def parseArguments():
parentParser = parserCommon.getParentArgParse()
bamParser = parserCommon.read_options()
normalizationParser = parserCommon.normalization_options()
requiredArgs = get_required_args()
optionalArgs = get_optional_args()
outputParser = parserCommon.output()
parser = \
argparse.ArgumentParser(
parents=[requiredArgs, outputParser, optionalArgs,
parentParser, normalizationParser, bamParser],
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description='This tool takes an alignment of reads or fragments '
'as input (BAM file) and generates a coverage track (bigWig or '
'bedGraph) as output. '
'The coverage is calculated as the number of reads per bin, '
'where bins are short consecutive counting windows of a defined '
'size. It is possible to extended the length of the reads '
'to better reflect the actual fragment length. *bamCoverage* '
'offers normalization by scaling factor, Reads Per Kilobase per '
'Million mapped reads (RPKM), counts per million (CPM), bins per '
'million mapped reads (BPM) and 1x depth (reads per genome '
'coverage, RPGC).\n',
usage='An example usage is:'
'$ bamCoverage -b reads.bam -o coverage.bw',
add_help=False)
return parser
def parseArguments():
parentParser = parserCommon.getParentArgParse()
bamParser = parserCommon.read_options()
normalizationParser = parserCommon.normalization_options()
requiredArgs = get_required_args()
optionalArgs = get_optional_args()
outputParser = parserCommon.output()
parser = \
argparse.ArgumentParser(
parents=[requiredArgs, outputParser, optionalArgs,
parentParser, normalizationParser, bamParser],
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description='This tool takes an alignment of reads or fragments '
'as input (BAM file) and generates a coverage track (bigWig or '
'bedGraph) as output. '
'The coverage is calculated as the number of reads per bin, '
'where bins are short consecutive counting windows of a defined '
'size. It is possible to extended the length of the reads '
'to better reflect the actual fragment length. *bamCoverage* '
'offers normalization by scaling factor, Reads Per Kilobase per '
'Million mapped reads (RPKM), counts per million (CPM), bins per '
'million mapped reads (BPM) and 1x depth (reads per genome '
'coverage, RPGC).\n',
usage='An example usage is:'
'$ bamCoverage -b reads.bam -o coverage.bw',
add_help=False)
return parser
def parseArguments():
parentParser = parserCommon.getParentArgParse()
bamParser = parserCommon.read_options()
normalizationParser = parserCommon.normalization_options()
requiredArgs = getRequiredArgs()
optionalArgs = getOptionalArgs()
outputParser = parserCommon.output()
parser = argparse.ArgumentParser(
parents=[requiredArgs, outputParser, optionalArgs,
parentParser, normalizationParser, bamParser],
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description='This tool compares two BAM files based on the number of '
'mapped reads. To compare the BAM files, the genome is partitioned '
'into bins of equal size, then the number of reads found in each bin'
'is counted per file and finally a summary value is '
'reported. This value can be the ratio of the number of reads per '
'bin, the log2 of the ratio or the difference. \nThis tool can '
'normalize the number of reads in each BAM file using the SES method '
'proposed by Diaz et al. (2012) "Normalization, bias correction, and '
'peak calling for ChIP-seq". Statistical Applications in Genetics '
'and Molecular Biology, 11(3). Normalization based on read counts '
'is also available. \nThe output is either a bedgraph or bigWig file '
'containing the bin location and the resulting comparison value. By '
'default, if reads are paired, the fragment length reported in the BAM '
'file is used. Each mate, however, '
'is treated independently to avoid a bias when a mixture of concordant '
'and discordant pairs is present. This means that *each end* will '
'be extended to match the fragment length.',
usage=' bamCompare -b1 treatment.bam -b2 control.bam -o log2ratio.bw',
add_help=False)
return parser
def parseArguments():
parentParser = parserCommon.getParentArgParse()
bamParser = parserCommon.read_options()
normalizationParser = parserCommon.normalization_options()
requiredArgs = getRequiredArgs()
optionalArgs = getOptionalArgs()
outputParser = parserCommon.output()
parser = argparse.ArgumentParser(
parents=[
requiredArgs, outputParser, optionalArgs, parentParser,
normalizationParser, bamParser
],
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description='This tool compares two BAM files based on the number of '
'mapped reads. To compare the BAM files, the genome is partitioned '
'into bins of equal size, then the number of reads found in each is counted per file '
