/usr/bin/macs2 is in macs 2.1.1.20160309-2.
This file is owned by root:root, with mode 0o755.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 | #!/usr/bin/python
# Time-stamp: <2016-03-09 14:34:14 Tao Liu>
"""Description: MACS v2 main executable.
Copyright (c) 2008,2009 Yong Zhang, Tao Liu <taoliu@jimmy.harvard.edu>
Copyright (c) 2010,2011,2012,2013,2014,2015 Tao Liu <taoliu@jimmy.harvard.edu>
This code is free software; you can redistribute it and/or modify it
under the terms of the BSD License (see the file COPYING included with
the distribution).
@status: release candidate
@version: $Id$
@author: Yong Zhang, Tao Liu
@contact: taoliu@jimmy.harvard.edu
"""
# ------------------------------------
# python modules
# ------------------------------------
import os
import sys
import argparse as ap
import tempfile
# ------------------------------------
# own python modules
# ------------------------------------
from MACS2.Constants import *
# ------------------------------------
# Main function
# ------------------------------------
def main():
"""The Main function/pipeline for MACS.
"""
# Parse options...
argparser = prepare_argparser()
args = argparser.parse_args()
if args.outdir:
# use a output directory to store MACS output
if not os.path.exists( args.outdir ):
try:
os.makedirs( args.outdir )
except:
sys.exit( "Output directory (%s) could not be created. Terminating program." % args.outdir )
subcommand = args.subcommand_name
if subcommand == "callpeak":
# General call peak
from MACS2.callpeak_cmd import run
run( args )
#elif subcommand == "diffpeak":
# # differential peak calling w/ bedgraphs + optional peak regions
# from MACS2.diffpeak_cmd import run
# run( args )
elif subcommand == "bdgpeakcall":
# call peak from bedGraph
from MACS2.bdgpeakcall_cmd import run
run( args )
elif subcommand == "bdgbroadcall":
# call broad peak from bedGraph
from MACS2.bdgbroadcall_cmd import run
run( args )
elif subcommand == "bdgcmp":
# compare treatment and control to make enrichment scores
from MACS2.bdgcmp_cmd import run
run( args )
elif subcommand == "bdgopt":
# operations on the score column of bedGraph file
from MACS2.bdgopt_cmd import run
run( args )
elif subcommand == "cmbreps":
# combine replicates
from MACS2.cmbreps_cmd import run
run( args )
elif subcommand == "randsample":
# randomly sample sequencing reads, and save as bed file
from MACS2.randsample_cmd import run
run( args )
elif subcommand == "filterdup":
# filter out duplicate reads, and save as bed file
from MACS2.filterdup_cmd import run
run( args )
elif subcommand == "bdgdiff":
# differential calling
from MACS2.bdgdiff_cmd import run
run( args )
elif subcommand == "refinepeak":
# refine peak summits
from MACS2.refinepeak_cmd import run
run( args )
elif subcommand == "predictd":
# predict d or fragment size
from MACS2.predictd_cmd import run
run( args )
elif subcommand == "pileup":
# pileup alignment results with a given extension method
from MACS2.pileup_cmd import run
run( args )
def prepare_argparser ():
"""Prepare optparser object. New options will be added in this
function first.
"""
description = "%(prog)s -- Model-based Analysis for ChIP-Sequencing"
epilog = "For command line options of each command, type: %(prog)s COMMAND -h"
#Check community site: http://groups.google.com/group/macs-announcement/
#Source code: https://github.com/taoliu/MACS/"
# top-level parser
argparser = ap.ArgumentParser( description = description, epilog = epilog ) #, usage = usage )
argparser.add_argument("--version", action="version", version="%(prog)s "+MACS_VERSION)
subparsers = argparser.add_subparsers( dest = 'subcommand_name' ) #help="sub-command help")
# command for 'callpeak'
add_callpeak_parser( subparsers )
# # command for 'diffpeak'
# add_diffpeak_parser( subparsers )
# command for 'bdgpeakcall'
add_bdgpeakcall_parser( subparsers )
# command for 'bdgbroadcall'
add_bdgbroadcall_parser( subparsers )
# command for 'bdgcmp'
add_bdgcmp_parser( subparsers )
# command for 'bdgopt'
add_bdgopt_parser( subparsers )
# command for 'cmbreps'
add_cmbreps_parser( subparsers )
# command for 'bdgdiff'
add_bdgdiff_parser( subparsers )
# command for 'filterdup'
add_filterdup_parser( subparsers )
# command for 'predictd'
add_predictd_parser( subparsers )
# command for 'pileup'
add_pileup_parser( subparsers )
# command for 'randsample'
add_randsample_parser( subparsers )
# command for 'refinepeak'
add_refinepeak_parser( subparsers )
return argparser
def add_outdir_option ( parser ):
parser.add_argument("--outdir", dest = "outdir", type = str, default = '',
help = "If specified all output files will be written to that directory. Default: the current working directory")
def add_output_group ( parser, required = True ):
output_group = parser.add_mutually_exclusive_group( required = required )
output_group.add_argument( "-o", "--ofile", dest = "ofile", type = str,
help = "Output file name. Mutually exclusive with --o-prefix." )
output_group.add_argument( "--o-prefix", dest = "oprefix", type = str,
help = "Output file prefix. Mutually exclusive with -o/--ofile." )
def add_callpeak_parser( subparsers ):
"""Add main function 'peak calling' argument parsers.
"""
argparser_callpeak = subparsers.add_parser("callpeak", help="Main MACS2 Function: Call peaks from alignment results.")
# group for input files
group_input = argparser_callpeak.add_argument_group( "Input files arguments" )
group_input.add_argument( "-t", "--treatment", dest = "tfile", type = str, required = True, nargs = "+",
help = "ChIP-seq treatment file. If multiple files are given as '-t A B C', then they will all be read and pooled together. REQUIRED." )
group_input.add_argument( "-c", "--control", dest = "cfile", type = str, nargs = "*",
help = "Control file. If multiple files are given as '-c A B C', they will be pooled to estimate ChIP-seq background noise.")
group_input.add_argument( "-f", "--format", dest = "format", type = str,
choices = ("AUTO", "BAM", "SAM", "BED", "ELAND",
"ELANDMULTI", "ELANDEXPORT", "BOWTIE",
"BAMPE", "BEDPE"),
help = "Format of tag file, \"AUTO\", \"BED\" or \"ELAND\" or \"ELANDMULTI\" or \"ELANDEXPORT\" or \"SAM\" or \"BAM\" or \"BOWTIE\" or \"BAMPE\" or \"BEDPE\". The default AUTO option will let MACS decide which format (except for BAMPE and BEDPE which should be implicitly set) the file is. Please check the definition in README. Please note that if the format is set as BAMPE or BEDPE, MACS2 will call its special Paired-end mode to call peaks by piling up the actual ChIPed fragments defined by both aligned ends, instead of predicting the fragment size first and extending reads. Also please note that the BEDPE only contains three columns, and is NOT the same BEDPE format used by BEDTOOLS. DEFAULT: \"AUTO\"",
default = "AUTO" )
group_input.add_argument( "-g", "--gsize", dest = "gsize", type = str, default = "hs",
help = "Effective genome size. It can be 1.0e+9 or 1000000000, or shortcuts:'hs' for human (2.7e9), 'mm' for mouse (1.87e9), 'ce' for C. elegans (9e7) and 'dm' for fruitfly (1.2e8), Default:hs" )
group_input.add_argument( "--keep-dup", dest = "keepduplicates", type = str, default = "1",
help = "It controls the MACS behavior towards duplicate tags at the exact same location -- the same coordination and the same strand. The 'auto' option makes MACS calculate the maximum tags at the exact same location based on binomal distribution using 1e-5 as pvalue cutoff; and the 'all' option keeps every tags. If an integer is given, at most this number of tags will be kept at the same location. Note, if you've used samtools or picard to flag reads as 'PCR/Optical duplicate' in bit 1024, MACS2 will still read them although the reads may be decided by MACS2 as duplicate later. The default is to keep one tag at the same location. Default: 1" )
group_input.add_argument( "--buffer-size", dest = "buffer_size", type = int, default = "100000",
help = "Buffer size for incrementally increasing internal array size to store reads alignment information. In most cases, you don't have to change this parameter. However, if there are large number of chromosomes/contigs/scaffolds in your alignment, it's recommended to specify a smaller buffer size in order to decrease memory usage (but it will take longer time to read alignment files). Minimum memory requested for reading an alignment file is about # of CHROMOSOME * BUFFER_SIZE * 2 Bytes. DEFAULT: 100000 " )
# group for output files
group_output = argparser_callpeak.add_argument_group( "Output arguments" )
add_outdir_option( group_output )
group_output.add_argument( "-n", "--name", dest = "name", type = str,
help = "Experiment name, which will be used to generate output file names. DEFAULT: \"NA\"",
default = "NA" )
group_output.add_argument( "-B", "--bdg", dest = "store_bdg", action = "store_true",
help = "Whether or not to save extended fragment pileup, and local lambda tracks (two files) at every bp into a bedGraph file. DEFAULT: False",
default = False )
group_output.add_argument( "--verbose", dest = "verbose", type = int, default = 2,
help = "Set verbose level of runtime message. 0: only show critical message, 1: show additional warning message, 2: show process information, 3: show debug messages. DEFAULT:2" )
group_output.add_argument( "--trackline", dest="trackline", action="store_true", default = False,
help = "Tells MACS to include trackline with bedGraph files. To include this trackline while displaying bedGraph at UCSC genome browser, can show name and description of the file as well. However my suggestion is to convert bedGraph to bigWig, then show the smaller and faster binary bigWig file at UCSC genome browser, as well as downstream analysis. Require -B to be set. Default: Not include trackline." )
group_output.add_argument( "--SPMR", dest = "do_SPMR", action = "store_true", default = False,
help = "If True, MACS will save signal per million reads for fragment pileup profiles. Require -B to be set. Default: False" )
# group for bimodal
group_bimodal = argparser_callpeak.add_argument_group( "Shifting model arguments" )
group_bimodal.add_argument( "-s", "--tsize", dest = "tsize", type = int, default = None,
help = "Tag size. This will override the auto detected tag size. DEFAULT: Not set")
group_bimodal.add_argument( "--bw", dest = "bw", type = int, default = 300,
help = "Band width for picking regions to compute fragment size. This value is only used while building the shifting model. DEFAULT: 300")
group_bimodal.add_argument( "-m", "--mfold", dest = "mfold", type = int, default = [5,50], nargs = 2,
help = "Select the regions within MFOLD range of high-confidence enrichment ratio against background to build model. Fold-enrichment in regions must be lower than upper limit, and higher than the lower limit. Use as \"-m 10 30\". DEFAULT:5 50" )
group_bimodal.add_argument( "--fix-bimodal", dest = "onauto", action = "store_true",
help = "Whether turn on the auto pair model process. If set, when MACS failed to build paired model, it will use the nomodel settings, the --exsize parameter to extend each tags towards 3' direction. Not to use this automate fixation is a default behavior now. DEFAULT: False",
default = False )
group_bimodal.add_argument( "--nomodel", dest = "nomodel", action = "store_true",
help = "Whether or not to build the shifting model. If True, MACS will not build model. by default it means shifting size = 100, try to set extsize to change it. DEFAULT: False",
default = False )
group_bimodal.add_argument( "--shift", dest = "shift", type = int, default = 0,
help = "(NOT the legacy --shiftsize option!) The arbitrary shift in bp. Use discretion while setting it other than default value. When NOMODEL is set, MACS will use this value to move cutting ends (5') towards 5'->3' direction then apply EXTSIZE to extend them to fragments. When this value is negative, ends will be moved toward 3'->5' direction. Recommended to keep it as default 0 for ChIP-Seq datasets, or -1 * half of EXTSIZE together with EXTSIZE option for detecting enriched cutting loci such as certain DNAseI-Seq datasets. Note, you can't set values other than 0 if format is BAMPE or BEDPE for paired-end data. DEFAULT: 0. " )
group_bimodal.add_argument( "--extsize", dest = "extsize", type = int, default = 200,
help = "The arbitrary extension size in bp. When nomodel is true, MACS will use this value as fragment size to extend each read towards 3' end, then pile them up. It's exactly twice the number of obsolete SHIFTSIZE. In previous language, each read is moved 5'->3' direction to middle of fragment by 1/2 d, then extended to both direction with 1/2 d. This is equivalent to say each read is extended towards 5'->3' into a d size fragment. DEFAULT: 200. EXTSIZE and SHIFT can be combined when necessary. Check SHIFT option." )
