def __init__(self, nib_fns=[], nib_dirs=[]):
'''*nib_fns* is a list of paths to specific .nib files desired for the
NibDB. *nib_dirs* is a list of paths to directories containing .nib
files such that every .nib file in the directories is added to the NibDB.
Explicitly passed files take precedence over those found in directories
when sequence names collide.
'''
SeqDB.__init__(self)
# find all *.nib files in the directories passed
if isinstance(nib_dirs, str): # user just provided single directory
nib_dirs = [nib_dirs]
dir_nibs = []
for d in nib_dirs:
dir_nibs.extend(glob.glob(os.path.join(d, '*.nib')))
if isinstance(nib_fns, str):
nib_fns = [nib_fns]
# for each .nib found, add to db
# if there is a collision of names, those specified in files (not dirs)
# takes precedence without warning
for fn in dir_nibs + nib_fns:
# open the nib file
nib_path, nib_fn, nib_base, nib_ext = get_file_parts(fn)
fn, nib_f = _nib_fd(fn)
self._db_map[nib_base] = nib_f
# store some info
self.db_info[nib_base]['path'] = fn
nbases = validate_nib_file(self._db_map[nib_base])
self.db_info[nib_base]['nbases'] = nbases
def __init__(self,nib_fns=[],nib_dirs=[]) :
'''*nib_fns* is a list of paths to specific .nib files desired for the
NibDB. *nib_dirs* is a list of paths to directories containing .nib
files such that every .nib file in the directories is added to the NibDB.
Explicitly passed files take precedence over those found in directories
when sequence names collide.
'''
SeqDB.__init__(self)
# find all *.nib files in the directories passed
if isinstance(nib_dirs,str) : # user just provided single directory
nib_dirs = [nib_dirs]
dir_nibs = []
for d in nib_dirs :
dir_nibs.extend(glob.glob(os.path.join(d,'*.nib')))
if isinstance(nib_fns,str) :
nib_fns = [nib_fns]
# for each .nib found, add to db
# if there is a collision of names, those specified in files (not dirs)
# takes precedence without warning
for fn in dir_nibs+nib_fns :
# open the nib file
nib_path,nib_fn,nib_base,nib_ext = get_file_parts(fn)
fn, nib_f = _nib_fd(fn)
self._db_map[nib_base] = nib_f
# store some info
self.db_info[nib_base]['path'] = fn
nbases = validate_nib_file(self._db_map[nib_base])
self.db_info[nib_base]['nbases'] = nbases
def get_nib_header_batch(nib, queries):
'''Batch method for creating nibFrag headers. *queries* is a list of at most
6-tuples (start,end,strand,name,dbHeader,tbaHeader) representing queries as
specified by the original nibFrag utility. Only start, end, and strand
fields are required.'''
nib_path, nib_f = _nib_fd(nib)
nib_dir, nib_fn, nib_base, nib_ext = get_file_parts(nib_path)
nbases = validate_nib_file(nib)
headers = []
header_tmpl = '>%(name)s%(db)s\n'
for rec in queries:
# set some defaults if they are not supplied
rec = list(rec)
rec.extend([None] * (6 - len(rec)))
start, end, strand, name, dbHeader, tbaHeader = rec
if end == -1:
end = nbases
fields = {}
fields['name'] = nib_path + ':%d-%d' % (start,
end) if not name else name
fields['db'] = ''
if tbaHeader:
# ignored for some reason in nibFrag when tbaHeader supplied and dbHeader is not
fields['name'] = '' if not dbHeader else fields['name']
fields['db'] = '%s.%s:%d-%d of %d' % (tbaHeader, nib_base, start,
end, nbases)
if dbHeader:
fields['db'] = ':%s.%s:%d-%d:%s:%d' % (dbHeader, nib_base, start,
end, strand, nbases)
headers.append(header_tmpl % fields)
return headers
def get_nib_header_batch(nib,queries) :
'''Batch method for creating nibFrag headers. *queries* is a list of at most
6-tuples (start,end,strand,name,dbHeader,tbaHeader) representing queries as
specified by the original nibFrag utility. Only start, end, and strand
fields are required.'''
