def add_tfbscan_arguments(parser):
parser.formatter_class = lambda prog: argparse.RawDescriptionHelpFormatter(prog, max_help_position=35, width=90)
description = "Find positions of Transcription Factor Binding Sites (TFBS) in FASTA sequences by scanning with motifs.\n\n"
description += "Usage:\nTOBIAS TFBScan --motifs <motifs.txt> --fasta <genome.fa> \n\n"
description += "By setting --outdir, the output files are:\n- <outdir>/<TF1>.bed\n- <outdir>/<TF2>.bed\n- (...)\n\n"
description += "By setting --outfile, all TFBS are written to one file (with motif specified in the 4th column of the .bed)."
parser.description = format_help_description("TFBScan", description)
parser._action_groups.pop() #pop -h
required_arguments = parser.add_argument_group('Required arguments')
required_arguments.add_argument('-m', '--motifs', metavar="", help='File containing motifs in either MEME, PFM or JASPAR format')
required_arguments.add_argument('-f', '--fasta', metavar="", help='A fasta file of sequences to use for scanning motifs') # whole genome file or regions of interest in FASTA format to be scanned with motifs')
#all other arguments are optional
optional_arguments = parser.add_argument_group('Optional arguments')
optional_arguments.add_argument('-r', '--regions', metavar="", help='Subset scanning to regions of interest')
optional_arguments.add_argument('--outdir', metavar="", help='Output directory for TFBS sites in one file per motif (default: ./tfbscan_output/). NOTE: Select either --outdir or --outfile.', default=None)
optional_arguments.add_argument('--outfile', metavar="", help='Output file for TFBS sites joined in one bed-file (default: not set). NOTE: Select either --outdir or --outfile.', default=None)
optional_arguments.add_argument('--naming', metavar="", help="Naming convention for bed-ids and output files ('id', 'name', 'name_id', 'id_name') (default: 'name_id')", choices=["id", "name", "name_id", "id_name"], default="name_id")
optional_arguments.add_argument('--gc', metavar="", type=lambda x: restricted_float(x,0,1), help='Set the gc content for background regions (default: will be estimated from fasta)')
optional_arguments.add_argument('--pvalue', metavar="", type=lambda x: restricted_float(x,0,1), help='Set p-value for motif matches (default: 0.0001)', default=0.0001)
optional_arguments.add_argument('--keep-overlaps', action='store_true', help='Keep overlaps of same motifs (default: overlaps are resolved by keeping best-scoring site)')
optional_arguments.add_argument('--add-region-columns', action='store_true', help="Add extra information columns (starting from 4th column) from --regions to the output .bed-file(s) (default: off)")
RUN = parser.add_argument_group('Run arguments')
RUN.add_argument('--split', metavar="<int>", type=int, help="Split of multiprocessing jobs (default: 100)", default=100)
RUN.add_argument('--cores', metavar="", type=int, help='Number of cores to use (default: 1)', default=1)
RUN.add_argument('--debug', action="store_true", help=argparse.SUPPRESS)
RUN = add_logger_args(optional_arguments)
return(parser)
def add_bindetect_arguments(parser):
parser.formatter_class = lambda prog: argparse.RawDescriptionHelpFormatter(prog, max_help_position=35, width=90)
description = "BINDetect takes motifs, signals (footprints) and genome as input to estimate bound transcription factor binding sites and differential binding between conditions. "
description += "The underlying method is a modified motif enrichment test to see which motifs have the largest differences in signal across input conditions. "
description += "The output is an in-depth overview of global changes as well as the individual binding site signal-differences.\n\n"
description += "Usage:\nTOBIAS BINDetect --signals <bigwig1> (<bigwig2> (...)) --motifs <motifs.txt> --genome <genome.fasta> --peaks <peaks.bed>\n\n"
description += "Output files:\n- <outdir>/<prefix>_figures.pdf\n- <outdir>/<prefix>_results.{txt,xlsx}\n- <outdir>/<prefix>_distances.txt\n"
description += "- <outdir>/<TF>/<TF>_overview.{txt,xlsx} (per motif)\n- <outdir>/<TF>/beds/<TF>_all.bed (per motif)\n"
description += "- <outdir>/<TF>/beds/<TF>_<condition>_bound.bed (per motif-condition pair)\n- <outdir>/<TF>/beds/<TF>_<condition>_unbound.bed (per motif-condition pair)\n\n"
parser.description = format_help_description("BINDetect", description)
parser._action_groups.pop() #pop -h
required = parser.add_argument_group('Required arguments')
required.add_argument('--signals', metavar="<bigwig>", help="Signal per condition (.bigwig format)", nargs="*")
required.add_argument('--peaks', metavar="<bed>", help="Peaks.bed containing open chromatin regions across all conditions")
required.add_argument('--motifs', metavar="<motifs>", help="Motif file(s) in pfm/jaspar/meme format", nargs="*")
required.add_argument('--genome', metavar="<fasta>", help="Genome .fasta file")
optargs = parser.add_argument_group('Optional arguments')
optargs.add_argument('--cond-names', metavar="<name>", nargs="*", help="Names of conditions fitting to --signals (default: prefix of --signals)")
optargs.add_argument('--peak-header', metavar="<file>", help="File containing the header of --peaks separated by whitespace or newlines (default: peak columns are named \"_additional_<count>\")")
optargs.add_argument('--naming', metavar="<string>", help="Naming convention for TF output files ('id', 'name', 'name_id', 'id_name') (default: 'name_id')", choices=["id", "name", "name_id", "id_name"], default="name_id")
optargs.add_argument('--motif-pvalue', metavar="<float>", type=lambda x: restricted_float(x, 0, 1), help="Set p-value threshold for motif scanning (default: 1e-4)", default=0.0001)
optargs.add_argument('--bound-pvalue', metavar="<float>", type=lambda x: restricted_float(x, 0, 1), help="Set p-value threshold for bound/unbound split (default: 0.001)", default=0.001)
#optargs.add_argument('--volcano-diff-thresh', metavar="<float>", help="", default=0.2) #not yet implemented
#optargs.add_argument('--volcano-p-thresh', metavar="<float>", help="", default=0.05) #not yet implemented
optargs.add_argument('--pseudo', type=float, metavar="<float>", help="Pseudocount for calculating log2fcs (default: estimated from data)", default=None)
optargs.add_argument('--time-series', action='store_true', help="Will only compare signals1<->signals2<->signals3 (...) in order of input, and skip all-against-all comparison.")
