def setUp(self):
self.assembly = Assembly('ce6')
self.assembly.genrep = GenRep(url='http://bbcftools.epfl.ch/genrep/',
root='/db/genrep')
self.assembly.intype = '0'
self.chromosomes = {
(3066, u'NC_003279', 6): {
'length': 15072421,
'name': u'chrI'
},
(3067, u'NC_003280', 7): {
'length': 15279323,
'name': u'chrII'
},
(3068, u'NC_003281', 8): {
'length': 13783681,
'name': u'chrIII'
},
(3069, u'NC_003282', 5): {
'length': 17493785,
'name': u'chrIV'
},
(3070, u'NC_003283', 8): {
'length': 20919568,
'name': u'chrV'
},
(3071, u'NC_003284', 7): {
'length': 17718854,
'name': u'chrX'
},
(2948, u'NC_001328', 1): {
'length': 13794,
'name': u'chrM'
}
}
def adn(self, ass, chr, id, **kw):
id = int(id)
g = GenRep()
chrs = g.get_genrep_objects('chromosomes',
'chromosome',
filters={'name': chr},
params={'assembly_id': ass})
ass = Assembly(ass)
for chrid, chrs in ass.chromosomes.iteritems():
if chrs['name'] == chr:
start = id * chunk
end = start + chunk
return g.get_sequence(chrid[0], [[start, end]])
return ''
"""
import os, sys, gzip, tarfile
from bbcflib.gfminer.stream import neighborhood, segment_features, score_by_feature
from bbcflib.gfminer.common import fusion, sorted_stream
from bbcflib.gfminer.figure import lineplot
from bbcflib.common import set_file_descr, unique_filename_in, intersect_many_bed, cat, merge_sql
from bbcflib.chipseq import add_macs_results
from bbcflib.mapseq import merge_bam, index_bam
from bbcflib.track import track, convert, FeatureStream
from bbcflib.genrep import GenRep
from bbcflib.motif import save_motif_profile
from bein import program
from bein.util import touch
from numpy import vstack, zeros
_gnrp = GenRep()
_macs_flank = 300
_plot_flank = (50, 50)
def macs_bedfiles(ex, chrmeta, tests, controls, names, macs_args, via,
logfile):
missing_beds = [k for k, t in enumerate(tests) if not t[0]]
if not missing_beds: return tests
genome_size = sum([x['length'] for x in chrmeta.values()])
logfile.write("Running MACS.\n")
logfile.flush()
_tts = [tests[k][1] for k in missing_beds]
_nms = {
'tests': [names['tests'][k] for k in missing_beds],
'controls': names['controls']
