def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE compare signal to roadmap')
parser.add_argument('--bigwig',
type=str,
help='BIGWIG file (from task macs2).')
parser.add_argument('--dnase', type=str, help='DNase file.')
parser.add_argument('--reg2map', type=str, help='Reg2map file.')
parser.add_argument('--reg2map-bed', type=str, help='Reg2map bed file.')
parser.add_argument('--roadmap-meta',
type=str,
help='Roadmap metadata file.')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
help='Log level',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
])
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE DCC FRiP.', description='')
parser.add_argument('peak', type=str, help='Peak file.')
parser.add_argument('ta', type=str, help='TAGALIGN file.')
parser.add_argument('--chrsz',
type=str,
help='2-col chromosome sizes file. \
If given, do shifted FRiP (for ChIP-Seq).')
parser.add_argument('--fraglen',
type=int,
default=0,
help='Fragment length for TAGALIGN file. \
If given, do shifted FRiP (for ChIP-Seq).')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE DCC MACS2 signal track',
description='')
parser.add_argument('ta', type=str,
help='Path for TAGALIGN file.')
parser.add_argument('--chrsz', type=str,
help='2-col chromosome sizes file.')
parser.add_argument('--gensz', type=str,
help='Genome size (sum of entries in 2nd column of \
chr. sizes file, or hs for human, ms for mouse).')
parser.add_argument('--pval-thresh', default=0.01, type=float,
help='P-Value threshold.')
parser.add_argument('--smooth-win', default=150, type=int,
help='Smoothing window size.')
parser.add_argument('--mem-gb', type=float, default=4.0,
help='Max. memory for this job in GB. '
'This will be used to determine GNU sort -S (defaulting to 0.5 of this value). '
'It should be total memory for this task (not memory per thread).')
parser.add_argument('--out-dir', default='', type=str,
help='Output directory.')
parser.add_argument('--log-level', default='INFO',
choices=['NOTSET', 'DEBUG', 'INFO',
'WARNING', 'CRITICAL', 'ERROR',
'CRITICAL'],
help='Log level')
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(
prog='ENCODE DCC control TAG-ALIGN subsampler.'
'This script does not check if number of reads in TA is higher than '
'subsampling number (--subsample). '
'If number of reads in TA is lower than subsampling number then '
'TA will be just shuffled.')
parser.add_argument('ta', type=str,
help='Path for control TAGALIGN file.')
parser.add_argument('--paired-end', action="store_true",
help='Paired-end TAGALIGN.')
parser.add_argument('--subsample', default=0, type=int,
help='Number of reads to subsample.')
parser.add_argument('--out-dir', default='', type=str,
help='Output directory.')
parser.add_argument('--log-level', default='INFO',
choices=['NOTSET', 'DEBUG', 'INFO',
'WARNING', 'CRITICAL', 'ERROR',
'CRITICAL'],
help='Log level')
args = parser.parse_args()
if not args.subsample:
raise ValueError('--subsample should be a positive integer.')
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(
prog='ENCODE DCC Count signal track generation')
parser.add_argument('ta', type=str, help='Path for TAGALIGN file.')
parser.add_argument('--chrsz',
type=str,
help='2-col chromosome sizes file.')
parser.add_argument(
'--mem-gb',
type=float,
default=4.0,
help='Max. memory for this job in GB. '
'This will be used to determine GNU sort -S (defaulting to 0.5 of this value). '
'It should be total memory for this task (not memory per thread).')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE preseq')
parser.add_argument('--paired-end',
action="store_true",
help='Paired-end BAM.')
parser.add_argument('--bam', type=str, help='Raw BAM file.')
parser.add_argument('--picard-java-heap',
help='Picard\'s Java max. heap: java -jar picard.jar '
'-Xmx[MAX_HEAP]')
parser.add_argument('--nth',
type=int,
default=1,
help='Number of threads to parallelize.')
parser.add_argument(
'--mem-gb',
type=float,
help='Max. memory for samtools sort in GB. '
'It should be total memory for this task (not memory per thread).')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
help='Log level',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
])
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE TSS enrichment.')
parser.add_argument('--read-len-log',
type=str,
help='Read length log file (from aligner task).')
parser.add_argument('--nodup-bam',
type=str,
help='Raw BAM file (from task filter).')
parser.add_argument('--chrsz',
type=str,
help='2-col chromosome sizes file.')