# The next two options are obsolete. To compare two conditions, using bdgcmp.
#group_bimodal.add_argument( "--control-as-ChIP", dest = "controlasChIP", action = "store_true", default = False,
# help = "When set, control tags will be shifted and extended using SHIFT and EXTSIZE options just as ChIP tags according to their strand before the extension of d, slocal and llocal. By default, control tags are extended centered at their current positions regardless of strand. You may consider to turn this option on while comparing two ChIP datasets of different condition but the same factor. DEFAULT: False" )
#group_bimodal.add_argument( "--half-ext", dest = "halfext", action = "store_true", default = False,
# help = "When set, MACS extends 1/2 d size for each fragment centered at its middle point. DEFAULT: False" )
# General options.
group_callpeak = argparser_callpeak.add_argument_group( "Peak calling arguments" )
p_or_q_group = group_callpeak.add_mutually_exclusive_group()
p_or_q_group.add_argument( "-q", "--qvalue", dest = "qvalue", type = float, default = 0.05,
help = "Minimum FDR (q-value) cutoff for peak detection. DEFAULT: 0.05. -q, and -p are mutually exclusive." )
p_or_q_group.add_argument( "-p", "--pvalue", dest = "pvalue", type = float,
help = "Pvalue cutoff for peak detection. DEFAULT: not set. -q, and -p are mutually exclusive. If pvalue cutoff is set, qvalue will not be calculated and reported as -1 in the final .xls file." )
#p_or_q_group.add_argument( "-F", "--foldenrichment", dest = "foldenrichment", type = float,
# help = "Foldenrichment cutoff for peak detection. DEFAULT: not set. -q, -p and -F are mutually exclusive. If pvalue cutoff is set, qvalue will not be calculated and reported as -1 in the final .xls file." )
# about scaling
group_callpeak.add_argument( "--to-large", dest = "tolarge", action = "store_true", default = False,
help = "When set, scale the small sample up to the bigger sample. By default, the bigger dataset will be scaled down towards the smaller dataset, which will lead to smaller p/qvalues and more specific results. Keep in mind that scaling down will bring down background noise more. DEFAULT: False" )
group_callpeak.add_argument( "--ratio", dest = "ratio", type = float, default = 1.0,
help = "When set, use a custom scaling ratio of ChIP/control (e.g. calculated using NCIS) for linear scaling. DEFAULT: ingore" )
group_callpeak.add_argument( "--down-sample", dest = "downsample", action = "store_true", default = False,
help = "When set, random sampling method will scale down the bigger sample. By default, MACS uses linear scaling. Warning: This option will make your result unstable and irreproducible since each time, random reads would be selected. Consider to use 'randsample' script instead. <not implmented>If used together with --SPMR, 1 million unique reads will be randomly picked.</not implemented> Caution: due to the implementation, the final number of selected reads may not be as you expected! DEFAULT: False" )
group_callpeak.add_argument( "--seed", dest = "seed", type = int, default = -1,
help = "Set the random seed while down sampling data. Must be a non-negative integer in order to be effective. DEFAULT: not set" )
group_callpeak.add_argument( "--tempdir", dest="tempdir", default=tempfile.gettempdir(),
help = "Optional directory to store temp files. DEFAULT: %(default)s")
group_callpeak.add_argument( "--nolambda", dest = "nolambda", action = "store_true",
help = "If True, MACS will use fixed background lambda as local lambda for every peak region. Normally, MACS calculates a dynamic local lambda to reflect the local bias due to potential chromatin structure. ",
default = False )
group_callpeak.add_argument( "--slocal", dest = "smalllocal", type = int, default = 1000,
help = "The small nearby region in basepairs to calculate dynamic lambda. This is used to capture the bias near the peak summit region. Invalid if there is no control data. If you set this to 0, MACS will skip slocal lambda calculation. *Note* that MACS will always perform a d-size local lambda calculation. The final local bias should be the maximum of the lambda value from d, slocal, and llocal size windows. DEFAULT: 1000 " )
group_callpeak.add_argument( "--llocal", dest = "largelocal", type = int, default = 10000,
help = "The large nearby region in basepairs to calculate dynamic lambda. This is used to capture the surround bias. If you set this to 0, MACS will skip llocal lambda calculation. *Note* that MACS will always perform a d-size local lambda calculation. The final local bias should be the maximum of the lambda value from d, slocal, and llocal size windows. DEFAULT: 10000." )
group_callpeak.add_argument( "--broad", dest = "broad", action = "store_true",
help = "If set, MACS will try to call broad peaks by linking nearby highly enriched regions. The linking region is controlled by another cutoff through --linking-cutoff. The maximum linking region length is 4 times of d from MACS. DEFAULT: False", default = False )
group_callpeak.add_argument( "--broad-cutoff", dest = "broadcutoff", type = float, default = 0.1,
help = "Cutoff for broad region. This option is not available unless --broad is set. If -p is set, this is a pvalue cutoff, otherwise, it's a qvalue cutoff. DEFAULT: 0.1 " )
group_callpeak.add_argument( "--cutoff-analysis", dest="cutoff_analysis", action="store_true",
help = "While set, MACS2 will analyze number or total length of peaks that can be called by different p-value cutoff then output a summary table to help user decide a better cutoff. The table will be saved in NAME_cutoff_analysis.txt file. Note, minlen and maxgap may affect the results. WARNING: May take ~30 folds longer time to finish. DEFAULT: False", default = False )
group_postprocessing = argparser_callpeak.add_argument_group( "Post-processing options" )
postprocess_group = group_postprocessing.add_mutually_exclusive_group()
postprocess_group.add_argument( "--call-summits", dest="call_summits", action="store_true",
help="If set, MACS will use a more sophisticated signal processing approach to find subpeak summits in each enriched peak region. DEFAULT: False",default=False)
# postprocess_group.add_argument( "--refine-peaks", dest="refine_peaks", action="store_true",
# help="If set, MACS will refine peak summits by measuring balance of waston/crick tags. Those peaks without balancing tags will be disgarded. Peak summits will be redefined and reassgined with scores. Note, duplicate reads will be put back while calculating read balance. And more memory will be used. Default: False", default=False )
group_postprocessing.add_argument( "--fe-cutoff", dest="fecutoff", type=float, default = 1.0,
help = "When set, the value will be used to filter out peaks with low fold-enrichment. Note, MACS2 use 1.0 as pseudocount while calculating fold-enrichment. DEFAULT: 1.0")
return
def add_diffpeak_parser( subparsers ):
"""Add main function 'peak calling' argument parsers.