'and finally a summary value is '
'reported. This value can be the ratio of the number of reads per '
'bin, the log2 of the ratio or the difference. This tool can '
'normalize the number of reads in each BAM file using the SES method '
'proposed in Diaz et al. (2012). "Normalization, bias correction, and '
'peak calling for ChIP-seq". Statistical applications in genetics '
'and molecular biology, 11(3). Normalization based on read counts '
'is also available. The output is either a bedgraph or bigWig file '
'containing the bin location and the resulting comparison values. By '
'default, if reads are mated, the fragment length reported in the BAM '
'file is used. In the case of paired-end mapping, each mate '
'is treated independently to avoid a bias when a mixture of concordant '
'and discordant pairs is present. This means that *each end* will '
'be extended to match the fragment length.',
usage='An example usage is:\n bamCompare '
'-b1 treatment.bam -b2 control.bam -o log2ratio.bw',
add_help=False)
return parser
def parseArguments():
parentParser = parserCommon.getParentArgParse()
bamParser = parserCommon.read_options()
normalizationParser = parserCommon.normalization_options()
requiredArgs = getRequiredArgs()
optionalArgs = getOptionalArgs()
outputParser = parserCommon.output()
parser = argparse.ArgumentParser(
parents=[
requiredArgs, outputParser, optionalArgs, parentParser,
normalizationParser, bamParser
],
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description='This tool compares two BAM files based on the number of '
'mapped reads. To compare the BAM files, the genome is partitioned '
'into bins of equal size, then the number of reads found in each bin'
' is counted per file, and finally a summary value is '
'reported. This value can be the ratio of the number of reads per '
'bin, the log2 of the ratio, or the difference. This tool can '
'normalize the number of reads in each BAM file using the SES method '
'proposed by Diaz et al. (2012) "Normalization, bias correction, and '
'peak calling for ChIP-seq". Statistical Applications in Genetics '
'and Molecular Biology, 11(3). Normalization based on read counts '
'is also available. The output is either a bedgraph or bigWig file '
'containing the bin location and the resulting comparison value. '
'Note that *each end* in a pair (for paired-end reads) is treated '
'independently. If this is undesirable, then use the --samFlagInclude '
'or --samFlagExclude options.',
usage=' bamCompare -b1 treatment.bam -b2 control.bam -o log2ratio.bw',
add_help=False)
return parser
def parseArguments():
parentParser = parserCommon.getParentArgParse()
bamParser = parserCommon.read_options()
normalizationParser = parserCommon.normalization_options()
requiredArgs = getRequiredArgs()
optionalArgs = getOptionalArgs()
outputParser = parserCommon.output()
parser = argparse.ArgumentParser(
parents=[requiredArgs, outputParser, optionalArgs,
parentParser, normalizationParser, bamParser],
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description='This tool compares two BAM files based on the number of '
'mapped reads. To compare the BAM files, the genome is partitioned '
'into bins of equal size, then the number of reads found in each bin'
' is counted per file, and finally a summary value is '
'reported. This value can be the ratio of the number of reads per '
'bin, the log2 of the ratio, or the difference. This tool can '
'normalize the number of reads in each BAM file using the SES method '
'proposed by Diaz et al. (2012) "Normalization, bias correction, and '
'peak calling for ChIP-seq". Statistical Applications in Genetics '
'and Molecular Biology, 11(3). Normalization based on read counts '
'is also available. The output is either a bedgraph or bigWig file '
'containing the bin location and the resulting comparison value. '
'Note that *each end* in a pair (for paired-end reads) is treated '
'independently. If this is undesirable, then use the --samFlagInclude '
'or --samFlagExclude options.',
usage=' bamCompare -b1 treatment.bam -b2 control.bam -o log2ratio.bw',
add_help=False)
return parser
def parse_arguments(args=None):
parentParser = parserCommon.getParentArgParse()
outputParser = parserCommon.output()
parser = argparse.ArgumentParser(
parents=[parentParser, outputParser],
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description='This tool compares two bigWig files based on the number '
'of mapped reads. To compare the bigWig files, the genome is '
'partitioned into bins of equal size, then the number of reads found '
'in each BAM file are counted per bin and finally a summary '
'value is reported. This value can be the ratio of the number of reads'
'per bin, the log2 of the ratio, the sum or the difference.')