nib_path, nib_f = _nib_fd(nib)
nib_dir,nib_fn,nib_base,nib_ext = get_file_parts(nib_path)
nbases = validate_nib_file(nib)
headers = []
header_tmpl = '>%(name)s%(db)s\n'
for rec in queries :
# set some defaults if they are not supplied
rec = list(rec)
rec.extend([None]*(6-len(rec)))
start, end, strand, name, dbHeader, tbaHeader = rec
if end == -1 :
end = nbases
fields = {}
fields['name'] = nib_path+':%d-%d'%(start,end) if not name else name
fields['db'] = ''
if tbaHeader :
# ignored for some reason in nibFrag when tbaHeader supplied and dbHeader is not
fields['name'] = '' if not dbHeader else fields['name']
fields['db'] = '%s.%s:%d-%d of %d'%(tbaHeader,nib_base,start,end,nbases)
if dbHeader :
fields['db'] = ':%s.%s:%d-%d:%s:%d'%(dbHeader,nib_base,start,end,strand,nbases)
headers.append(header_tmpl%fields)
return headers
# parse command line arguments
opts, args = parser.parse_args(sys.argv[1:])
if len(args) < 3 :
parser.error('Must provide two non-option arguments')
# filenames and paths
organism, experiment_fn, control_fn = args[0:3]
control_fn = None
if len(args) > 3 :
control_fn = args[2]
org_settings = get_org_settings(organism)
refseq_fn = org_settings['annotation_path']
exp_fpath,exp_fname,exp_fbase,exp_fext = get_file_parts(experiment_fn)
exp_wrk_dir = os.path.abspath('.exp_%s_%s'%(exp_fbase,opts.exp_name))
if control_fn :
cnt_fpath,cnt_fname,cnt_fbase,cnt_fext = get_file_parts(control_fn)
cnt_wrk_dir = os.path.abspath('.cnt_%s_%s'%(cnt_fbase,opts.exp_name))
# the pipeline
pipeline = Pypeline()
steps = []
# split up files
calls = ["mkdir %s"%exp_wrk_dir,
"split_file.py %s --outdir=%s %s"%(opts.split_args,exp_wrk_dir,experiment_fn),]
if control_fn :
if __name__ == '__main__' :
opts,args = parser.parse_args(sys.argv[1:])
if len(args) == 0 :
parser.print_usage()
sys.exit(1)
gerald_fns = args
# step through the files
for gerald_fn in gerald_fns :
path,fn,fnbase,fnext = get_file_parts(gerald_fn)
bed_lines = []
# where to write output to
if opts.stdout :
f_out = sys.stdout
else :
f_out = open(os.path.join(path,fnbase+'.bed'),'w')
# process input
gerald_d = DictReader(open(gerald_fn),fieldnames=GERALDOutput.FIELD_NAMES,delimiter='\t')
for line_d in gerald_d :
if (opts.pass_only and line_d['filtering'] == 'Y' and line_d['match_pos'] != '') or (not opts.pass_only and line_d['match_pos'] != '') :
if opts.chromo_strip is not None :
if __name__ == '__main__' :
opts, args = parser.parse_args(sys.argv[1:])
utility, filenames = args[0], args[1:]
# try to find the utility
abs_utility = os.path.abspath(utility)
if not os.path.exists(abs_utility) :
# look on the path
abs_utility = Popen('which %s'%utility,shell=True,stdout=PIPE,stderr=PIPE).communicate()[0].strip()
if not os.path.exists(abs_utility) :
raise Exception("Utility %s could not be found in the local directory or on the user's path, exiting"%utility)
sys.exit(1)
upath,uname,ubase,uext = get_file_parts(abs_utility)
runscript_tmpl = """
#!/bin/bash
#$ -N %(jobname)s
#$ -S /bin/sh
#$ -o %(stdout)s
#$ -e %(stderr)s
#$ -cwd
export PYTHONPATH=%(pythonpath)s:${PYTHONPATH}
%(utility)s %(utilargs)s %(filename)s"""