parser.add_argument('--tss', type=str, help='TSS definition bed file.')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
help='Log level',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
])
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE DCC TAGALIGN pooler.',
description='')
parser.add_argument('tas',
nargs='+',
type=str,
help='List of TAGALIGNs to be pooled.')
parser.add_argument('--prefix', type=str, help='Basename prefix.')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--col',
help='Number of columns to keep in a pooled TAGALIGN. '
'Keep all columns if not defined.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE DCC filter.')
parser.add_argument('bam', type=str, help='Path for raw BAM file.')
parser.add_argument('--dup-marker',
type=str,
choices=['picard', 'sambamba'],
default='picard',
help='Dupe marker for filtering mapped reads in BAM.')
parser.add_argument('--mapq-thresh',
default=30,
type=int,
help='Threshold for low MAPQ reads removal.')
parser.add_argument('--no-dup-removal',
action="store_true",
help='No dupe reads removal when filtering BAM.')
parser.add_argument('--paired-end',
action="store_true",
help='Paired-end BAM.')
parser.add_argument('--multimapping',
default=0,
type=int,
help='Multimapping reads.')
parser.add_argument(
'--filter-chrs',
nargs='*',
help='Chromosomes to be filtered for final (nodup/filt) BAM.')
parser.add_argument('--chrsz',
type=str,
help='2-col chromosome sizes file.')
parser.add_argument('--mito-chr-name',
default='chrM',
help='Mito chromosome name.')
parser.add_argument('--nth',
type=int,
default=1,
help='Number of threads to parallelize.')
parser.add_argument(
'--mem-gb',
type=float,
help='Max. memory for samtools sort in GB. '
'It should be total memory for this task (not memory per thread).')
parser.add_argument('--picard-java-heap',
help='Picard\'s Java max. heap: java -jar picard.jar '
'-Xmx[MAX_HEAP]')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE post_call_peak (chip)',
description='')
parser.add_argument('peak', type=str,
help='Path for PEAK file. Peak filename should be "*.*Peak.gz". '
'e.g. rep1.narrowPeak.gz')
parser.add_argument('--ta', type=str,
help='TAG-ALIGN file.')
parser.add_argument('--peak-type', type=str, required=True,
choices=['narrowPeak', 'regionPeak',
'broadPeak', 'gappedPeak'],
help='Peak file type.')
parser.add_argument('--fraglen', type=int, required=True,
help='Fragment length.')
parser.add_argument('--chrsz', type=str,
help='2-col chromosome sizes file.')
parser.add_argument('--blacklist', type=str, required=True,
help='Blacklist BED file.')
parser.add_argument('--keep-irregular-chr', action="store_true",
help='Keep reads with non-canonical chromosome names.')
parser.add_argument('--out-dir', default='', type=str,
help='Output directory.')
parser.add_argument('--log-level', default='INFO',
choices=['NOTSET', 'DEBUG', 'INFO',
'WARNING', 'CRITICAL', 'ERROR',
'CRITICAL'],
help='Log level')
args = parser.parse_args()
if args.blacklist.endswith('/dev/null'):
args.blacklist = ''
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE DCC MACS2 signal track',
description='')
parser.add_argument('tas', type=str, nargs='+',
help='Path for TAGALIGN file (first) and control TAGALIGN file (second; optional).')
parser.add_argument('--fraglen', type=int, required=True,
help='Fragment length.')
parser.add_argument('--shift', type=int, default=0,
help='macs2 callpeak --shift.')
parser.add_argument('--chrsz', type=str,
help='2-col chromosome sizes file.')
parser.add_argument('--gensz', type=str,
help='Genome size (sum of entries in 2nd column of \
chr. sizes file, or hs for human, ms for mouse).')
parser.add_argument('--pval-thresh', default=0.01, type=float,
help='P-Value threshold.')
parser.add_argument('--out-dir', default='', type=str,
help='Output directory.')
parser.add_argument('--log-level', default='INFO',
choices=['NOTSET', 'DEBUG', 'INFO',
'WARNING', 'CRITICAL', 'ERROR',
'CRITICAL'],
help='Log level')
args = parser.parse_args()
if len(args.tas) == 1:
args.tas.append('')
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE post align', description='')
parser.add_argument('fastq', type=str, help='Path for FASTQ R1')
parser.add_argument('bam', type=str, help='Path for BAM')
parser.add_argument('--chrsz',
type=str,
help='2-col chromosome sizes file. If not given then '
'SAMstats on mito-free BAM will not be calcaulted.')