# define the arguments
parser.add_argument('--bigwig1',
'-b1',
metavar='Bigwig file',
help='Bigwig file 1. Usually the file for the '
'treatment.',
required=True)
parser.add_argument('--bigwig2',
'-b2',
metavar='Bigwig file',
help='Bigwig file 2. Usually the file for the '
'control.',
required=True)
parser.add_argument('--scaleFactors',
help='Set this parameter to multipy the bigwig values '
'by a constant. The format is '
'scaleFactor1:scaleFactor2. '
'For example 0.7:1 to scale the first bigwig file '
'by 0.7 while not scaling the second bigwig file',
default=None,
required=False)
parser.add_argument('--pseudocount',
help='small number to avoid x/0. Only useful '
'when ratio = log2 or ratio',
default=1,
type=float,
required=False)
parser.add_argument(
'--ratio',
help='The default is to compute the log2(ratio) '
'between the two samples. The reciprocal '
'ratio returns the '
'the negative of the inverse of the ratio '
'if the ratio is less than 0. The resulting '
'values are interpreted as negative fold changes. '
'Other possible operations are : simple ratio, '
'subtraction, sum',
default='log2',
choices=['log2', 'ratio', 'subtract', 'add', 'reciprocal_ratio'],
required=False)
parser.add_argument(
'--skipNonCoveredRegions',
'--skipNAs',
help=
'This parameter determines if non-covered regions (regions without a score) '
'in the bigWig files should be skipped. The default is to treat those '
'regions as having a value of zero. '
'The decision to skip non-covered regions '
'depends on the interpretation of the data. Non-covered regions '
'in a bigWig file may represent repetitive regions that should '
'be skipped. Alternatively, the interpretation of non-covered regions as '
'zeros may be wrong and this option should be used ',
action='store_true')
return parser
def parse_arguments(args=None):
parentParser = parserCommon.getParentArgParse()
outputParser = parserCommon.output()
dbParser = parserCommon.deepBlueOptionalArgs()
parser = argparse.ArgumentParser(
parents=[parentParser, outputParser, dbParser],
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description='This tool compares two bigWig files based on the number '
'of mapped reads. To compare the bigWig files, the genome is '
'partitioned into bins of equal size, then the number of reads found '
'in each BAM file are counted per bin and finally a summary '
'value is reported. This value can be the ratio of the number of reads'
'per bin, the log2 of the ratio, the sum or the difference.')
