def __init__(
self,
gene_id,
gene_name,
contig,
start,
end,
strand,
biotype,
ensembl,
require_valid_biotype=True):
self.id = gene_id
# can't check the type of ensembl since it will create a circular
# dependency between this module and ensembl_release but note that
# it's expected to be an EnsemblRelease object
self.ensembl = ensembl
self.db = ensembl.db
require_instance(self.db, Database, "db")
self.name = gene_name
Locus.__init__(self, contig, start, end, strand)
if require_valid_biotype and not is_valid_biotype(biotype):
raise ValueError(
"Invalid gene_biotype %s for gene with ID = %s" % (
biotype, gene_id))
self.biotype = biotype
def __init__(
self,
gene_id,
gene_name,
contig,
start,
end,
strand,
biotype,
genome,
require_valid_biotype=True):
"""
genome is a Genome object.
"""
self.id = gene_id
self.genome = genome
self.db = genome.db
require_instance(self.db, Database, "db")
self.name = gene_name
Locus.__init__(self, contig, start, end, strand)
if require_valid_biotype and not is_valid_biotype(biotype):
raise ValueError(
"Invalid gene_biotype %s for gene with ID = %s" % (
biotype, gene_id))
self.biotype = biotype
def __init__(self,
gene_id,
gene_name,
contig,
start,
end,
strand,
biotype,
genome,
require_valid_biotype=True):
"""
genome is a Genome object.
"""
self.id = gene_id
self.genome = genome
self.db = genome.db
require_instance(self.db, Database, "db")
self.name = gene_name
Locus.__init__(self, contig, start, end, strand)
if require_valid_biotype and not is_valid_biotype(biotype):
raise ValueError("Invalid gene_biotype %s for gene with ID = %s" %
(biotype, gene_id))
self.biotype = biotype
def __lt__(self, other):
"""
Variants are ordered by locus.
"""
require_instance(other, Variant, name="variant")
if self.contig == other.contig:
return self.start < other.start
return self.contig < other.contig
def __lt__(self, other):
"""
Variants are ordered by locus.
"""
require_instance(other, Variant, name="variant")
if self.contig == other.contig:
return self.start < other.start
return self.contig < other.contig
def check_pMHC_affinity_arrays(alleles, peptides, affinities, sample_weights):
"""
Make sure that we have the same number of peptides, affinity values,
and weights.
"""
require_instance(alleles, np.ndarray)
require_instance(peptides, np.ndarray)
require_instance(affinities, np.ndarray)
require_instance(sample_weights, np.ndarray)
if len(alleles.shape) != 1:
raise ValueError("Expected 1d array of alleles but got shape %s" %
(alleles.shape, ))
if len(peptides.shape) != 1:
raise ValueError("Expected 1d array of peptides but got shape %s" %
(peptides.shape, ))
if len(affinities.shape) != 1:
raise ValueError(
"Expected 1d array of affinity values but got shape %s" %
(alleles.shape, ))
if len(sample_weights.shape) != 1:
raise ValueError(
"Expected 1d array of sample weights but got shape %s" %
(sample_weights.shape, ))
n = len(alleles)
if len(peptides) != n:
raise ValueError("Expected %d peptides but got %d" %
(n, len(peptides)))
if len(affinities) != n:
raise ValueError("Expected %d affinity values but got %d" %
(n, len(affinities)))
if len(sample_weights) != n:
raise ValueError("Expected %d sample weights but got %d" %
(n, len(sample_weights)))
def check_pMHC_affinity_arrays(alleles, peptides, affinities, sample_weights):
"""
Make sure that we have the same number of peptides, affinity values,
and weights.
"""
require_instance(alleles, np.ndarray)
require_instance(peptides, np.ndarray)
require_instance(affinities, np.ndarray)
require_instance(sample_weights, np.ndarray)
if len(alleles.shape) != 1:
raise ValueError("Expected 1d array of alleles but got shape %s" % (
alleles.shape,))
if len(peptides.shape) != 1:
raise ValueError("Expected 1d array of peptides but got shape %s" % (
peptides.shape,))
if len(affinities.shape) != 1:
raise ValueError(
"Expected 1d array of affinity values but got shape %s" % (
alleles.shape,))
if len(sample_weights.shape) != 1:
raise ValueError(
"Expected 1d array of sample weights but got shape %s" % (
sample_weights.shape,))
n = len(alleles)
if len(peptides) != n:
raise ValueError(
"Expected %d peptides but got %d" % (n, len(peptides)))
if len(affinities) != n:
raise ValueError(
"Expected %d affinity values but got %d" % (n, len(affinities)))
if len(sample_weights) != n:
raise ValueError(
"Expected %d sample weights but got %d" % (n, len(sample_weights)))
def _validate_peptide_lengths(self, peptides, max_peptide_length=None):
require_instance(peptides, (list, tuple, np.ndarray))
if max_peptide_length is None:
max_peptide_length = max(len(p) for p in peptides)
if self.variable_length_sequences:
max_observed_length = max(len(p) for p in peptides)
if max_observed_length > max_peptide_length:
example = [
p for p in peptides if len(p) == max_observed_length
][0]
raise ValueError(
"Peptide(s) of length %d when max = %d (example '%s')" %
(max_observed_length, max_peptide_length, example))
elif any(len(p) != max_peptide_length for p in peptides):
example = [p for p in peptides if len(p) != max_peptide_length][0]
raise ValueError(
"Expected all peptides to have length %d, '%s' has length %d" %
(max_peptide_length, example, len(example)))
return max_peptide_length