parser.add_argument('--mito-chr-name',
default='chrM',
help='Mito chromosome name.')
parser.add_argument('--nth',
type=int,
default=1,
help='Number of threads to parallelize.')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(
prog='ENCODE annot_enrich (fraction of reads in annotated regions)')
parser.add_argument('--ta',
type=str,
help='TAG-ALIGN file (from task bam2ta).')
parser.add_argument('--dnase', type=str, help='DNase definition bed file.')
parser.add_argument('--blacklist', type=str, help='Blacklist bed file.')
parser.add_argument('--prom',
type=str,
help='Promoter definition bed file.')
parser.add_argument('--enh',
type=str,
help='Enhancer definition bed file.')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
help='Log level',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
])
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE DCC Blacklist filter.')
parser.add_argument('peak', type=str, help='Peak file.')
parser.add_argument('--blacklist',
type=str,
required=True,
help='Blacklist BED file.')
parser.add_argument('--keep-irregular-chr',
action="store_true",
help='Keep reads with non-canonical chromosome names.')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
if args.blacklist.endswith('null'):
args.blacklist = ''
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(
prog='ENCODE frac mito',
description='Calculates fraction of mito reads')
parser.add_argument('non_mito_samstat',
type=str,
help='Path for SAMstats log file')
parser.add_argument('mito_samstat',
type=str,
help='Path for SAMstats log file (mito only)')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(
prog='Wrapper for BSUB job submission for ATAC-seq data.',
description='')
parser.add_argument('--path-to-fastqs',
default='',
type=str,
help='Path to FASTQ files.')
parser.add_argument('--memory',
default='10GB',
type=str,
help='Memory requested to run the analysis.')
parser.add_argument(
'--queue',
default='standard',
type=str,
help='Queue to submit the job in HPCF (use bqueues to choose).')
parser.add_argument('--out-dir', type=str, help='Output Directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE DCC pseudo replicator.')
parser.add_argument('ta', type=str, help='Path for TAGALIGN file.')
parser.add_argument('--paired-end',
action="store_true",
help='Paired-end TAGALIGN.')
parser.add_argument(
'--pseudoreplication-random-seed',
type=int,
default=0,
help='Set it to 0 to use file\'s size (in bytes) as random seed.'
'Otherwise this seed will be used for GNU shuf --random-source=sha256(seed).'
'It is useful when random seed based on input file size does not work.'
)
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(
prog='ENCODE spp call_peak')
parser.add_argument(
'tas', type=str, nargs=2,
help='Path for TAGALIGN file and control TAGALIGN file.')
parser.add_argument('--chrsz', type=str,
help='2-col chromosome sizes file.')
parser.add_argument('--fraglen', type=int, required=True,
help='Fragment length.')
parser.add_argument('--fdr-thresh', default=0.01, type=float,
help='FDR threshold for run_spp.R -fdr parameter.')
parser.add_argument('--cap-num-peak', default=300000, type=int,
help='Capping number of peaks by taking top N peaks.')
parser.add_argument('--nth', type=int, default=1,
help='Number of threads to parallelize.')
parser.add_argument('--out-dir', default='', type=str,
help='Output directory.')
parser.add_argument('--log-level', default='INFO',
choices=['NOTSET', 'DEBUG', 'INFO',
'WARNING', 'CRITICAL', 'ERROR',
'CRITICAL'],
help='Log level')
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE DCC MACS2 signal track',
description='')
parser.add_argument('ta', type=str, help='Path for TAGALIGN file.')
parser.add_argument('--chrsz',
type=str,
help='2-col chromosome sizes file.')
parser.add_argument('--gensz',
type=str,
help='Genome size (sum of entries in 2nd column of \
chr. sizes file, or hs for human, ms for mouse).')
parser.add_argument('--pval-thresh',
default=0.01,
type=float,
help='P-Value threshold.')
parser.add_argument('--smooth-win',
default=73,
type=int,
help='Smoothing window size.')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE DCC Blacklist filter.')
parser.add_argument('peak', type=str, help='Peak file.')
parser.add_argument('--blacklist', type=str, help='Blacklist BED file.')
