logging.basicConfig(
level=logging.DEBUG, format='[%(name)s] [%(asctime)s]: %(message)s')
logger = logging.getLogger('metaseq data download')
hg19 = pybedtools.chromsizes('hg19')
genomes_file = pybedtools.chromsizes_to_file('hg19', 'hg19')
usage = """
Downloads data from UCSC, GEO, and Ensembl.
"""
import argparse
ap = argparse.ArgumentParser(usage=usage)
ap.add_argument(
'--data-dir',
default=metaseq.data_dir(),
help='Location to store downloaded and prepped data. '
'Default is %(default)s')
args = ap.parse_args()
CHROM = 'chr17'
COORD = "%s:%s-%s" % (CHROM, 0, hg19[CHROM][-1])
def download(url, dest):
"""
Platform-agnostic downloader.
"""
u = urllib.FancyURLopener()
logger.info("Downloading %s..." % url)
u.retrieve(url, dest)
#! /usr/bin/python # Download large data for running metaseq tests. # # > 1.6 GB of downloads import sys import os import hashlib import gffutils import pybedtools import metaseq DATA_DIR = metaseq.data_dir() # md5 hex digests for example files =========================================== # ENCODE data DATA = """ ff6979ace9befe82e71b6a05609d36e1 http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeHaibTfbs/wgEncodeHaibTfbsK562RxlchV0416101AlnRep1.bam ab2f3d2efd5a0281092e7ad542dfad36 http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeHaibTfbs/wgEncodeHaibTfbsK562RxlchV0416101AlnRep1.bam.bai fa20b05ea082dcb063463b73b6a5af2f http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeHaibTfbs/wgEncodeHaibTfbsK562RxlchV0416101RawRep1.bigWig b0716bd81170efe1fd0a8e411fb669d8 http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeHaibTfbs/wgEncodeHaibTfbsK562Atf3V0416101AlnRep1.bam 6e8f85d3ab428ef95e3382237b1b2419 http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeHaibTfbs/wgEncodeHaibTfbsK562Atf3V0416101PkRep1.broadPeak.gz cf869424dc915e59d9f1b3f73d720883 http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeHaibTfbs/wgEncodeHaibTfbsK562Atf3V0416101AlnRep1.bam.bai fb3b9dc8e85636a3a1226d22f8c1dbec http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeHaibTfbs/wgEncodeHaibTfbsK562Atf3V0416101RawRep1.bigWig """ # Ensembl annotations DATA += """ 25e76f628088daabd296447d06abe16b ftp://ftp.ensembl.org/pub/release-66/gtf/homo_sapiens/Homo_sapiens.GRCh37.66.gtf.gz
logging.basicConfig(level=logging.DEBUG,
format='[%(name)s] [%(asctime)s]: %(message)s')
logger = logging.getLogger('metaseq data download')
hg19 = pybedtools.chromsizes('hg19')
genomes_file = pybedtools.chromsizes_to_file('hg19', 'hg19')
usage = """
Downloads data from UCSC, GEO, and Ensembl.
"""
import argparse
ap = argparse.ArgumentParser(usage=usage)
ap.add_argument('--data-dir',
default=metaseq.data_dir(),
help='Location to store downloaded and prepped data. '
'Default is %(default)s')
args = ap.parse_args()
CHROM = 'chr17'
COORD = "%s:%s-%s" % (CHROM, 0, hg19[CHROM][-1])
def download(url, dest):
"""
Platform-agnostic downloader.
"""
u = urllib.FancyURLopener()
logger.info("Downloading %s..." % url)
u.retrieve(url, dest)
#! /usr/bin/python # Download large data for running metaseq tests. # # > 1.6 GB of downloads import sys import os import hashlib import gffutils import pybedtools import metaseq DATA_DIR = metaseq.data_dir() # md5 hex digests for example files =========================================== # ENCODE data DATA = """ ff6979ace9befe82e71b6a05609d36e1 http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeHaibTfbs/wgEncodeHaibTfbsK562RxlchV0416101AlnRep1.bam ab2f3d2efd5a0281092e7ad542dfad36 http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeHaibTfbs/wgEncodeHaibTfbsK562RxlchV0416101AlnRep1.bam.bai fa20b05ea082dcb063463b73b6a5af2f http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeHaibTfbs/wgEncodeHaibTfbsK562RxlchV0416101RawRep1.bigWig b0716bd81170efe1fd0a8e411fb669d8 http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeHaibTfbs/wgEncodeHaibTfbsK562Atf3V0416101AlnRep1.bam 6e8f85d3ab428ef95e3382237b1b2419 http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeHaibTfbs/wgEncodeHaibTfbsK562Atf3V0416101PkRep1.broadPeak.gz cf869424dc915e59d9f1b3f73d720883 http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeHaibTfbs/wgEncodeHaibTfbsK562Atf3V0416101AlnRep1.bam.bai fb3b9dc8e85636a3a1226d22f8c1dbec http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeHaibTfbs/wgEncodeHaibTfbsK562Atf3V0416101RawRep1.bigWig """ # Ensembl annotations DATA += """ 25e76f628088daabd296447d06abe16b ftp://ftp.ensembl.org/pub/release-66/gtf/homo_sapiens/Homo_sapiens.GRCh37.66.gtf.gz
'--stop',
type=int,
default=5000000,
help='stop coord of possible windows. See --nfeatures help regarding size.'
)
ap.add_argument('--chrom',
default='chr2L',
help='chromsome to make windows on')
ap.add_argument('--type',
default='all',
help='Only use the specified file types. Either "all" '
'(default) or a comma-separated list of [bam, bigwig, bed, '
'bigbed].')
ap.add_argument(
'--prefix',
default=os.path.join(metaseq.data_dir(), 'x'),
help='Prefix of filenames to use. Expects files '
'with this prefix, and the following suffixes: .bam, .bigwig, '
'.bed.gz (should already be tabixed), .bigbed. Default: %(default)s')
ap.add_argument(
'--plot-prefix',
default='./speedtest',
help='Filename used to save the resulting plot. Default is %(default)s')
ap.add_argument('--bins', default=100, help='Number of bins for each feature')
args = ap.parse_args()
requested = args.type.split(',')
allowed = ['bam', 'bed', 'bigwig', 'bigbed', 'all']
for req in requested:
if req not in allowed:
raise ValueError("%s not in %s" % (req, allowed))
ap.add_argument(
'--start', type=int, default=10000,
help='start coord of possible windows. See --nfeatures help regarding size.')
ap.add_argument(
'--stop', type=int, default=5000000,
help='stop coord of possible windows. See --nfeatures help regarding size.')
ap.add_argument(
'--chrom', default='chr2L',
help='chromsome to make windows on')
ap.add_argument(
'--type', default='all',
help='Only use the specified file types. Either "all" '
'(default) or a comma-separated list of [bam, bigwig, bed, '
'bigbed].')
ap.add_argument(
'--prefix', default=os.path.join(metaseq.data_dir(), 'x'),
help='Prefix of filenames to use. Expects files '
'with this prefix, and the following suffixes: .bam, .bigwig, '
'.bed.gz (should already be tabixed), .bigbed. Default: %(default)s')
ap.add_argument(
'--plot-prefix', default='./speedtest',
help='Filename used to save the resulting plot. Default is %(default)s')
ap.add_argument(
'--bins', default=100,
help='Number of bins for each feature')
args = ap.parse_args()
requested = args.type.split(',')
allowed = ['bam', 'bed', 'bigwig', 'bigbed', 'all']
for req in requested: