def get_argument_parser():
"""Function to obtain the argument parser.
Returns
-------
A fully configured `argparse.ArgumentParser` object.
Notes
-----
This function is used by the `sphinx-argparse` extension for sphinx.
"""
file_mv = cli.file_mv
desc = 'Find all runs (SRR..) associated with an SRA experiment (SRX...).'
parser = cli.get_argument_parser(desc=desc)
parser.add_argument(
'-e', '--experiment-file', type=str, required=True, metavar=file_mv,
help='File with SRA experiment IDs (starting with "SRX").'
)
parser.add_argument(
'-o', '--output-file', type=str, required=True, metavar=file_mv,
help='The output file.'
)
cli.add_reporting_args(parser)
return parser
def get_gtf_argument_parser(desc, default_field_name='gene'):
"""Return an argument parser with basic options for reading GTF files.
Parameters
----------
desc: str
Description of the ArgumentParser
default_field_name: str, optional
Name of field in GTF file to look for.
Returns
-------
`argparse.ArgumentParser` object
The argument parser.
"""
parser = cli.get_argument_parser(desc=desc)
parser.add_argument(
'-a', '--annotation-file', default='-', type=str,
help=textwrap.dedent("""\
Path of Ensembl gene annotation file (in GTF format). The file
may be gzip'ed. If set to ``-``, read from ``stdin``.""")
)
parser.add_argument(
'-o', '--output-file', required=True, type=str,
help=textwrap.dedent("""\
Path of output file. If set to ``-``, print to ``stdout``,
and redirect logging messages to ``stderr``.""")
)
parser.add_argument(
'-s', '--species', type=str,
choices=sorted(ensembl.species_chrompat.keys()), default='human',
help=textwrap.dedent("""\
Species for which to extract genes. (This parameter is ignored
if ``--chromosome-pattern`` is specified.)""")
)
parser.add_argument(
'-c', '--chromosome-pattern', type=str, required=False,
default=None, help=textwrap.dedent("""\
Regular expression that chromosome names have to match.
If not specified, determine pattern based on
``--species``.""")
)
parser.add_argument(
'-f', '--field-name', type=str, default=default_field_name,
help=textwrap.dedent("""\
Rows in the GTF file that do not contain this value
in the third column are ignored.""")
)
cli.add_reporting_args(parser)
return parser
def get_argument_parser():
"""Function to obtain the argument parser.
Returns
-------
A fully configured `argparse.ArgumentParser` object.
Notes
-----
This function is used by the `sphinx-argparse` extension for sphinx.
"""
file_mv = cli.file_mv
desc = 'Extracts gene-level expression data from StringTie output.'
parser = cli.get_argument_parser(desc)
parser.add_argument('-s',
'--stringtie-file',
type=str,
required=True,
metavar=file_mv,
help="""Path of the StringTie output file .""")
parser.add_argument(
'-g',
'--gene-file',
type=str,
required=True,
metavar=file_mv,
help="""File containing a list of protein-coding genes.""")
parser.add_argument('--no-novel-transcripts',
action='store_true',
help="""Ignore novel transcripts.""")
# parser.add_argument(
# '--ambiguous-transcripts', default = 'ignore',
# help='Strategy for counting expression of ambiguous novel '
# 'transcripts.'
# )
# possible strategies for ambiguous transcripts: 'ignore','highest','all'
parser.add_argument('-o',
'--output-file',
type=str,
required=True,
metavar=file_mv,
help="""Path of output file.""")
cli.add_reporting_args(parser)
return parser
def get_argument_parser():
"""Function to obtain the argument parser.
Returns
-------
A fully configured `argparse.ArgumentParser` object.
Notes
-----
This function is used by the `sphinx-argparse` extension for sphinx.
"""
file_mv = cli.file_mv
desc = "Extracts gene-level expression data from StringTie output."
parser = cli.get_argument_parser(desc)
parser.add_argument(
"-s",
"--stringtie-file",
type=str,
required=True,
metavar=file_mv,
help="""Path of the StringTie output file .""",
)
parser.add_argument(
"-g",
"--gene-file",
type=str,
required=True,
metavar=file_mv,
help="""File containing a list of protein-coding genes.""",
)
parser.add_argument("--no-novel-transcripts", action="store_true", help="""Ignore novel transcripts.""")
# parser.add_argument(
# '--ambiguous-transcripts', default = 'ignore',
# help='Strategy for counting expression of ambiguous novel '
# 'transcripts.'
# )
# possible strategies for ambiguous transcripts: 'ignore','highest','all'
parser.add_argument(
"-o", "--output-file", type=str, required=True, metavar=file_mv, help="""Path of output file."""
)
cli.add_reporting_args(parser)
return parser
def get_argument_parser():
"""Returns an argument parser object for the script."""
desc = 'Filter FASTA file by chromosome names.'
parser = cli.get_argument_parser(desc=desc)
parser.add_argument('-f',
'--fasta-file',
default='-',
type=str,
help=textwrap.dedent("""\
Path of the FASTA file. The file may be gzip'ed.
