def test_is_integer():
assert is_integer(0)
assert is_integer(-1)
assert is_integer(1)
# big integer
assert is_integer(10**30)
assert not is_integer("")
assert not is_integer("a")
assert not is_integer([])
assert not is_integer([1])
assert not is_integer(object())
assert not is_integer(None)
def infer_genome(genome_object_string_or_int):
"""
If given an integer, return associated human EnsemblRelease for that
Ensembl version.
If given a string, return latest EnsemblRelease which has a reference
of the same name.
If given a PyEnsembl Genome, simply return it.
"""
if isinstance(genome_object_string_or_int, Genome):
return genome_object_string_or_int
if is_integer(genome_object_string_or_int):
return cached_release(genome_object_string_or_int)
elif is_string(genome_object_string_or_int):
# first infer the canonical reference name, e.g. mapping hg19 -> GRCh37
# and then get the associated PyEnsembl Genome object
reference_name = infer_reference_name(genome_object_string_or_int)
return genome_for_reference_name(reference_name)
else:
raise TypeError(
("Expected genome to be an int, string, or pyensembl.Genome "
"instance, got %s : %s") % (
str(genome_object_string_or_int),
type(genome_object_string_or_int)))
def normalize_chromosome(c):
try:
return NORMALIZE_CHROMOSOME_CACHE[c]
except KeyError:
pass
if not (is_string(c) or is_integer(c)):
raise TypeError("Chromosome cannot be '%s' : %s" % (c, type(c)))
result = str(c)
if result == "0":
raise ValueError("Chromosome name cannot be 0")
elif result == "":
raise ValueError("Chromosome name cannot be empty")
# only strip off lowercase chr since some of the non-chromosomal
# contigs start with "CHR"
if result.startswith("chr"):
result = result[3:]
# just in case someone is being lazy, capitalize "M", "MT", X", "Y"
result = result.upper()
# standardize mitochondrial genome to be "MT"
if result == "M":
result = "MT"
# interning strings since the chromosome names probably get constructed
# or parsed millions of times, can save memory in tight situations
# (such as parsing GTF files)
result = intern(result)
NORMALIZE_CHROMOSOME_CACHE[c] = result
return result
def normalize_chromosome(c):
try:
return NORMALIZE_CHROMOSOME_CACHE[c]
except KeyError:
pass
if not (is_string(c) or is_integer(c)):
raise TypeError("Chromosome cannot be '%s' : %s" % (c, type(c)))
result = str(c)
if result == "0":
raise ValueError("Chromosome name cannot be 0")
elif result == "":
raise ValueError("Chromosome name cannot be empty")
# only strip off lowercase chr since some of the non-chromosomal
# contigs start with "CHR"
if result.startswith("chr"):
result = result[3:]
# standardize mitochondrial genome to be "MT"
if result == "M":
result = "MT"
else:
# just in case someone is being lazy, capitalize "X" and "Y"
result = result.upper()
# interning strings since the chromosome names probably get constructed
# or parsed millions of times, can save memory in tight situations
# (such as parsing GTF files)
result = intern(result)
NORMALIZE_CHROMOSOME_CACHE[c] = result
return result
def normalize_chromosome(c):
try:
return NORMALIZE_CHROMOSOME_CACHE[c]
except KeyError:
pass
result = c
if is_integer(result):
if result == 0:
raise ValueError("Contig cannot be 0")
result = str(result)
else:
require_string(result, "contig name", nonempty=True)
# only strip off lowercase chr since some of the non-chromosomal
# contigs start with "CHR"
if result.startswith("chr"):
result = result[3:]
# standardize mitochondrial genome to be "MT"
if result == "M":
result = "MT"
else:
# just in case someone is being lazy, capitalize "X" and "Y"
result = result.upper()
NORMALIZE_CHROMOSOME_CACHE[c] = result
return result
def infer_genome(genome_object_string_or_int):
"""
If given an integer, get the human EnsemblRelease object for that
Ensembl version.
If given a string, return latest EnsemblRelease which has an equivalent
reference. If the given name is a UCSC genome (e.g. hg19) then convert
it to the equivalent Ensembl reference (e.g. GRCh37).
If given a PyEnsembl Genome, simply use it.
Returns a pair of (Genome, bool) where the bool corresponds to whether
the input requested a UCSC genome (e.g. "hg19") and an Ensembl (e.g. GRCh37)
was returned as a substitute.
"""
converted_ucsc_to_ensembl = False
if isinstance(genome_object_string_or_int, Genome):
genome = genome_object_string_or_int
elif is_integer(genome_object_string_or_int):
genome = cached_ensembl_release(genome_object_string_or_int)
elif is_string(genome_object_string_or_int):
genome, converted_ucsc_to_ensembl = \
infer_genome_for_reference_name(genome_object_string_or_int)
else:
raise TypeError(
("Expected genome to be an int, string, or pyensembl.Genome "
"instance, got %s : %s") % (
str(genome_object_string_or_int),
type(genome_object_string_or_int)))
return genome, converted_ucsc_to_ensembl
def infer_genome(genome_object_string_or_int):
"""
If given an integer, return associated human EnsemblRelease for that
Ensembl version.
If given a string, return latest EnsemblRelease which has a reference
of the same name.
If given a PyEnsembl Genome, simply return it.
"""
if isinstance(genome_object_string_or_int, Genome):
return genome_object_string_or_int
if is_integer(genome_object_string_or_int):
return cached_release(genome_object_string_or_int)
elif is_string(genome_object_string_or_int):
# first infer the canonical reference name, e.g. mapping hg19 -> GRCh37
# and then get the associated PyEnsembl Genome object
reference_name = infer_reference_name(genome_object_string_or_int)
return genome_for_reference_name(reference_name)
else:
raise TypeError(
("Expected genome to be an int, string, or pyensembl.Genome "
"instance, got %s : %s") % (
str(genome_object_string_or_int),
type(genome_object_string_or_int)))
def normalize_chromosome(c):
try:
return NORMALIZE_CHROMOSOME_CACHE[c]
except KeyError:
pass
if not (is_string(c) or is_integer(c)):
raise TypeError("Chromosome cannot be '%s' : %s" % (c, type(c)))
result = str(c)
if result == "0":
raise ValueError("Chromosome name cannot be 0")
elif result == "":
raise ValueError("Chromosome name cannot be empty")
if result.startswith("chr") and "_" not in result:
# excluding "_" for names like "chrUn_gl000212"
# capitalize "chrx" -> "chrX"
result = "chr" + result[3:].upper()
elif result.isalpha():
# capitalize e.g. "x" -> "X"
result = result.upper()
# interning strings since the chromosome names probably get constructed
# or parsed millions of times, can save memory in tight situations
# (such as parsing GTF files)
result = intern(result)
NORMALIZE_CHROMOSOME_CACHE[c] = result
return result
