def column_values_at_locus(
self,
column_name,
feature,
contig,
position,
end=None,
strand=None,
distinct=False,
sorted=False):
"""
Get the non-null values of a column from the database
at a particular range of loci
"""
# TODO: combine with the query method, since they overlap
# significantly
require_string(column_name, "column_name", nonempty=True)
contig = normalize_chromosome(contig)
require_integer(position, "position")
if end is None:
end = position
require_integer(end, "end")
if not self.column_exists(feature, column_name):
raise ValueError("Table %s doesn't have column %s" % (
feature, column_name,))
if distinct:
distinct_string = "DISTINCT "
else:
distinct_string = ""
query = """
SELECT %s%s
FROM %s
WHERE seqname = ?
AND start <= ?
AND end >= ?
""" % (distinct_string, column_name, feature)
query_params = [contig, end, position]
if strand:
query += " AND strand = ?"
query_params.append(strand)
tuples = self.connection.execute(query, query_params).fetchall()
# each result is a tuple, so pull out its first element
results = [t[0] for t in tuples if t[0] is not None]
if sorted:
results.sort()
return results
def test_require_integer():
require_integer(0)
require_integer(10)
require_integer(-10)
with assert_raises(TypeError):
require_integer("")
with assert_raises(TypeError):
require_integer(None)
def from_interbase_coordinates(contig, start, end=None):
'''
Given coordinates in 0-based interbase coordinates, return a Locus
instance.
'''
typechecks.require_string(contig)
typechecks.require_integer(start)
if end is None:
end = start + 1
typechecks.require_integer(end)
return Locus(contig, start, end)
def from_interbase_coordinates(contig, start, end=None):
'''
Given coordinates in 0-based interbase coordinates, return a Locus
instance.
'''
typechecks.require_string(contig)
typechecks.require_integer(start)
if end is None:
end = start + 1
typechecks.require_integer(end)
contig = pyensembl.locus.normalize_chromosome(contig)
return Locus(contig, start, end)
def from_inclusive_coordinates(contig, start, end=None):
'''
Given coordinates in 1-based coordinates that are inclusive on start
and end, return a Locus instance. Locus instances are always 0-based
"interbase" coordinates.
'''
typechecks.require_string(contig)
typechecks.require_integer(start)
if end is None:
end = start
typechecks.require_integer(end)
return Locus(contig, start - 1, end)
def _create_cached_db(db_path, tables, version=1):
"""
Either create or retrieve sqlite database.
Parameters
--------
db_path : str
Path to sqlite3 database file
tables : dict
Dictionary mapping table names to datacache.DatabaseTable objects
version : int, optional
Version acceptable as cached data.
Returns sqlite3 connection
"""
require_string(db_path, "db_path")
require_iterable_of(tables, DatabaseTable)
require_integer(version, "version")
# if the database file doesn't already exist and we encounter an error
# later, delete the file before raising an exception
delete_on_error = not exists(db_path)
# if the database already exists, contains all the table
# names and has the right version, then just return it
db = Database(db_path)
# make sure to delete the database file in case anything goes wrong
# to avoid leaving behind an empty DB
table_names = [table.name for table in tables]
try:
if db.has_tables(table_names) and \
db.has_version() and \
db.version() == version:
logger.info("Found existing table in database %s", db_path)
else:
if len(db.table_names()) > 0:
logger.info("Dropping tables from database %s: %s", db_path,
", ".join(db.table_names()))
db.drop_all_tables()
logger.info("Creating database %s containing: %s", db_path,
", ".join(table_names))
db.create(tables, version)
except:
logger.warning("Failed to create tables %s in database %s",
table_names, db_path)
db.close()
if delete_on_error:
remove(db_path)
raise
return db.connection
def from_inclusive_coordinates(contig, start, end=None):
'''
Given coordinates in 1-based coordinates that are inclusive on start
and end, return a Locus instance. Locus instances are always 0-based
"interbase" coordinates.