optargs.add_argument('--skip-excel', action='store_true', help="Skip creation of excel files - for large datasets, this will speed up BINDetect considerably")
runargs = parser.add_argument_group("Run arguments")
runargs.add_argument('--outdir', metavar="<directory>", help="Output directory to place TFBS/plots in (default: bindetect_output)", default="bindetect_output")
optargs.add_argument('--prefix', metavar="<prefix>", help="Prefix for overview files in --outdir folder (default: bindetect)", default="bindetect")
runargs.add_argument('--cores', metavar="<int>", type=int, help="Number of cores to use for computation (default: 1)", default=1)
runargs.add_argument('--split', metavar="<int>", type=int, help="Split of multiprocessing jobs (default: 100)", default=100)
runargs.add_argument('--debug', help=argparse.SUPPRESS, action='store_true')
runargs = add_logger_args(runargs)
return(parser)
def add_aggregate_arguments(parser):
parser.formatter_class = lambda prog: argparse.RawDescriptionHelpFormatter(
prog, max_help_position=40, width=90)
description = ""
parser.description = format_help_description("PlotAggregate", description)
parser._action_groups.pop() #pop -h
IO = parser.add_argument_group('Input / output arguments')
IO.add_argument('--TFBS',
metavar="<bed>",
nargs="*",
help="TFBS sites (*required)") #default is None
IO.add_argument(
'--signals',
metavar="<bigwig>",
nargs="*",
help="Signals in bigwig format (*required)") #default is None
IO.add_argument('--regions',
metavar="<bed>",
nargs="*",
help="Regions to overlap with TFBS (optional)",
default=[])
IO.add_argument('--whitelist',
metavar="<bed>",
nargs="*",
help="Only plot sites overlapping whitelist (optional)",
default=[])
IO.add_argument('--blacklist',
metavar="<bed>",
nargs="*",
help="Exclude sites overlapping blacklist (optional)",
default=[])
IO.add_argument('--output',
metavar="",
help="Path to output plot (default: TOBIAS_aggregate.pdf)",
default="TOBIAS_aggregate.pdf")
IO.add_argument(
'--output-txt',
metavar="",
help="Path to output file for aggregates in .txt-format (default: None)"
)
PLOT = parser.add_argument_group('Plot arguments')
PLOT.add_argument('--title',
metavar="",
help="Title of plot (default: \"Aggregated signals\")",
default="Aggregated signals")
PLOT.add_argument(
'--flank',
metavar="",
help=
"Flanking basepairs (+/-) to show in plot (counted from middle of the TFBS) (default: 60)",
default=60,
type=int)
PLOT.add_argument(
'--TFBS-labels',
metavar="",
help="Labels used for each TFBS file (default: prefix of each --TFBS)",
nargs="*")
PLOT.add_argument(
'--signal-labels',
metavar="",
help=
"Labels used for each signal file (default: prefix of each --signals)",
nargs="*")
PLOT.add_argument(
'--region-labels',
metavar="",
help=
"Labels used for each regions file (default: prefix of each --regions)",
nargs="*")
PLOT.add_argument(
'--share-y',
metavar="",
help=
"Share y-axis range across plots (none/signals/sites/both). Use \"--share-y signals\" if bigwig signals have similar ranges. Use \"--share_y sites\" if sites per bigwig are comparable, but bigwigs themselves aren't comparable (default: none)",
choices=["none", "signals", "sites", "both"],
default="none")
#Signals / regions
PLOT.add_argument(
'--normalize',
action='store_true',
help=
"Normalize the aggregate signal(s) to be between 0-1 (default: the true range of values is shown)"
)
PLOT.add_argument('--negate',
action='store_true',
help="Negate overlap with regions")
PLOT.add_argument(
'--smooth',
metavar="<int>",
type=int,
help=
"Smooth output signal by taking the mean of <smooth> bp windows (default: 1 (no smooth)",
default=1)
PLOT.add_argument('--log-transform',
help="Log transform the signals before aggregation",
action="store_true")
PLOT.add_argument(
'--plot-boundaries',
help=
"Plot TFBS boundaries (Note: estimated from first region in each --TFBS)",
action='store_true')
PLOT.add_argument(
'--signal-on-x',
help=
"Show signals on x-axis and TFBSs on y-axis (default: signal is on y-axis)",
action='store_true')
PLOT.add_argument(
'--remove-outliers',
metavar="<float>",
help=
"Value between 0-1 indicating the percentile of regions to include, e.g. 0.99 to remove the sites with 1%% highest values (default: 1)",
type=lambda x: restricted_float(x, 0, 1),
default=1)
RUN = parser.add_argument_group("Run arguments")
RUN = add_logger_args(RUN)
return (parser)