"""
argparser_diffpeak = subparsers.add_parser("diffpeak", help="MACS2 Differential Peak Function: Call peaks from bedgraphs (or use optional peak regions) and determine peaks of differential occupancy")
# group for input files
group_input = argparser_diffpeak.add_argument_group( "Input files arguments" )
group_input.add_argument( "--t1", dest = "t1bdg", type = str, required = True,
help = "MACS pileup bedGraph for condition 1. REQUIRED" )
group_input.add_argument( "--t2", dest="t2bdg", type = str, required = True,
help = "MACS pileup bedGraph for condition 2. REQUIRED" )
group_input.add_argument( "--c1", dest = "c1bdg", type = str, required = True,
help = "MACS control lambda bedGraph for condition 1. REQUIRED" )
group_input.add_argument( "--c2", dest="c2bdg", type = str, required = True,
help = "MACS control lambda bedGraph for condition 2. REQUIRED" )
group_input.add_argument( "--peaks1", dest = "peaks1", type = str, default='',
help = "MACS peaks.xls file for condition 1. Optional but must specify peaks2 if present" )
group_input.add_argument( "--peaks2", dest="peaks2", type = str, default='',
help = "MACS peaks.xls file for condition 2. Optional but must specify peaks1 if present" )
group_input.add_argument( "-d", "--depth-multiplier", dest = "depth", type = float, default = [1.0], nargs = "+",
help = "Sequence depth in million reads. If two depths are different, use '-d X -d Y' for X million reads in condition 1 and Y million reads in condition 2. If they are same, use '-d X' for X million reads in both condition 1 and condition 2 (e.g. the bedGraph files are from 'callpeak --SPMR'). Default: 1 (if you use 'macs2 callpeak --SPMR' to generate bdg files, we recommend using the smaller depth as a multiplier)" )
# group_input.add_argument( "-f", "--format", dest = "format", type = str,
# choices = ("AUTO", "BED", "XLS"),
# help = "Format of peak regions file, \"AUTO\", \"BED\" or \"XLS\". The default AUTO option will let MACS decide which format the file is based on the file extension. DEFAULT: \"AUTO\"",
# default = "AUTO" )
# group for output files
group_output = argparser_diffpeak.add_argument_group( "Output arguments" )
add_outdir_option( group_output )
group_output.add_argument( "-n", "--name", dest = "name", type = str,
help = "Experiment name, which will be used to generate output file names. DEFAULT: \"diffpeak\"",
default = "diffpeak" )
group_output.add_argument( "-B", "--bdg", dest = "store_bdg", action = "store_true",
help = "Whether or not to save basewise p/qvalues from every peak region into a bedGraph file. DEFAULT: False",
default = False )
group_output.add_argument( "--verbose", dest = "verbose", type = int, default = 2,
help = "Set verbose level of runtime message. 0: only show critical message, 1: show additional warning message, 2: show process information, 3: show debug messages. DEFAULT:2" )
group_output.add_argument( "--trackline", dest="trackline", action="store_true", default = False,
help = "Tells MACS to include trackline with bedGraph files. To include this trackline while displaying bedGraph at UCSC genome browser, can show name and description of the file as well. However my suggestion is to convert bedGraph to bigWig, then show the smaller and faster binary bigWig file at UCSC genome browser, as well as downstream analysis. Require -B to be set. Default: Not include trackline." )
# General options.
group_diffpeak = argparser_diffpeak.add_argument_group( "Peak calling arguments" )
p_or_q_group = group_diffpeak.add_mutually_exclusive_group()
p_or_q_group.add_argument( "-q", "--qvalue", dest = "diff_qvalue", type = float, default = 0.05,
help = "Minimum FDR (q-value) cutoff for differences. DEFAULT: 0.05. -q and -p are mutually exclusive." )
p_or_q_group.add_argument( "-p", "--pvalue", dest = "diff_pvalue", type = float,
help = "Pvalue cutoff for differences. DEFAULT: not set. -q and -p are mutually exclusive." )
p_or_q_group2 = group_diffpeak.add_mutually_exclusive_group()
p_or_q_group2.add_argument( "--peaks-qvalue", dest = "peaks_qvalue", type = float, default = 0.05,
help = "Minimum FDR (q-value) cutoff for peak detection. DEFAULT: 0.05. --peaks-qvalue and --peaks-pvalue are mutually exclusive." )
p_or_q_group2.add_argument( "--peaks-pvalue", dest = "peaks_pvalue", type = float,
help = "Pvalue cutoff for peak detection. DEFAULT: not set. --peaks-qvalue and --peaks-pvalue are mutually exclusive." )
group_diffpeak.add_argument( "-m", "--peak-min-len", dest = "pminlen", type = int,
help = "Minimum length of peak regions. DEFAULT: 200", default = 200 )
group_diffpeak.add_argument( "--diff-min-len", dest = "dminlen", type = int,
help = "Minimum length of differential region (must overlap a valid peak). DEFAULT: 50", default = 100 )
group_diffpeak.add_argument( "--ignore-duplicate-peaks", dest="ignore_duplicate_peaks", action="store_false",
help="If set, MACS will ignore duplicate regions with identical coordinates. Helpful if --call-summits was set. DEFAULT: True",default=True)
return
def add_filterdup_parser( subparsers ):
argparser_filterdup = subparsers.add_parser( "filterdup",
help = "Remove duplicate reads at the same position, then convert acceptable format to BED format." )
argparser_filterdup.add_argument( "-i", "--ifile", dest = "ifile", type = str, required = True, nargs = "+",
help = "ChIP-seq alignment file. If multiple files are given as '-t A B C', then they will all be read and combined. Note that pair-end data is not supposed to work with this command. REQUIRED." )
argparser_filterdup.add_argument( "-f", "--format", dest = "format", type = str,
choices=("AUTO","BAM","SAM","BED","ELAND","ELANDMULTI","ELANDEXPORT","BOWTIE"),
help = "Format of tag file, \"AUTO\", \"BED\" or \"ELAND\" or \"ELANDMULTI\" or \"ELANDEXPORT\" or \"SAM\" or \"BAM\" or \"BOWTIE\". The default AUTO option will let '%(prog)s' decide which format the file is. Please check the definition in README file if you choose ELAND/ELANDMULTI/ELANDEXPORT/SAM/BAM/BOWTIE. DEFAULT: \"AUTO\"",
default = "AUTO" )
argparser_filterdup.add_argument( "-g", "--gsize", dest = "gsize", type = str, default = "hs",
help = "Effective genome size. It can be 1.0e+9 or 1000000000, or shortcuts:'hs' for human (2.7e9), 'mm' for mouse (1.87e9), 'ce' for C. elegans (9e7) and 'dm' for fruitfly (1.2e8), DEFAULT:hs" )
argparser_filterdup.add_argument( "-s", "--tsize", dest = "tsize", type = int,
help = "Tag size. This will override the auto detected tag size. DEFAULT: Not set" )
argparser_filterdup.add_argument( "-p", "--pvalue", dest = "pvalue", type = float,
help = "Pvalue cutoff for binomial distribution test. DEFAULT:1e-5" )
argparser_filterdup.add_argument( "--keep-dup", dest = "keepduplicates", type = str, default = "auto",
help = "It controls the '%(prog)s' behavior towards duplicate tags/pairs at the exact same location -- the same coordination and the same strand. The 'auto' option makes '%(prog)s' calculate the maximum tags at the exact same location based on binomal distribution using given -p as pvalue cutoff; and the 'all' option keeps every tags (useful if you only want to convert formats). If an integer is given, at most this number of tags will be kept at the same location. Note, MACS2 callpeak function uses KEEPDUPLICATES=1 as default. Note, if you've used samtools or picard to flag reads as 'PCR/Optical duplicate' in bit 1024, MACS2 will still read them although the reads may be decided by MACS2 as duplicate later. Default: auto" )
argparser_filterdup.add_argument( "--verbose", dest = "verbose", type = int, default = 2,
help = "Set verbose level. 0: only show critical message, 1: show additional warning message, 2: show process information, 3: show debug messages. If you want to know where are the duplicate reads, use 3. DEFAULT:2" )
add_outdir_option( argparser_filterdup )
argparser_filterdup.add_argument( "-o", "--ofile", dest = "outputfile", type = str,
help = "Output BED file name. If not specified, will write to standard output. DEFAULT: stdout",
default = "stdout" )
argparser_filterdup.add_argument( "-d", "--dry-run", dest="dryrun", action="store_true", default=False,
help = "When set, filterdup will only output numbers instead of writing output files, including maximum allowable duplicates, total number of reads before filtering, total number of reads after filtering, and redundant rate. Default: not set" )
return
def add_bdgpeakcall_parser( subparsers ):
"""Add function 'peak calling on bedGraph' argument parsers.