parser.add_argument('--regex-bfilt-peak-chr-name',
help='Keep chromosomes matching this pattern only '
'in .bfilt. peak files.')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
if args.blacklist is None or args.blacklist.endswith('null'):
args.blacklist = ''
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(
prog='ENCODE DCC Naive overlap.',
description='NarrowPeak or RegionPeak only.')
parser.add_argument('peak1', type=str, help='Peak 1.')
parser.add_argument('peak2', type=str, help='Peak 2.')
parser.add_argument('peak_pooled', type=str, help='Pooled peak.')
parser.add_argument('--prefix',
default='overlap',
type=str,
help='Prefix basename for output overlap peak.')
parser.add_argument(
'--peak-type',
type=str,
required=True,
choices=['narrowPeak', 'regionPeak', 'broadPeak', 'gappedPeak'],
help='Peak file type.')
parser.add_argument('--nonamecheck',
action='store_true',
help='bedtools intersect -nonamecheck. \
use this if you get bedtools intersect \
naming convenction warnings/errors).')
parser.add_argument('--blacklist', type=str, help='Blacklist BED file.')
parser.add_argument('--regex-bfilt-peak-chr-name',
help='Keep chromosomes matching this pattern only '
'in .bfilt. peak files.')
parser.add_argument('--ta', type=str, help='TAGALIGN file for FRiP.')
parser.add_argument('--chrsz',
type=str,
help='2-col chromosome sizes file.')
parser.add_argument('--fraglen',
type=int,
default=0,
help='Fragment length for TAGALIGN file. \
If given, do shifted FRiP (for ChIP-Seq).')
parser.add_argument(
'--mem-gb',
type=float,
default=4.0,
help='Max. memory for this job in GB. '
'This will be used to determine GNU sort -S (defaulting to 0.5 of this value). '
'It should be total memory for this task (not memory per thread).')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
if args.blacklist is None or args.blacklist.endswith('null'):
args.blacklist = ''
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE DCC bwa aligner.',
description='')
parser.add_argument('bwa_index_prefix_or_tar', type=str,
help='Path for prefix (or a tarball .tar) \
for reference bwa index. \
Prefix must be like [PREFIX].sa. \
TAR ball can have any [PREFIX] but it should not \
have a directory structure in it.')
parser.add_argument('fastqs', nargs='+', type=str,
help='List of FASTQs (R1 and R2). \
FASTQs must be compressed with gzip (with .gz).')
parser.add_argument(
'--use-bwa-mem-for-pe', action="store_true",
help='Use "bwa mem" for PAIRED-ENDED dataset with R1 FASTQ\'s read length >= --bwa-mem-read-len-limit. '
'For shorter reads, bwa aln will be used. ')
parser.add_argument(
'--rescue-reads-for-bwa-mem', action="store_true",
help='Use -P for "bwa mem" to rescue missing hits only (by using SW algorithm) '
'but do not try to find hits that fit a proper pair.'
)
parser.add_argument('--bwa-mem-read-len-limit', type=int, default=70,
help='Read length limit for bwa mem (for paired-ended FASTQs only). '
'bwa aln will be used instead of bwa mem if R1 reads are shorter than this.')
parser.add_argument('--paired-end', action="store_true",
help='Paired-end FASTQs.')
parser.add_argument('--nth', type=int, default=1,
help='Number of threads to parallelize.')
parser.add_argument('--mem-gb', type=float,
help='Max. memory for samtools sort and GNU sort -S '
'(half of this value will be used for GNU sort) in GB. '
'It should be total memory for this task (not memory per thread).')
parser.add_argument('--out-dir', default='', type=str,
help='Output directory.')
parser.add_argument('--log-level', default='INFO',
choices=['NOTSET', 'DEBUG', 'INFO',
'WARNING', 'CRITICAL', 'ERROR',
'CRITICAL'],
help='Log level')
args = parser.parse_args()
# check if fastqs have correct dimension
if args.paired_end and len(args.fastqs) != 2:
raise argparse.ArgumentTypeError('Need 2 fastqs for paired end.')
if not args.paired_end and len(args.fastqs) != 1:
raise argparse.ArgumentTypeError('Need 1 fastq for single end.')
if args.use_bwa_mem_for_pe and not args.paired_end:
raise ValueError(
'--use-bwa-mem-for-pe is for paired ended FASTQs only.'