'''
typechecks.require_string(contig)
typechecks.require_integer(start)
if end is None:
end = start
typechecks.require_integer(end)
contig = pyensembl.locus.normalize_chromosome(contig)
return Locus(contig, start - 1, end)
def _finalize_database(self, version):
"""
Create metadata table for database with version number.
Parameters
----------
version : int
Tag created database with user-specified version number
"""
require_integer(version, "version")
create_metadata_sql = \
"CREATE TABLE %s (version INT)" % METADATA_TABLE_NAME
self.execute_sql(create_metadata_sql)
insert_version_sql = \
"INSERT INTO %s VALUES (%s)" % (METADATA_TABLE_NAME, version)
self.execute_sql(insert_version_sql)
def _finalize_database(self, version):
"""
Create metadata table for database with version number.
Parameters
----------
version : int
Tag created database with user-specified version number
"""
require_integer(version, "version")
create_metadata_sql = \
"CREATE TABLE %s (version INT)" % METADATA_TABLE_NAME
self.execute_sql(create_metadata_sql)
insert_version_sql = \
"INSERT INTO %s VALUES (%s)" % (METADATA_TABLE_NAME, version)
self.execute_sql(insert_version_sql)
def check_padding_around_mutation(given_padding, epitope_lengths):
"""
If user doesn't provide any padding around the mutation we need
to at least include enough of the surrounding non-mutated
esidues to construct candidate epitopes of the specified lengths.
"""
min_required_padding = max(epitope_lengths) - 1
if not given_padding:
return min_required_padding
else:
require_integer(given_padding, "Padding around mutation")
if given_padding < min_required_padding:
raise ValueError(
"Padding around mutation %d cannot be less than %d "
"for epitope lengths %s" %
(given_padding, min_required_padding, epitope_lengths))
return given_padding
def check_padding_around_mutation(given_padding, epitope_lengths):
"""
If user doesn't provide any padding around the mutation we need
to at least include enough of the surrounding non-mutated
esidues to construct candidate epitopes of the specified lengths.
"""
min_required_padding = max(epitope_lengths) - 1
if not given_padding:
return min_required_padding
else:
require_integer(given_padding, "Padding around mutation")
if given_padding < min_required_padding:
raise ValueError("Padding around mutation %d cannot "
"be less than %d for epitope lengths "
"%s" % (
given_padding,
min_required_padding,
epitope_lengths))
return given_padding
def _create_cached_db(
db_path,
tables,
version=1):
"""
Either create or retrieve sqlite database.
Parameters
--------
db_path : str
Path to sqlite3 database file
tables : dict
Dictionary mapping table names to datacache.DatabaseTable objects
version : int, optional
Version acceptable as cached data.
Returns sqlite3 connection
"""
require_string(db_path, "db_path")
require_iterable_of(tables, DatabaseTable)
require_integer(version, "version")
# if the database file doesn't already exist and we encounter an error
# later, delete the file before raising an exception
delete_on_error = not exists(db_path)
# if the database already exists, contains all the table
# names and has the right version, then just return it
db = Database(db_path)
# make sure to delete the database file in case anything goes wrong
# to avoid leaving behind an empty DB
table_names = [table.name for table in tables]
try:
if db.has_tables(table_names) and \
db.has_version() and \
db.version() == version:
logger.info("Found existing table in database %s", db_path)
else:
if len(db.table_names()) > 0:
logger.info("Dropping tables from database %s: %s",
db_path,
", ".join(db.table_names()))
db.drop_all_tables()
logger.info(
"Creating database %s containing: %s",
db_path,
", ".join(table_names))
db.create(tables, version)
except:
logger.warning(
"Failed to create tables %s in database %s",
table_names,
db_path)
db.close()
if delete_on_error:
remove(db_path)
raise
return db.connection
def column_values_at_locus(self,
column_name,
feature,
contig,
position,
end=None,
strand=None,
distinct=False,
sorted=False):
"""
Get the non-null values of a column from the database
at a particular range of loci
"""
# TODO: combine with the query method, since they overlap
# significantly
require_string(column_name, "column_name", nonempty=True)
contig = normalize_chromosome(contig)
require_integer(position, "position")
if end is None:
end = position
require_integer(end, "end")
if not self.column_exists(feature, column_name):
raise ValueError("Table %s doesn't have column %s" % (
feature,
column_name,
))
if distinct:
distinct_string = "DISTINCT "
else:
distinct_string = ""
query = """
SELECT %s%s
FROM %s
WHERE seqname = ?
