def parse_arguments(args=None):
parser = \
argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter,
description="""
This tool calculates scores per genome regions and prepares an intermediate file that can be used with ``plotHeatmap`` and ``plotProfiles``.
Typically, the genome regions are genes, but any other regions defined in a BED file can be used.
computeMatrix accepts multiple score files (bigWig format) and multiple regions files (BED format).
This tool can also be used to filter and sort regions according
to their score.
To learn more about the specific parameters, type:
$ computeMatrix reference-point --help or
$ computeMatrix scale-regions --help
""",
epilog='An example usage is:\n computeMatrix reference-point -S '
'<bigwig file(s)> -R <bed file(s)> -b 1000\n \n')
parser.add_argument('--version', action='version',
version='%(prog)s {}'.format(__version__))
subparsers = parser.add_subparsers(
title='Commands',
dest='command',
metavar='')
# scale-regions mode options
subparsers.add_parser(
'scale-regions',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
parents=[computeMatrixRequiredArgs(),
computeMatrixOutputArgs(),
computeMatrixOptArgs(case='scale-regions'),
parserCommon.gtf_options()],
help="In the scale-regions mode, all regions in the BED file are "
"stretched or shrunken to the length (in bases) indicated by the user.",
usage='An example usage is:\n computeMatrix -S '
'<biwig file> -R <bed file> -b 1000\n\n')
# reference point arguments
subparsers.add_parser(
'reference-point',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
parents=[computeMatrixRequiredArgs(),
computeMatrixOutputArgs(),
computeMatrixOptArgs(case='reference-point'),
parserCommon.gtf_options()],
help="Reference-point refers to a position within a BED region "
"(e.g., the starting point). In this mode, only those genomic"
"positions before (upstream) and/or after (downstream) of the "
"reference point will be plotted.",
usage='An example usage is:\n computeMatrix -S '
'<biwig file> -R <bed file> -a 3000 -b 3000\n\n')
return parser
def parse_arguments(args=None):
parser = \
argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter,
description="""
Given typically two or more bigWig files, ``multiBigwigSummary`` computes the average scores for each of the files in every genomic region.
This analysis is performed for the entire genome by running the program in ``bins`` mode, or for certain user selected regions in ``BED-file``
mode. Most commonly, the default output of ``multiBigwigSummary`` (a compressed numpy array, .npz) is used by other tools such as ``plotCorrelation`` or ``plotPCA`` for visualization and diagnostic purposes.
Note that using a single bigWig file is only recommended if you want to produce a bedGraph file (i.e., with the ``--outRawCounts`` option; the default output file cannot be used by ANY deepTools program if only a single file was supplied!).
A detailed sub-commands help is available by typing:
multiBigwigSummary bins -h
multiBigwigSummary BED-file -h
""",
epilog='example usage:\n multiBigwigSummary bins '
'-b file1.bw file2.bw -o results.npz\n\n'
'multiBigwigSummary BED-file -b file1.bw file2.bw -o results.npz\n'
'--BED selection.bed'
' \n\n',
conflict_handler='resolve')
parser.add_argument('--version',
action='version',
version='multiBigwigSummary {}'.format(__version__))
subparsers = parser.add_subparsers(title="commands",
dest='command',
metavar='')
parent_parser = parserCommon.getParentArgParse(binSize=False)
dbParser = parserCommon.deepBlueOptionalArgs()
# bins mode options
subparsers.add_parser(
'bins',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
parents=[
multiBigwigSummaryArgs(case='bins'), parent_parser,
parserCommon.gtf_options(suppress=True), dbParser
],
help="The average score is based on equally sized bins "
"(10 kilobases by default), which consecutively cover the "
"entire genome. The only exception is the last bin of a chromosome, which "
"is often smaller. The output of this mode is commonly used to assess the "
"overall similarity of different bigWig files.",
add_help=False,
usage='multiBigwigSummary bins '
'-b file1.bw file2.bw '
'-o results.npz\n')
# BED file arguments
subparsers.add_parser(
'BED-file',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
parents=[
multiBigwigSummaryArgs(case='BED-file'), parent_parser,
parserCommon.gtf_options(), dbParser
],
help="The user provides a BED file that contains all regions "
"that should be considered for the analysis. A "
"common use is to compare scores (e.g. ChIP-seq scores) between "
"different samples over a set of pre-defined peak regions.",
usage='multiBigwigSummary BED-file '
'-b file1.bw file2.bw '
'-o results.npz --BED selection.bed\n',
add_help=False)
return parser
def parse_arguments(args=None):
parser = \
argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter,
description="""
``multiBamSummary`` computes the read coverages for genomic regions for typically two or more BAM files.
The analysis can be performed for the entire genome by running the program in 'bins' mode.