)
if not args.use_bwa_mem_for_pe and args.rescue_reads_for_bwa_mem:
raise ValueError(
'--rescue-reads-for-bwa-mem is available only when --use-bwa-mem-for-pe is activated.'
)
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE DCC bowtie2 aligner.',
description='')
parser.add_argument('bowtie2_index_prefix_or_tar',
type=str,
help='Path for prefix (or a tarball .tar) \
for reference bowtie2 index. \
Prefix must be like [PREFIX].1.bt2*. \
TAR ball can have any [PREFIX] but it should not \
have a directory structure in it.')
parser.add_argument('fastqs',
nargs='+',
type=str,
help='List of FASTQs (R1 and R2). \
FASTQs must be compressed with gzip (with .gz).')
parser.add_argument('--paired-end',
action="store_true",
help='Paired-end FASTQs.')
parser.add_argument(
'--multimapping',
default=0,
type=int,
help='Multimapping reads (for bowtie2 -k(m+1). '
'This will be incremented in an actual bowtie2 command line'
'e.g. --multimapping 3 will be bowtie2 -k 4')
parser.add_argument('--nth',
type=int,
default=1,
help='Number of threads to parallelize.')
parser.add_argument(
'--mem-gb',
type=float,
help='Max. memory for samtools sort in GB. '
'It should be total memory for this task (not memory per thread).')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
# check if fastqs have correct dimension
if args.paired_end and len(args.fastqs) != 2:
raise argparse.ArgumentTypeError('Need 2 fastqs for paired end.')
if not args.paired_end and len(args.fastqs) != 1:
raise argparse.ArgumentTypeError('Need 1 fastq for single end.')
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(
prog='ENCODE DCC IDR.', description='NarrowPeak or RegionPeak only.')
parser.add_argument('peak1', type=str, help='Peak file 1.')
parser.add_argument('peak2', type=str, help='Peak file 2.')
parser.add_argument('peak_pooled', type=str, help='Pooled peak file.')
parser.add_argument('--prefix',
default='idr',
type=str,
help='Prefix basename for output IDR peak.')
parser.add_argument(
'--peak-type',
type=str,
required=True,
choices=['narrowPeak', 'regionPeak', 'broadPeak', 'gappedPeak'],
help='Peak file type.')
parser.add_argument('--idr-thresh',
default=0.1,
type=float,
help='IDR threshold.')
parser.add_argument('--idr-rank',
default='p.value',
type=str,
choices=['p.value', 'q.value', 'signal.value'],
help='IDR ranking method.')
parser.add_argument('--blacklist', type=str, help='Blacklist BED file.')
parser.add_argument('--regex-bfilt-peak-chr-name',
help='Keep chromosomes matching this pattern only '
'in .bfilt. peak files.')
parser.add_argument('--ta', type=str, help='TAGALIGN file for FRiP.')
parser.add_argument('--chrsz',
type=str,
help='2-col chromosome sizes file.')
parser.add_argument('--fraglen',
type=int,
default=0,
help='Fragment length for TAGALIGN file. \
If given, do shifted FRiP (for ChIP-Seq).')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
if args.blacklist is None or args.blacklist.endswith('null'):
args.blacklist = ''
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(
prog='ENCODE DCC Naive overlap.',
description='NarrowPeak or RegionPeak only.')
parser.add_argument('peak1', type=str, help='Peak 1.')
parser.add_argument('peak2', type=str, help='Peak 2.')
parser.add_argument('peak_pooled', type=str, help='Pooled peak.')
parser.add_argument('--prefix',
default='overlap',
type=str,
help='Prefix basename for output overlap peak.')
parser.add_argument(
'--peak-type',
type=str,
required=True,
choices=['narrowPeak', 'regionPeak', 'broadPeak', 'gappedPeak'],
help='Peak file type.')
parser.add_argument('--nonamecheck',
action='store_true',
help='bedtools intersect -nonamecheck. \
use this if you get bedtools intersect \
naming convenction warnings/errors).')
parser.add_argument('--blacklist',
type=str,
required=True,
help='Blacklist BED file.')
parser.add_argument('--keep-irregular-chr',
action="store_true",
help='Keep reads with non-canonical chromosome names.')
parser.add_argument('--ta', type=str, help='TAGALIGN file for FRiP.')