# define the arguments
parser.add_argument('--bigwig1', '-b1',
metavar='Bigwig file',
help='Bigwig file 1. Usually the file for the '
'treatment.',
required=True)
parser.add_argument('--bigwig2', '-b2',
metavar='Bigwig file',
help='Bigwig file 2. Usually the file for the '
'control.',
required=True)
parser.add_argument('--scaleFactors',
help='Set this parameter to multipy the bigwig values '
'by a constant. The format is '
'scaleFactor1:scaleFactor2. '
'For example 0.7:1 to scale the first bigwig file '
'by 0.7 while not scaling the second bigwig file',
default=None,
required=False)
parser.add_argument('--pseudocount',
help='small number to avoid x/0. Only useful '
'when ratio = log2 or ratio',
default=1,
type=float,
required=False)
parser.add_argument('--ratio',
help='The default is to output the log2ratio of the '
'two samples. The reciprocal ratio returns the '
'the negative of the inverse of the ratio '
'if the ratio is less than 0. The resulting '
'values are interpreted as negative fold changes. '
'*NOTE*: Only with --ratio subtract can --normalizeTo1x or '
'--normalizeUsingRPKM be used. Instead of performing a '
'computation using both files, the scaled signal can '
'alternatively be output for the first or second file using '
'the \'--ratio first\' or \'--ratio second\'',
default='log2',
choices=['log2', 'ratio', 'subtract', 'add', 'mean',
'reciprocal_ratio', 'first', 'second'],
required=False)
parser.add_argument('--skipNonCoveredRegions', '--skipNAs',
help='This parameter determines if non-covered regions (regions without a score) '
'in the bigWig files should be skipped. The default is to treat those '
'regions as having a value of zero. '
'The decision to skip non-covered regions '
'depends on the interpretation of the data. Non-covered regions '
'in a bigWig file may represent repetitive regions that should '
'be skipped. Alternatively, the interpretation of non-covered regions as '
'zeros may be wrong and this option should be used ',
action='store_true')
return parser
def parse_arguments(args=None):
parentParser = parserCommon.getParentArgParse()
outputParser = parserCommon.output()
dbParser = parserCommon.deepBlueOptionalArgs()
parser = argparse.ArgumentParser(
parents=[parentParser, outputParser, dbParser],
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description='This tool compares two bigWig files based on the number '
'of mapped reads. To compare the bigWig files, the genome is '
'partitioned into bins of equal size, then the number of reads found '
'in each BAM file are counted per bin and finally a summary '
'value is reported. This value can be the ratio of the number of reads'
'per bin, the log2 of the ratio, the sum or the difference.')
# define the arguments
parser.add_argument('--bigwig1',
'-b1',
metavar='Bigwig file',
help='Bigwig file 1. Usually the file for the '
'treatment.',
required=True)
parser.add_argument('--bigwig2',
'-b2',
metavar='Bigwig file',
help='Bigwig file 2. Usually the file for the '
'control.',
required=True)
parser.add_argument('--scaleFactors',
help='Set this parameter to multipy the bigwig values '
'by a constant. The format is '
'scaleFactor1:scaleFactor2. '
'For example 0.7:1 to scale the first bigwig file '
'by 0.7 while not scaling the second bigwig file',
default=None,
required=False)
parser.add_argument(
'--pseudocount',
help='A small number to avoid x/0. Only useful '
'together with --operation log2 or --operation ratio. '
'You can specify different values as pseudocounts for '
'the numerator and the denominator by providing two '
'values (the first value is used as the numerator '
'pseudocount and the second the denominator pseudocount). (Default: %(default)s)',
default=1,
nargs='+',
action=parserCommon.requiredLength(1, 2),
type=float,
required=False)
parser.add_argument('--skipZeroOverZero',
help='Skip bins where BOTH BAM files lack coverage. '
'This is determined BEFORE any applicable pseudocount '
'is added.',
action='store_true')
parser.add_argument(
'--operation',
help='The default is to output the log2ratio of the '
'two samples. The reciprocal ratio returns the '
'the negative of the inverse of the ratio '
'if the ratio is less than 0. The resulting '
'values are interpreted as negative fold changes. '
'Instead of performing a '
'computation using both files, the scaled signal can '
'alternatively be output for the first or second file using '
'the \'--operation first\' or \'--operation second\' (Default: %(default)s)',
default='log2',
choices=[
'log2', 'ratio', 'subtract', 'add', 'mean', 'reciprocal_ratio',
'first', 'second'
],
required=False)
parser.add_argument(
'--skipNonCoveredRegions',
'--skipNAs',
help=
'This parameter determines if non-covered regions (regions without a score) '
'in the bigWig files should be skipped. The default is to treat those '
'regions as having a value of zero. '
'The decision to skip non-covered regions '
'depends on the interpretation of the data. Non-covered regions '
'in a bigWig file may represent repetitive regions that should '
'be skipped. Alternatively, the interpretation of non-covered regions as '
'zeros may be wrong and this option should be used ',
action='store_true')
return parser