AND start <= ?
AND end >= ?
""" % (distinct_string, column_name, feature)
query_params = [contig, end, position]
if strand:
query += " AND strand = ?"
query_params.append(strand)
tuples = self.connection.execute(query, query_params).fetchall()
# each result is a tuple, so pull out its first element
results = [t[0] for t in tuples if t[0] is not None]
if sorted:
results.sort()
return results
def __init__(
self,
program_name,
alleles,
epitope_lengths,
parse_output_fn,
supported_alleles_flag,
input_fasta_flag,
length_flag,
allele_flag,
tempdir_flag=None,
extra_flags=[],
max_file_records=None,
process_limit=0):
"""
Parameters
----------
program_name : str
Name of prediction program to run
(e.g. "netMHCcons" or "netMHCIIpan")
alleles : list of str
MHC alleles
epitope_lengths : list of int
supported_alleles_flag : str
Flag to pass to the predictor to get a list of supported alleles
(e.g. "-A", "-list", "-listMHC")
parse_output_fn : fn
Takes the stdout string from the predictor and returns a collection
of BindingPrediction objects
input_fasta_flag : str
How to specify the input FASTA file of source sequences (e.g. "-f")
length_flag : str
How to specify the desired predicted epitope length (e.g. "-length")
allele_flag : str
How to specify the allele we want predictions for (e.g. "-a")
tempdir_flag : str, optional
How to specify the predictor's temporary directory (e.g. "-tdir")
extra_flags : list of str
Extra flags to pass to the predictor
max_file_records : int, optional
Maximum number of sequences per input FASTA file
process_limit : int, optional
Maximum number of parallel processes to start
"""
require_string(program_name, "Predictor program name")
self.program_name = program_name
if supported_alleles_flag is not None:
require_string(supported_alleles_flag, "Supported alleles flag")
self.supported_alleles_flag = supported_alleles_flag
require_string(input_fasta_flag, "Input FASTA file flag")
self.input_fasta_flag = input_fasta_flag
require_string(allele_flag, "Allele flag")
self.allele_flag = allele_flag
require_string(length_flag, "Peptide length flag")
self.length_flag = length_flag
if tempdir_flag is not None:
require_string(tempdir_flag, "Temporary directory flag")
self.tempdir_flag = tempdir_flag
self.extra_flags = extra_flags
if max_file_records is not None:
require_integer(
max_file_records,
"Maximum number of sequences per input files")
self.max_file_records = max_file_records
require_integer(process_limit, "Maximum number of processes")
self.process_limit = process_limit
self.parse_output_fn = parse_output_fn
if self.supported_alleles_flag:
valid_alleles = self._determine_supported_alleles(
self.program_name,
self.supported_alleles_flag)
else:
# if we're not running the tool to determine supported alleles
# then at least try running it by itself to determine if it's
# it's present
try:
run_command([self.program_name])
except:
raise SystemError("Failed to run %s" % self.program_name)
valid_alleles = None
try:
BasePredictor.__init__(
self,
alleles,
epitope_lengths,
valid_alleles=valid_alleles)
except UnsupportedAllele as e:
if self.supported_alleles_flag:
additional_message = (
"\nRun command %s %s to see a list of valid alleles" % (
self.program_name,
self.supported_alleles_flag))
else:
additional_message = ""
raise UnsupportedAllele(str(e) + additional_message)
def __init__(
self,
program_name,
alleles,
parse_output_fn,
supported_alleles_flag,
input_file_flag,
length_flag,
allele_flag,
peptide_mode_flags=["-p"],
tempdir_flag=None,
extra_flags=[],
max_peptides_per_file=10**4,
process_limit=-1,
default_peptide_lengths=[9],
group_peptides_by_length=False,
min_peptide_length=8,
max_peptide_length=None,
):
"""
Parameters
----------
program_name : str
Name of prediction program to run
(e.g. "netMHCcons" or "netMHCIIpan")
alleles : list of str
MHC alleles
supported_alleles_flag : str
Flag to pass to the predictor to get a list of supported alleles
(e.g. "-A", "-list", "-listMHC")
parse_output_fn : fn
Takes the stdout string from the predictor and returns a collection
of BindingPrediction objects
input_file_flag : str
How to specify the input FASTA file of source sequences (e.g. "-f")
length_flag : str
How to specify the desired predicted peptide length (e.g. "-length")
allele_flag : str
How to specify the allele we want predictions for (e.g. "-a")
peptide_mode_flags : list of str
How to switch from the default FASTA subsequences input mode to
where peptides are explicitly given one per line of a text file.