parser.add_argument('--chrsz',
type=str,
help='2-col chromosome sizes file.')
parser.add_argument('--fraglen',
type=int,
default=0,
help='Fragment length for TAGALIGN file. \
If given, do shifted FRiP (for ChIP-Seq).')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
if args.blacklist.endswith('/dev/null'):
args.blacklist = ''
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments(debug=False):
parser = argparse.ArgumentParser(prog='ENCODE DCC Trimmomatic wrapper.')
parser.add_argument('--fastq1', help='FASTQ R1 to be trimmed.')
parser.add_argument('--fastq2', help='FASTQ R2 to be trimmed.')
parser.add_argument('--paired-end',
action="store_true",
help='Paired-end FASTQs.')
parser.add_argument('--crop-length',
type=int,
required=True,
help='Number of basepair to crop.'
'Trimmomatic\'s parameter CROP.')
parser.add_argument(
'--crop-length-tol',
type=int,
default=2,
help='Crop length tolerance to keep shorter reads '
'around the crop length. '
'Trimmomatic\'s parameter MINLEN will be --crop-length '
'- abs(--crop-length-tol).')
parser.add_argument('--phred-score-format',
default='auto',
choices=['auto', 'phred33', 'phred64'],
help='Base encoding for Phred scores in FASTQs. '
'If it is not auto then -phred33 or -phred64 to '
'Trimmomatic\'s command line.')
parser.add_argument('--out-dir-R1',
default='',
type=str,
help='Output directory for cropped R1 fastq.')
parser.add_argument('--out-dir-R2',
default='',
type=str,
help='Output directory for cropped R2 fastq.')
parser.add_argument(
'--trimmomatic-java-heap',
help='Trimmomatic\'s Java max. heap: java -jar Trimmomatic.jar '
'-Xmx[MAX_HEAP]')
parser.add_argument('--nth',
type=int,
default=1,
help='Number of threads to parallelize.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
if not args.crop_length:
raise ValueError('Crop length must be > 0.')
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE DCC MACS2 callpeak')
parser.add_argument('tas',
type=str,
nargs='+',
help='Path for TAGALIGN file (first) and '
'control TAGALIGN file (second; optional).')
parser.add_argument('--fraglen',
type=int,
required=True,
help='Fragment length.')
parser.add_argument('--shift',
type=int,
default=0,
help='macs2 callpeak --shift.')
parser.add_argument('--chrsz',
type=str,
help='2-col chromosome sizes file.')
parser.add_argument('--gensz',
type=str,
help='Genome size (sum of entries in 2nd column of \
chr. sizes file, or hs for human, ms for mouse).')
parser.add_argument('--pval-thresh',
default=0.01,
type=float,
help='P-Value threshold.')
parser.add_argument('--cap-num-peak',
default=500000,
type=int,
help='Capping number of peaks by taking top N peaks.')
parser.add_argument('--ctl-subsample',
default=0,
type=int,
help='Subsample control to this read depth '
'(0: no subsampling).')
parser.add_argument('--ctl-paired-end',
action="store_true",
help='Paired-end control TA.')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
if len(args.tas) == 1:
args.tas.append('')
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(
prog='ENCODE DCC Choose control.',
description='Choose appropriate control for each IP replicate.'
'ctl_for_repN.tagAlign.gz will be generated for each '
'IP replicate on --out-dir. '
'This outputs a file with integers '
'(chosen control index for each replicate per line).')
parser.add_argument('--tas', type=str, nargs='+', required=True,
help='List of experiment TAG-ALIGN per IP replicate.')
parser.add_argument('--ctl-tas', type=str, nargs='+', required=True,
help='List of control TAG-ALIGN per IP replicate.')
parser.add_argument('--ta-pooled', type=str, nargs='*',
help='Pooled experiment TAG-ALIGN.')
parser.add_argument('--ctl-ta-pooled', type=str, nargs='*',
help='Pooled control TAG-ALIGN.')
parser.add_argument('--ctl-depth-ratio', type=float, required=True,
help='Control depth ratio (between any two controls).')
parser.add_argument('--ctl-depth-limit', type=int, default=200000000,
help='Control depth limit. If read depth of chosen control is '
'over this limit then such control should be subsampled.')