"""
argparser_bdgpeakcall = subparsers.add_parser( "bdgpeakcall",
help = "Call peaks from bedGraph output. Note: All regions on the same chromosome in the bedGraph file should be continuous so only bedGraph files from MACS2 are accpetable." )
argparser_bdgpeakcall.add_argument( "-i", "--ifile", dest = "ifile", type = str, required = True,
help = "MACS score in bedGraph. REQUIRED" )
argparser_bdgpeakcall.add_argument( "-c", "--cutoff" , dest = "cutoff", type = float,
help = "Cutoff depends on which method you used for score track. If the file contains pvalue scores from MACS2, score 5 means pvalue 1e-5. DEFAULT: 5", default = 5 )
argparser_bdgpeakcall.add_argument( "-l", "--min-length", dest = "minlen", type = int,
help = "minimum length of peak, better to set it as d value. DEFAULT: 200", default = 200 )
argparser_bdgpeakcall.add_argument( "-g", "--max-gap", dest = "maxgap", type = int,
help = "maximum gap between significant points in a peak, better to set it as tag size. DEFAULT: 30", default = 30 )
argparser_bdgpeakcall.add_argument( "--call-summits", dest="call_summits", action="store_true", help=ap.SUPPRESS, default=False)
# help="If set, MACS will use a more sophisticated approach to find all summits in each enriched peak region. DEFAULT: False",default=False)
argparser_bdgpeakcall.add_argument( "--cutoff-analysis", dest="cutoff_analysis", action="store_true",
help = "While set, bdgpeakcall will analyze number or total length of peaks that can be called by different cutoff then output a summary table to help user decide a better cutoff. Note, minlen and maxgap may affect the results. DEFAULT: False", default = False )
argparser_bdgpeakcall.add_argument("--no-trackline", dest="trackline", action="store_false", default=True,
help="Tells MACS not to include trackline with bedGraph files. The trackline is required by UCSC.")
add_outdir_option( argparser_bdgpeakcall )
add_output_group( argparser_bdgpeakcall )
return
def add_bdgbroadcall_parser( subparsers ):
"""Add function 'broad peak calling on bedGraph' argument parsers.
"""
argparser_bdgbroadcall = subparsers.add_parser( "bdgbroadcall",
help = "Call broad peaks from bedGraph output. Note: All regions on the same chromosome in the bedGraph file should be continuous so only bedGraph files from MACS2 are accpetable." )
argparser_bdgbroadcall.add_argument( "-i", "--ifile", dest = "ifile" , type = str, required = True,
help = "MACS score in bedGraph. REQUIRED" )
argparser_bdgbroadcall.add_argument( "-c", "--cutoff-peak", dest = "cutoffpeak", type = float,
help = "Cutoff for peaks depending on which method you used for score track. If the file contains qvalue scores from MACS2, score 2 means qvalue 0.01. DEFAULT: 2",
default = 2 )
argparser_bdgbroadcall.add_argument( "-C", "--cutoff-link", dest = "cutofflink", type = float,
help = "Cutoff for linking regions/low abundance regions depending on which method you used for score track. If the file contains qvalue scores from MACS2, score 1 means qvalue 0.1, and score 0.3 means qvalue 0.5. DEFAULT: 1", default = 1 )
argparser_bdgbroadcall.add_argument( "-l", "--min-length", dest = "minlen", type = int,
help = "minimum length of peak, better to set it as d value. DEFAULT: 200", default = 200 )
argparser_bdgbroadcall.add_argument( "-g", "--lvl1-max-gap", dest = "lvl1maxgap", type = int,
help = "maximum gap between significant peaks, better to set it as tag size. DEFAULT: 30", default = 30 )
argparser_bdgbroadcall.add_argument( "-G", "--lvl2-max-gap", dest = "lvl2maxgap", type = int,
help = "maximum linking between significant peaks, better to set it as 4 times of d value. DEFAULT: 800", default = 800)
add_outdir_option( argparser_bdgbroadcall )
add_output_group( argparser_bdgbroadcall )
return
def add_bdgcmp_parser( subparsers ):
"""Add function 'peak calling on bedGraph' argument parsers.