If you want to count the read coverage for specific regions only, use the ``BED-file`` mode instead.
The standard output of ``multiBamSummary`` is a compressed numpy array (``.npz``).
It can be directly used to calculate and visualize pairwise correlation values between the read coverages using the tool 'plotCorrelation'.
Similarly, ``plotPCA`` can be used for principal component analysis of the read coverages using the .npz file.
Note that using a single bigWig file is only recommended if you want to produce a bedGraph file (i.e., with the ``--outRawCounts`` option; the default output file cannot be used by ANY deepTools program if only a single file was supplied!).
A detailed sub-commands help is available by typing:
multiBamSummary bins -h
multiBamSummary BED-file -h
""",
epilog='example usages:\n'
'multiBamSummary bins --bamfiles file1.bam file2.bam -out results.npz \n\n'
'multiBamSummary BED-file --BED selection.bed --bamfiles file1.bam file2.bam \n'
'-out results.npz'
' \n\n',
conflict_handler='resolve')
parser.add_argument('--version', action='version',
version='%(prog)s {}'.format(__version__))
subparsers = parser.add_subparsers(
title="commands",
dest='command',
description='subcommands',
help='subcommands',
metavar='')
parent_parser = parserCommon.getParentArgParse(binSize=False)
read_options_parser = parserCommon.read_options()
# bins mode options
subparsers.add_parser(
'bins',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
parents=[bamcorrelate_args(case='bins'),
parent_parser, read_options_parser,
parserCommon.gtf_options(suppress=True)
],
help="The coverage calculation is done for consecutive bins of equal "
"size (10 kilobases by default). This mode is useful to assess the "
"genome-wide similarity of BAM files. The bin size and "
"distance between bins can be adjusted.",
add_help=False,
usage='%(prog)s '
'--bamfiles file1.bam file2.bam '
'-out results.npz \n')
# BED file arguments
subparsers.add_parser(
'BED-file',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
parents=[bamcorrelate_args(case='BED-file'),
parent_parser, read_options_parser,
parserCommon.gtf_options()
],
help="The user provides a BED file that contains all regions "
"that should be considered for the coverage analysis. A "
"common use is to compare ChIP-seq coverages between two "
"different samples for a set of peak regions.",
usage='%(prog)s --BED selection.bed --bamfiles file1.bam file2.bam -out results.npz\n',
add_help=False)
return parser
def parse_arguments(args=None):
parser = \
argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter,
description="""
``multiBamSummary`` computes the read coverages for genomic regions for typically two or more BAM files.
The analysis can be performed for the entire genome by running the program in 'bins' mode.
If you want to count the read coverage for specific regions only, use the ``BED-file`` mode instead.
The standard output of ``multiBamSummary`` is a compressed numpy array (``.npz``).
It can be directly used to calculate and visualize pairwise correlation values between the read coverages using the tool 'plotCorrelation'.
Similarly, ``plotPCA`` can be used for principal component analysis of the read coverages using the .npz file.
Note that using a single bigWig file is only recommended if you want to produce a bedGraph file (i.e., with the ``--outRawCounts`` option; the default output file cannot be used by ANY deepTools program if only a single file was supplied!).
A detailed sub-commands help is available by typing:
multiBamSummary bins -h
multiBamSummary BED-file -h
""",
epilog='example usages:\n'
'multiBamSummary bins --bamfiles file1.bam file2.bam -o results.npz \n\n'
'multiBamSummary BED-file --BED selection.bed --bamfiles file1.bam file2.bam \n'
'-o results.npz'
' \n\n',
conflict_handler='resolve')
parser.add_argument('--version',
action='version',
version='%(prog)s {}'.format(__version__))
subparsers = parser.add_subparsers(title="commands",
dest='command',
description='subcommands',
help='subcommands',
metavar='')
parent_parser = parserCommon.getParentArgParse(binSize=False)
read_options_parser = parserCommon.read_options()
# bins mode options
subparsers.add_parser(
'bins',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
parents=[
bamcorrelate_args(case='bins'), parent_parser, read_options_parser,
parserCommon.gtf_options(suppress=True)
],
help="The coverage calculation is done for consecutive bins of equal "
"size (10 kilobases by default). This mode is useful to assess the "
"genome-wide similarity of BAM files. The bin size and "
"distance between bins can be adjusted.",
add_help=False,
usage='%(prog)s '
'--bamfiles file1.bam file2.bam '
'-o results.npz \n')
# BED file arguments
subparsers.add_parser(
'BED-file',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
parents=[
bamcorrelate_args(case='BED-file'), parent_parser,
read_options_parser,
parserCommon.gtf_options()
],
help="The user provides a BED file that contains all regions "
"that should be considered for the coverage analysis. A "
"common use is to compare ChIP-seq coverages between two "
"different samples for a set of peak regions.",
usage=
'%(prog)s --BED selection.bed --bamfiles file1.bam file2.bam -o results.npz\n',
add_help=False)
return parser
def parse_arguments(args=None):
parser = \
argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter,
description="""
This tool calculates scores per genome regions and prepares an intermediate file that can be used with ``plotHeatmap`` and ``plotProfiles``.