parser.add_argument('--exp-ctl-depth-ratio-limit', type=float, default=5.0,
help='Exp vs. control depth ratio limit. ')
parser.add_argument('--always-use-pooled-ctl', action="store_true",
help='Always use pooled control for all IP '
'replicates.')
parser.add_argument('--out-tsv-basename', default='chosen_ctl.tsv', type=str,
help='Output TSV basename '
'(will be written on directory --out-dir). '
'This TSV file has chosen control index '
'per line (for each exp replicate).')
parser.add_argument('--out-tsv-subsample-basename', default='chosen_ctl_subsample.tsv', type=str,
help='Output TSV subsample basename '
'(will be written on directory --out-dir). '
'This TSV file has number of reads to subsample control '
'per line (for each exp replicate). '
'0 means no subsampling for control.')
parser.add_argument('--out-txt-subsample-pooled-basename', default='chosen_ctl_subsample_pooled.txt', type=str,
help='Output TXT subsample basename for pooled control'
'(will be written on directory --out-dir). '
'This TXT file has a single line for '
'number of reads to subsample pooled control control'
'0 means no subsampling for control.')
parser.add_argument('--out-dir', default='', type=str,
help='Output directory.')
parser.add_argument('--log-level', default='INFO',
choices=['NOTSET', 'DEBUG', 'INFO',
'WARNING', 'CRITICAL', 'ERROR',
'CRITICAL'],
help='Log level')
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(
prog='ENCODE DCC cross-correlation analysis.')
parser.add_argument('ta', type=str, help='Path for TAGALIGN file.')
parser.add_argument('--mito-chr-name',
default='chrM',
help='Mito chromosome name.')
parser.add_argument('--subsample',
type=int,
default=0,
help='Subsample TAGALIGN.')
parser.add_argument('--speak',
type=int,
default=-1,
help='User-defined cross-corr. peak strandshift \
(-speak= in run_spp.R). Disabled if -1.')
parser.add_argument('--exclusion-range-min',
type=int,
help='User-defined exclusion range minimum used for '
'-x=${xcor_exclusion_range_min}:'
'${xcor_exclusion_range_max}')
parser.add_argument('--exclusion-range-max',
type=int,
help='User-defined exclusion range maximum used for '
'-x=${xcor_exclusion_range_min}:'
'${xcor_exclusion_range_max}')
parser.add_argument('--chip-seq-type',
choices=['tf', 'histone'],
help='Type of ChIP-seq pipeline (histone of tf)')
parser.add_argument('--paired-end',
action="store_true",
help='Paired-end TAGALIGN.')
parser.add_argument('--nth',
type=int,
default=1,
help='Number of threads to parallelize.')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
log.setLevel(args.log_level)
log.info(sys.argv)
return args
def parse_arguments():
parser = argparse.ArgumentParser(prog='ENCODE post_call_peak (chip)',
description='')
parser.add_argument(
'peak',
type=str,
help='Path for PEAK file. Peak filename should be "*.*Peak.gz". '
'e.g. rep1.narrowPeak.gz')
parser.add_argument('--ta', type=str, help='TAG-ALIGN file.')
parser.add_argument(
'--peak-type',
type=str,
required=True,
choices=['narrowPeak', 'regionPeak', 'broadPeak', 'gappedPeak'],
help='Peak file type.')
parser.add_argument('--fraglen',
type=int,
required=True,
help='Fragment length.')
parser.add_argument('--chrsz',
type=str,
help='2-col chromosome sizes file.')
parser.add_argument('--blacklist', type=str, help='Blacklist BED file.')
parser.add_argument('--regex-bfilt-peak-chr-name',
help='Keep chromosomes matching this pattern only '
'in .bfilt. peak files.')
parser.add_argument(
'--mem-gb',
type=float,
default=4.0,
help='Max. memory for this job in GB. '
'This will be used to determine GNU sort -S (defaulting to 0.5 of this value). '
'It should be total memory for this task (not memory per thread).')
parser.add_argument('--out-dir',
default='',
type=str,
help='Output directory.')
parser.add_argument('--log-level',
default='INFO',
choices=[
'NOTSET', 'DEBUG', 'INFO', 'WARNING', 'CRITICAL',
'ERROR', 'CRITICAL'
],
help='Log level')
args = parser.parse_args()
if args.blacklist is None or args.blacklist.endswith('null'):
args.blacklist = ''
log.setLevel(args.log_level)
log.info(sys.argv)
return args