tempdir_flag : str, optional
How to specify the predictor's temporary directory (e.g. "-tdir")
extra_flags : list of str
Extra flags to pass to the predictor
max_peptides_per_file : int, optional
Maximum number of lines per file when predicting peptides directly.
process_limit : int, optional
Maximum number of parallel processes to start
(0 for no limit, -1 for use all available processors)
default_peptide_lengths : list of int, optional
When making predictions across subsequences of protein sequences,
what peptide lengths to predict for.
group_peptides_by_length : bool
Run commandline predictor on groups of peptides of equal length
min_peptide_length : int
Shortest peptide this predictor can handle
max_peptide_length : int
Longest peptide this predictor can handle
"""
require_string(program_name, "Predictor program name")
self.program_name = program_name
if supported_alleles_flag is not None:
require_string(supported_alleles_flag, "Supported alleles flag")
self.supported_alleles_flag = supported_alleles_flag
require_string(input_file_flag, "Input file flag")
self.input_file_flag = input_file_flag
require_string(length_flag, "Peptide length flag")
self.length_flag = length_flag
require_string(allele_flag, "Allele flag")
self.allele_flag = allele_flag
require_iterable_of(peptide_mode_flags, string_types)
self.peptide_mode_flags = peptide_mode_flags
if tempdir_flag is not None:
require_string(tempdir_flag, "Temporary directory flag")
self.tempdir_flag = tempdir_flag
require_iterable_of(extra_flags, string_types)
self.extra_flags = extra_flags
require_integer(max_peptides_per_file,
"Maximum number of lines in a peptides input file")
self.max_peptides_per_file = max_peptides_per_file
require_integer(process_limit, "Maximum number of processes")
self.process_limit = process_limit
self.parse_output_fn = parse_output_fn
if isinstance(default_peptide_lengths, int):
default_peptide_lengths = [default_peptide_lengths]
self.group_peptides_by_length = group_peptides_by_length
if self.supported_alleles_flag:
valid_alleles = self._determine_supported_alleles(
self.program_name, self.supported_alleles_flag)
else:
# if we're not running the tool to determine supported alleles
# then at least try running it by itself to determine if it's
# it's present
try:
run_command([self.program_name])
except:
raise SystemError("Failed to run %s" % self.program_name)
valid_alleles = None
try:
BasePredictor.__init__(
self,
alleles=alleles,
valid_alleles=valid_alleles,
default_peptide_lengths=default_peptide_lengths,
min_peptide_length=min_peptide_length,
max_peptide_length=max_peptide_length)
except UnsupportedAllele as e:
if self.supported_alleles_flag:
additional_message = (
"\nRun command %s %s to see a list of valid alleles" %
(self.program_name, self.supported_alleles_flag))
else:
additional_message = ""
raise UnsupportedAllele(str(e) + additional_message)