"""
argparser_bdgcmp = subparsers.add_parser( "bdgcmp",
help = "Deduct noise by comparing two signal tracks in bedGraph. Note: All regions on the same chromosome in the bedGraph file should be continuous so only bedGraph files from MACS2 are accpetable." )
argparser_bdgcmp.add_argument( "-t", "--tfile", dest = "tfile", type = str, required = True,
help = "Treatment bedGraph file, e.g. *_treat_pileup.bdg from MACSv2. REQUIRED")
argparser_bdgcmp.add_argument( "-c", "--cfile", dest = "cfile", type = str, required = True,
help = "Control bedGraph file, e.g. *_control_lambda.bdg from MACSv2. REQUIRED")
argparser_bdgcmp.add_argument( "-S", "--scaling-factor", dest = "sfactor", type = float, default = 1.0,
help = "Scaling factor for treatment and control track. Keep it as 1.0 or default in most cases. Set it ONLY while you have SPMR output from MACS2 callpeak, and plan to calculate scores as MACS2 callpeak module. If you want to simulate 'callpeak' w/o '--to-large', calculate effective smaller sample size after filtering redudant reads in million (e.g., put 31.415926 if effective reads are 31,415,926) and input it for '-S'; for 'callpeak --to-large', calculate effective reads in larger sample. DEFAULT: 1.0")
argparser_bdgcmp.add_argument( "-p", "--pseudocount", dest = "pseudocount", type = float, default = 0.0,
help = "The pseudocount used for calculating logLR, logFE or FE. The count will be applied after normalization of sequencing depth. DEFAULT: 0.0, no pseudocount is applied.")
argparser_bdgcmp.add_argument( "-m", "--method", dest = "method", type = str, nargs = "+",
choices = ( "ppois", "qpois", "subtract", "logFE", "FE", "logLR", "slogLR", "max" ),
help = "Method to use while calculating a score in any bin by comparing treatment value and control value. Available choices are: ppois, qpois, subtract, logFE, logLR, and slogLR. They represent Poisson Pvalue (-log10(pvalue) form) using control as lambda and treatment as observation, q-value through a BH process for poisson pvalues, subtraction from treatment, linear scale fold enrichment, log10 fold enrichment(need to set pseudocount), log10 likelihood between ChIP-enriched model and open chromatin model(need to set pseudocount), symmetric log10 likelihood between two ChIP-enrichment models, or maximum value between the two tracks. Default option is ppois.",default="ppois")
add_outdir_option( argparser_bdgcmp )
output_group = argparser_bdgcmp.add_mutually_exclusive_group( required = True )
output_group.add_argument( "--o-prefix", dest = "oprefix", type = str,
help = "The PREFIX of output bedGraph file to write scores. If it is given as A, and method is 'ppois', output file will be A_ppois.bdg. Mutually exclusive with -o/--ofile." )
output_group.add_argument( "-o", "--ofile", dest = "ofile", type = str, nargs = "+",
help = "Output filename. Mutually exclusive with --o-prefix. The number and the order of arguments for --ofile must be the same as for -m." )
return
def add_bdgopt_parser( subparsers ):
"""Add function 'operations on score column of bedGraph' argument parsers.
"""
argparser_bdgopt = subparsers.add_parser( "bdgopt",
help = "Operations on score column of bedGraph file. Note: All regions on the same chromosome in the bedGraph file should be continuous so only bedGraph files from MACS2 are accpetable." )
argparser_bdgopt.add_argument( "-i", "--ifile", dest = "ifile", type = str, required = True,
help = "MACS score in bedGraph. Note: this must be a bedGraph file covering the ENTIRE genome. REQUIRED" )
argparser_bdgopt.add_argument( "-m", "--method", dest = "method", type = str,
choices = ( "multiply", "add", "p2q", "max", "min" ),
help = "Method to modify the score column of bedGraph file. Available choices are: multiply, add, max, min, or p2q. 1) multiply, the EXTRAPARAM is required and will be multiplied to the score column. If you intend to divide the score column by X, use value of 1/X as EXTRAPARAM. 2) add, the EXTRAPARAM is required and will be added to the score column. If you intend to subtract the score column by X, use value of -X as EXTRAPARAM. 3) max, the EXTRAPARAM is required and will take the maximum value between score and the EXTRAPARAM. 4) min, the EXTRAPARAM is required and will take the minimum value between score and the EXTRAPARAM. 5) p2q, this will convert p-value scores to q-value scores using Benjamini-Hochberg process. The EXTRAPARAM is not required. This method assumes the scores are -log10 p-value from MACS2. Any other types of score will cause unexpected errors.", default="p2q")
argparser_bdgopt.add_argument( "-p", "--extra-param", dest = "extraparam", type = float, nargs = "*",
help = "The extra parameter for METHOD. Check the detail of -m option.")
add_outdir_option( argparser_bdgopt )
argparser_bdgopt.add_argument( "-o", "--ofile", dest = "ofile", type = str,
help = "Output BEDGraph filename.", required = True )
return
def add_cmbreps_parser( subparsers ):
"""Add function 'combine replicates' argument parsers.
"""
argparser_cmbreps = subparsers.add_parser( "cmbreps",
help = "Combine BEDGraphs of scores from replicates. Note: All regions on the same chromosome in the bedGraph file should be continuous so only bedGraph files from MACS2 are accpetable." )
argparser_cmbreps.add_argument( "-i", dest = "ifile", type = str, required = True, nargs = "+",
help = "MACS score in bedGraph for each replicate. Require exactly two files such as '-i A B'. REQUIRED" )
# argparser_cmbreps.add_argument( "-w", dest = "weights", type = float, nargs = "*",
# help = "Weight for each replicate. Default is 1.0 for each. When given, require same number of parameters as IFILE." )
argparser_cmbreps.add_argument( "-m", "--method", dest = "method", type = str,
choices = ( "fisher", "max", "mean" ),
help = "Method to use while combining scores from replicates. 1) fisher: Fisher's combined probability test. It requires scores in ppois form (-log10 pvalues) from bdgcmp. Other types of scores for this method may cause cmbreps unexpected errors. 2) max: take the maximum value from replicates for each genomic position. 3) mean: take the average value. Note, except for Fisher's method, max or mean will take scores AS IS which means they won't convert scores from log scale to linear scale or vice versa.", default="fisher")
add_outdir_option( argparser_cmbreps )
argparser_cmbreps.add_argument( "-o", "--ofile", dest = "ofile", type = str, required = True,
help = "Output BEDGraph filename for combined scores." )
return
def add_randsample_parser( subparsers ):
argparser_randsample = subparsers.add_parser( "randsample",
help = "Randomly sample number/percentage of total reads." )
argparser_randsample.add_argument( "-t", "--tfile", dest = "tfile", type = str, required = True, nargs = "+",
help = "ChIP-seq alignment file. If multiple files are given as '-t A B C', then they will all be read and combined. Note that pair-end data is not supposed to work with this command. REQUIRED." )
p_or_n_group = argparser_randsample.add_mutually_exclusive_group( required = True )
p_or_n_group.add_argument( "-p", "--percentage", dest = "percentage", type = float,
help = "Percentage of tags you want to keep. Input 80.0 for 80%%. This option can't be used at the same time with -n/--num. REQUIRED")
p_or_n_group.add_argument( "-n", "--number", dest = "number", type = float,
help = "Number of tags you want to keep. Input 8000000 or 8e+6 for 8 million. This option can't be used at the same time with -p/--percent. Note that the number of tags in output is approximate as the number specified here. REQUIRED" )
argparser_randsample.add_argument( "--seed", dest = "seed", type = int, default = -1,
help = "Set the random seed while down sampling data. Must be a non-negative integer in order to be effective. DEFAULT: not set" )
argparser_randsample.add_argument( "-o", "--ofile", dest = "outputfile", type = str,
help = "Output BED file name. If not specified, will write to standard output. DEFAULT: stdout",
default = None)
add_outdir_option( argparser_randsample )
argparser_randsample.add_argument( "-s", "--tsize", dest = "tsize", type = int, default = None,
help = "Tag size. This will override the auto detected tag size. DEFAULT: Not set")
argparser_randsample.add_argument( "-f", "--format", dest = "format", type = str,
choices=("AUTO","BAM","SAM","BED","ELAND","ELANDMULTI","ELANDEXPORT","BOWTIE"),
help = "Format of tag file, \"AUTO\", \"BED\" or \"ELAND\" or \"ELANDMULTI\" or \"ELANDEXPORT\" or \"SAM\" or \"BAM\" or \"BOWTIE\". The default AUTO option will %(prog)s decide which format the file is. Please check the definition in README file if you choose ELAND/ELANDMULTI/ELANDEXPORT/SAM/BAM/BOWTIE. DEFAULT: \"AUTO\"",
default = "AUTO" )
argparser_randsample.add_argument( "--verbose", dest = "verbose", type = int, default = 2,
help = "Set verbose level. 0: only show critical message, 1: show additional warning message, 2: show process information, 3: show debug messages. If you want to know where are the duplicate reads, use 3. DEFAULT:2" )
return
def add_bdgdiff_parser( subparsers ):
argparser_bdgdiff = subparsers.add_parser( "bdgdiff",
help = "Differential peak detection based on paired four bedgraph files. Note: All regions on the same chromosome in the bedGraph file should be continuous so only bedGraph files from MACS2 are accpetable." )
argparser_bdgdiff.add_argument( "--t1", dest = "t1bdg", type = str, required = True,
help = "MACS pileup bedGraph for condition 1. Incompatible with callpeak --SPMR output. REQUIRED" )
argparser_bdgdiff.add_argument( "--t2", dest="t2bdg", type = str, required = True,
help = "MACS pileup bedGraph for condition 2. Incompatible with callpeak --SPMR output. REQUIRED" )
argparser_bdgdiff.add_argument( "--c1", dest = "c1bdg", type = str, required = True,
help = "MACS control lambda bedGraph for condition 1. Incompatible with callpeak --SPMR output. REQUIRED" )
argparser_bdgdiff.add_argument( "--c2", dest="c2bdg", type = str, required = True,
help = "MACS control lambda bedGraph for condition 2. Incompatible with callpeak --SPMR output. REQUIRED" )
argparser_bdgdiff.add_argument( "-C", "--cutoff", dest = "cutoff", type = float,
help = "logLR cutoff. DEFAULT: 3 (likelihood ratio=1000)", default = 3 )
argparser_bdgdiff.add_argument( "-l", "--min-len", dest = "minlen", type = int,
help = "Minimum length of differential region. Try bigger value to remove small regions. DEFAULT: 200", default = 200 )
argparser_bdgdiff.add_argument( "-g", "--max-gap", dest = "maxgap", type = int,
help = "Maximum gap to merge nearby differential regions. Consider a wider gap for broad marks. Maximum gap should be smaller than minimum length (-g). DEFAULT: 100", default = 100 )
argparser_bdgdiff.add_argument( "--d1", "--depth1", dest = "depth1", type = float, default = 1.0,
help = "Sequencing depth (# of non-redundant reads in million) for condition 1. It will be used together with --d2. See description for --d2 below for how to assign them. Default: 1" )
argparser_bdgdiff.add_argument( "--d2", "--depth2", dest = "depth2", type = float, default = 1.0,
help = "Sequencing depth (# of non-redundant reads in million) for condition 2. It will be used together with --d1. DEPTH1 and DEPTH2 will be used to calculate scaling factor for each sample, to down-scale larger sample to the level of smaller one. For example, while comparing 10 million condition 1 and 20 million condition 2, use --d1 10 --d2 20, then pileup value in bedGraph for condition 2 will be divided by 2. Default: 1" )
add_outdir_option( argparser_bdgdiff )
output_group = argparser_bdgdiff.add_mutually_exclusive_group( required = True )
output_group.add_argument( "--o-prefix", dest = "oprefix", type = str,
help = "Output file prefix. Actual files will be named as PREFIX_cond1.bed, PREFIX_cond2.bed and PREFIX_common.bed. Mutually exclusive with -o/--ofile." )
output_group.add_argument( "-o", "--ofile", dest = "ofile", type = str, nargs = 3,
help = "Output filenames. Must give three arguments in order: 1. file for unique regions in condition 1; 2. file for unique regions in condition 2; 3. file for common regions in both conditions. Note: mutually exclusive with --o-prefix." )
return
def add_refinepeak_parser( subparsers ):
argparser_refinepeak = subparsers.add_parser( "refinepeak",
help = "(Experimental) Take raw reads alignment, refine peak summits and give scores measuring balance of waston/crick tags. Inspired by SPP." )
argparser_refinepeak.add_argument( "-b", dest = "bedfile", type = str, required = True,
help = "Candidate peak file in BED format. REQUIRED." )
argparser_refinepeak.add_argument( "-i", "--ifile", dest = "ifile", type = str, required = True, nargs = "+",
help = "ChIP-seq alignment file. If multiple files are given as '-t A B C', then they will all be read and combined. Note that pair-end data is not supposed to work with this command. REQUIRED." )
argparser_refinepeak.add_argument( "-f", "--format", dest = "format", type = str,
choices=("AUTO","BAM","SAM","BED","ELAND","ELANDMULTI","ELANDEXPORT","BOWTIE"),
help = "Format of tag file, \"AUTO\", \"BED\" or \"ELAND\" or \"ELANDMULTI\" or \"ELANDEXPORT\" or \"SAM\" or \"BAM\" or \"BOWTIE\". The default AUTO option will let '%(prog)s' decide which format the file is. Please check the definition in README file if you choose ELAND/ELANDMULTI/ELANDEXPORT/SAM/BAM/BOWTIE. DEFAULT: \"AUTO\"",
default = "AUTO" )
argparser_refinepeak.add_argument( "-c", "--cutoff" , dest = "cutoff", type = float,
help = "Cutoff DEFAULT: 5", default = 5 )
argparser_refinepeak.add_argument( "-w", "--window-size", dest= "windowsize", help = 'Scan window size on both side of the summit (default: 100bp)',
type = int, default = 200)
argparser_refinepeak.add_argument( "--verbose", dest = "verbose", type = int, default = 2,
help = "Set verbose level. 0: only show critical message, 1: show additional warning message, 2: show process information, 3: show debug messages. If you want to know where are the duplicate reads, use 3. DEFAULT:2" )
add_outdir_option( argparser_refinepeak )
add_output_group( argparser_refinepeak )
return
def add_predictd_parser( subparsers ):
"""Add main function 'predictd' argument parsers.