Typically, the genome regions are genes, but any other regions defined in a BED file can be used.
computeMatrix accepts multiple score files (bigWig format) and multiple regions files (BED format).
This tool can also be used to filter and sort regions according
to their score.
To learn more about the specific parameters, type:
$ computeMatrix reference-point --help or
$ computeMatrix scale-regions --help
""",
epilog='An example usage is:\n computeMatrix reference-point -S '
'<bigwig file(s)> -R <bed file(s)> -b 1000\n \n')
parser.add_argument('--version', action='version',
version='%(prog)s {}'.format(__version__))
subparsers = parser.add_subparsers(
title='Commands',
dest='command',
metavar='')
dbParser = parserCommon.deepBlueOptionalArgs()
# scale-regions mode options
subparsers.add_parser(
'scale-regions',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
parents=[computeMatrixRequiredArgs(),
computeMatrixOutputArgs(),
computeMatrixOptArgs(case='scale-regions'),
parserCommon.gtf_options(),
dbParser],
help="In the scale-regions mode, all regions in the BED file are "
"stretched or shrunken to the length (in bases) indicated by the user.",
usage='An example usage is:\n computeMatrix scale-regions -S '
'<biwig file(s)> -R <bed file> -b 1000\n\n')
# reference point arguments
subparsers.add_parser(
'reference-point',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
parents=[computeMatrixRequiredArgs(),
computeMatrixOutputArgs(),
computeMatrixOptArgs(case='reference-point'),
parserCommon.gtf_options(),
dbParser],
help="Reference-point refers to a position within a BED region "
"(e.g., the starting point). In this mode, only those genomic"
"positions before (upstream) and/or after (downstream) of the "
"reference point will be plotted.",
usage='An example usage is:\n computeMatrix reference-point -S '
'<biwig file(s)> -R <bed file> -a 3000 -b 3000\n\n')
return parser
def parse_arguments(args=None):
parser = \
argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter,
description="""
Given typically two or more bigWig files, ``multiBigwigSummary`` computes the average scores for each of the files in every genomic region.
This analysis is performed for the entire genome by running the program in ``bins`` mode, or for certain user selected regions in ``BED-file``
mode. Most commonly, the default output of ``multiBigwigSummary`` (a compressed numpy array, .npz) is used by other tools such as ``plotCorrelation`` or ``plotPCA`` for visualization and diagnostic purposes.
Note that using a single bigWig file is only recommended if you want to produce a bedGraph file (i.e., with the ``--outRawCounts`` option; the default output file cannot be used by ANY deepTools program if only a single file was supplied!).
A detailed sub-commands help is available by typing:
multiBigwigSummary bins -h
multiBigwigSummary BED-file -h
""",
epilog='example usage:\n multiBigwigSummary bins '
'-b file1.bw file2.bw -out results.npz\n\n'
'multiBigwigSummary BED-file -b file1.bw file2.bw -out results.npz\n'
'--BED selection.bed'
' \n\n',
conflict_handler='resolve')
parser.add_argument('--version', action='version',
version='multiBigwigSummary {}'.format(__version__))
subparsers = parser.add_subparsers(
title="commands",
dest='command',
metavar='')
parent_parser = parserCommon.getParentArgParse(binSize=False)
dbParser = parserCommon.deepBlueOptionalArgs()
# bins mode options
subparsers.add_parser(
'bins',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
parents=[multiBigwigSummaryArgs(case='bins'),
parent_parser,
parserCommon.gtf_options(suppress=True),
dbParser
],
help="The average score is based on equally sized bins "
"(10 kilobases by default), which consecutively cover the "
"entire genome. The only exception is the last bin of a chromosome, which "
"is often smaller. The output of this mode is commonly used to assess the "
"overall similarity of different bigWig files.",
add_help=False,
usage='multiBigwigSummary '
'-b file1.bw file2.bw '
'-out results.npz\n')
# BED file arguments
subparsers.add_parser(
'BED-file',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
parents=[multiBigwigSummaryArgs(case='BED-file'),
parent_parser,
parserCommon.gtf_options(),
dbParser
],
help="The user provides a BED file that contains all regions "
"that should be considered for the analysis. A "
"common use is to compare scores (e.g. ChIP-seq scores) between "
"different samples over a set of pre-defined peak regions.",
usage='multiBigwigSummary '
'-b file1.bw file2.bw '
'-out results.npz --BED selection.bed\n',
add_help=False)
return parser