If set to ``-``, read from ``stdin``."""))
parser.add_argument('-s',
'--species',
type=str,
choices=sorted(ensembl.SPECIES_CHROMPAT.keys()),
default='human',
help=textwrap.dedent("""\
Species for which to extract genes. (This parameter is ignored
if ``--chromosome-pattern`` is specified.)"""))
parser.add_argument('-c',
'--chromosome-pattern',
type=str,
required=False,
default=None,
help=textwrap.dedent("""\
Regular expression that chromosome names have to match.
If not specified, determine pattern based on the setting of
``--species``."""))
parser.add_argument('-o',
'--output-file',
type=str,
required=True,
help=textwrap.dedent("""\
Path of output file. If set to ``-``, print to ``stdout``,
and redirect logging messages to ``stderr``."""))
parser = cli.add_reporting_args(parser)
return parser
def get_argument_parser():
"""Returns an argument parser object for the script."""
desc = 'Filter FASTA file by chromosome names.'
parser = cli.get_argument_parser(desc=desc)
parser.add_argument(
'-f', '--fasta-file', default='-', type=str, help=textwrap.dedent("""\
Path of the FASTA file. The file may be gzip'ed.
If set to ``-``, read from ``stdin``."""))
parser.add_argument(
'-s', '--species', type=str,
choices=sorted(ensembl.species_chrompat.keys()),
default='human', help=textwrap.dedent("""\
Species for which to extract genes. (This parameter is ignored
if ``--chromosome-pattern`` is specified.)""")
)
parser.add_argument(
'-c', '--chromosome-pattern', type=str, required=False,
default=None, help=textwrap.dedent("""\
Regular expression that chromosome names have to match.
If not specified, determine pattern based on the setting of
``--species``.""")
)
parser.add_argument(
'-o', '--output-file', type=str, required=True,
help=textwrap.dedent("""\
Path of output file. If set to ``-``, print to ``stdout``,
and redirect logging messages to ``stderr``."""))
parser = cli.add_reporting_args(parser)
return parser
def get_argument_parser():
"""Function to obtain the argument parser.
Parameters
----------
Returns
-------
`argparse.ArgumentParser`
A fully configured `argparse.ArgumentParser` object.
Notes
-----
This function can also be used by the `sphinx-argparse` extension for
sphinx to generate documentation for this script.
"""
desc = "Convert Entrez IDs to gene symbols."
parser = cli.get_argument_parser(desc=desc)
file_mv = cli.file_mv
g = parser.add_argument_group("Input and output files")
g.add_argument(
"-e", "--expression-file", required=True, type=cli.str_type, metavar=file_mv, help="The expression file."
)
g.add_argument(
"-g",
"--gene-file",
required=True,
type=cli.str_type,
metavar=file_mv,
help=textwrap.dedent(
"""\
The gene file (e.g., generated by the
ensembl_extract_protein_coding_genes.py script)."""
),
)
g.add_argument(
"-c",
"--entrez2gene-file",
required=True,
type=cli.str_type,
metavar=file_mv,
help=textwrap.dedent(
"""\
The entrez2gene file (.e.g., generated by the
ncbi_extract_entrez2gene.py script)."""
),
)
g.add_argument("-o", "--output-file", required=True, type=cli.str_type, metavar=file_mv, help="The output file.")
g = parser.add_argument_group("Conversion options")
g.add_argument(
"-s",
"--strip-affy-suffix",
action="store_true",
help=textwrap.dedent(
"""\
Strip the suffix "_at" from all Entrez IDs.
(For use in affymetrix microarray pipeline.)"""
),
)
cli.add_reporting_args(parser)
return parser
def get_argument_parser():
"""Function to obtain the argument parser.
Parameters
----------
Returns
-------
`argparse.ArgumentParser`
A fully configured `argparse.ArgumentParser` object.
Notes
-----
This function can also be used by the `sphinx-argparse` extension for
sphinx to generate documentation for this script.
"""
desc = 'Convert Entrez IDs to gene symbols.'
parser = cli.get_argument_parser(desc=desc)
file_mv = cli.file_mv
g = parser.add_argument_group('Input and output files')
g.add_argument('-e',
'--expression-file',
required=True,
type=cli.str_type,
metavar=file_mv,
help='The expression file.')
g.add_argument('-g',
'--gene-file',
required=True,
type=cli.str_type,
metavar=file_mv,
help=textwrap.dedent('''\
The gene file (e.g., generated by the
ensembl_extract_protein_coding_genes.py script).'''))
g.add_argument('-c',
'--entrez2gene-file',
required=True,
type=cli.str_type,
metavar=file_mv,
help=textwrap.dedent('''\
The entrez2gene file (.e.g., generated by the
ncbi_extract_entrez2gene.py script).'''))
g.add_argument('-o',
'--output-file',
required=True,
type=cli.str_type,
metavar=file_mv,
help='The output file.')
g = parser.add_argument_group('Conversion options')
g.add_argument('-s',
'--strip-affy-suffix',
action='store_true',
help=textwrap.dedent('''\
Strip the suffix "_at" from all Entrez IDs.
(For use in affymetrix microarray pipeline.)'''))
cli.add_reporting_args(parser)
return parser