"""
argparser_predictd = subparsers.add_parser("predictd", help="Predict d or fragment size from alignment results. *Will NOT filter duplicates*")
# group for input files
argparser_predictd.add_argument( "-i", "--ifile", dest = "ifile", type = str, required = True, nargs = "+",
help = "ChIP-seq alignment file. If multiple files are given as '-t A B C', then they will all be read and combined. Note that pair-end data is not supposed to work with this command. REQUIRED." )
argparser_predictd.add_argument( "-f", "--format", dest = "format", type = str,
choices = ("AUTO", "BAM", "SAM", "BED", "ELAND",
"ELANDMULTI", "ELANDEXPORT", "BOWTIE",
"BAMPE", "BEDPE"),
help = "Format of tag file, \"AUTO\", \"BED\" or \"ELAND\" or \"ELANDMULTI\" or \"ELANDEXPORT\" or \"SAM\" or \"BAM\" or \"BOWTIE\" or \"BAMPE\" or \"BEDPE\". The default AUTO option will let MACS decide which format the file is. Please check the definition in README file if you choose ELAND/ELANDMULTI/ELANDEXPORT/SAM/BAM/BOWTIE. DEFAULT: \"AUTO\"",
default = "AUTO" )
argparser_predictd.add_argument( "-g", "--gsize", dest = "gsize", type = str, default = "hs",
help = "Effective genome size. It can be 1.0e+9 or 1000000000, or shortcuts:'hs' for human (2.7e9), 'mm' for mouse (1.87e9), 'ce' for C. elegans (9e7) and 'dm' for fruitfly (1.2e8), Default:hs" )
argparser_predictd.add_argument( "-s", "--tsize", dest = "tsize", type = int, default = None,
help = "Tag size. This will override the auto detected tag size. DEFAULT: Not set")
argparser_predictd.add_argument( "--bw", dest = "bw", type = int, default = 300,
help = "Band width for picking regions to compute fragment size. This value is only used while building the shifting model. DEFAULT: 300")
argparser_predictd.add_argument( "-m", "--mfold", dest = "mfold", type = int, default = [5,50], nargs = 2,
help = "Select the regions within MFOLD range of high-confidence enrichment ratio against background to build model. Fold-enrichment in regions must be lower than upper limit, and higher than the lower limit. Use as \"-m 10 30\". DEFAULT:5 50" )
add_outdir_option( argparser_predictd )
argparser_predictd.add_argument( "--rfile", dest = "rfile", type = str, default = "predictd",
help = "PREFIX of filename of R script for drawing X-correlation figure. DEFAULT:'predictd' and R file will be predicted_model.R" )
argparser_predictd.add_argument( "--verbose", dest = "verbose", type = int, default = 2,
help = "Set verbose level of runtime message. 0: only show critical message, 1: show additional warning message, 2: show process information, 3: show debug messages. DEFAULT:2" )
return
def add_pileup_parser( subparsers ):
argparser_pileup = subparsers.add_parser( "pileup",
help = "Pileup aligned reads with a given extension size (fragment size or d in MACS language). Note there will be no step for duplicate reads filtering or sequencing depth scaling, so you may need to do certain pre/post-processing." )
argparser_pileup.add_argument( "-i", "--ifile", dest = "ifile", type = str, required = True, nargs = "+",
help = "ChIP-seq alignment file. If multiple files are given as '-t A B C', then they will all be read and combined. Note that pair-end data is not supposed to work with this command. REQUIRED." )
argparser_pileup.add_argument( "-o", "--ofile", dest = "outputfile", type = str, required = True,
help = "Output bedGraph file name. If not specified, will write to standard output. REQUIRED." )
add_outdir_option( argparser_pileup )
argparser_pileup.add_argument( "-f", "--format", dest = "format", type = str,
choices=("AUTO","BAM","SAM","BED","ELAND","ELANDMULTI","ELANDEXPORT","BOWTIE"),
help = "Format of tag file, \"AUTO\", \"BED\" or \"ELAND\" or \"ELANDMULTI\" or \"ELANDEXPORT\" or \"SAM\" or \"BAM\" or \"BOWTIE\". The default AUTO option will let '%(prog)s' decide which format the file is. Please check the definition in README file if you choose ELAND/ELANDMULTI/ELANDEXPORT/SAM/BAM/BOWTIE. DEFAULT: \"AUTO\"",
default = "AUTO" )
argparser_pileup.add_argument( "-B", "--both-direction", dest = "bothdirection", action = "store_true", default = False,
help = "By default, any read will be extended towards downstream direction by extension size. So it's [0,size-1] (1-based index system) for plus strand read and [-size+1,0] for minus strand read where position 0 is 5' end of the aligned read. Default behavior can simulate MACS2 way of piling up ChIP sample reads where extension size is set as fragment size/d. If this option is set as on, aligned reads will be extended in both upstream and downstream directions by extension size. It means [-size,size] where 0 is the 5' end of a aligned read. It can partially simulate MACS2 way of piling up control reads. However MACS2 local bias is calculated by maximizing the expected pileup over a ChIP fragment size/d estimated from 10kb, 1kb, d and whole genome background. DEFAULT: False" )
argparser_pileup.add_argument( "--extsize", dest = "extsize", type = int, default = 200,
help = "The extension size in bps. Each alignment read will become a EXTSIZE of fragment, then be piled up. Check description for -B for detail. It's twice the `shiftsize` in old MACSv1 language. DEFAULT: 200 " )
argparser_pileup.add_argument( "--verbose", dest = "verbose", type = int, default = 2,
help = "Set verbose level. 0: only show critical message, 1: show additional warning message, 2: show process information, 3: show debug messages. If you want to know where are the duplicate reads, use 3. DEFAULT:2" )
return
if __name__ == '__main__':
try:
main()
except KeyboardInterrupt:
sys.stderr.write("User interrupted me! ;-) Bye!\n")
sys.exit(0)
|