Transcript`, transcripts processed, sample model
"""
exons = sambamba.depth_output(sequence)
transcripts = groupby_tx(exons, sambamba=True)
raw_stats = ((tx_id, tx_stat(tx_id, exons, threshold=threshold))
for tx_id, exons in iteritems(transcripts))
if sample_id is None:
sample_id = next(iter(itervalues(transcripts)))[0]['sampleName']
sample_obj = Sample(id=sample_id, group_id=group_id, source=source)
models = (make_model(sample_obj, tx_id, raw_stat) for tx_id, raw_stat
in raw_stats)
return Result(models=models, count=len(transcripts), sample=sample_obj)
def gene(self, *gene_ids):
r"""Report aggregate statistics for particular genes.
Args:
\*gene_ids (List[str]): gene ids
Returns:
List[dict]: metrics grouped by sample and gene
"""
samples = {}
for gene_id in gene_ids:
logger.debug('figure out which transcripts the gene belongs to')
exon_objs = self.gene_exons(gene_id).all()
if len(exon_objs) == 0:
raise AttributeError(
"gene id not in database: {}".format(gene_id))
exon_ids = [exon_obj.exon_id for exon_obj in exon_objs]
query = (self.query().filter(Exon.exon_id.in_(exon_ids)))
for sample_id, data in self.means(query):
if sample_id not in samples:
samples[sample_id] = {'sample_id': sample_id, 'genes': {}}
samples[sample_id]['genes'][gene_id] = data
return itervalues(samples)
def gene(self, *gene_ids):
r"""Report aggregate statistics for particular genes.
Args:
\*gene_ids (List[str]): gene ids
Returns:
List[dict]: metrics grouped by sample and gene
"""
samples = {}
for gene_id in gene_ids:
logger.debug('figure out which transcripts the gene belongs to')
exon_objs = self.gene_exons(gene_id).all()
if len(exon_objs) == 0:
raise AttributeError("gene id not in database: {}"
.format(gene_id))
exon_ids = [exon_obj.exon_id for exon_obj in exon_objs]
query = (self.query().filter(Exon.exon_id.in_(exon_ids)))
for sample_id, data in self.means(query):
if sample_id not in samples:
samples[sample_id] = {'sample_id': sample_id, 'genes': {}}
samples[sample_id]['genes'][gene_id] = data
return itervalues(samples)