suffix = ubase if opts.suffix is None else opts.suffix
for fn in filenames :
nibFrag_grp.add_option('--dbHeader',dest='dbHeader',default=None,help='Add full database info to the header, with or without -name option')
nibFrag_grp.add_option('--tbaHeader',dest='tbaHeader',default=None,help='Format header for compatibility with tba, takes database name as argument')
parser.add_option_group(nibFrag_grp)
if __name__ == '__main__' :
opts, args = parser.parse_args(sys.argv[1:])
if len(args) < 1 :
parser.print_usage()
parser.exit(1)
# setup
nib_path = args[0]
nib_dir,nib_fn,nib_base,nib_ext = get_file_parts(nib_path)
queries = []
if opts.batch :
if len(args) < 2 :
parser.error('Two arguments must be supplied in batch mode')
batch_fns = args[1:]
for fn in batch_fns :
if opts.batch_format == 'BED' :
for bed in BEDFile(fn) :
if bed['chrom'] != nib_base :
warnings.warn('Chromosome in BED line %s does not match file %s, skipping'%(bed['chrom'],nib_base))
else :
filter_str = filter_str.replace('>=','_GTE_')
filter_str = filter_str.replace('<=','_LTE_')
filter_str = filter_str.replace('>','_GT_')
filter_str = filter_str.replace('<','_LT_')
fn_str += '_%s'%filter_str
if opts.top is not None :
fn_str += '_top%d'%opts.top
if len(opts.sort_by) != 0 :
fn_str += '_sortby_%s'%opts.sort_by
if opts.shuffle :
fn_str += '_shuffled'
macs_path,macs_fn,macs_basefn,macs_ext = get_file_parts(args[0])
encoded_fn = os.path.join(macs_path,macs_basefn+fn_str+macs_ext)
if opts.print_encoded_fn :
sys.stdout.write(encoded_fn)
sys.exit(0)
else :
out_f = open(encoded_fn,'w')
elif opts.output :
out_f = open(opts.output,'w')
else :
out_f = sys.stdout
# parse the filters
field_filters = defaultdict(list)
for filter in opts.filters :
field, filter_cond = parse_filter(filter)
from optparse import OptionParser
from chipsequtil import KnownGeneFile, get_file_parts
#args = ['/nfs/genomes/mouse_gp_jul_07/anno/knownGene-2010-07-08.txt','/nfs/genomes/mouse_gp_jul_07/anno/kgXref-2010-07-08.txt']
args = ['/nfs/genomes/mouse_gp_jul_07/anno/knownGene-2010-08-03.gtf','/nfs/genomes/mouse_gp_jul_07/anno/kgXref-2010-07-08.txt']
usage = '%prog <knownGene annotation>'
description = 'convert a UCSC knownGene annotation to GFF'
parser = OptionParser(usage=usage,description=description)
if __name__ == '__main__' :
opts, args = parser.parse_args(args)
kg_path,kg_fn,kg_base,kg_ext = get_file_parts(args[0])
#kg_f = KnownGeneFile(args[0])
# xref for finding gene symbols
kgXref_fn = args[1]
kgXref_fieldnames = ['kgID','mRNA','spID','spDisplayID','geneSymbol','refseq','proAcc','description']
xref_map = dict([(x['kgID'],x) for x in DictReader(open(kgXref_fn),delimiter='\t',fieldnames=kgXref_fieldnames)])
gff_headers = ['seqname','source','feature','start','end','score','strand','frame','attributes']
gff_reader = DictReader(open(args[0]),delimiter='\t',fieldnames=gff_headers)
gff_writer = DictWriter(sys.stdout,delimiter='\t',fieldnames=gff_headers,quotechar='',quoting=QUOTE_NONE,lineterminator='\n')
#gff_writer.writerow(dict([(x,x) for x in gff_headers]))
for i,rec in enumerate(gff_reader) :
#d = {}
#d['seqname'] = rec['chrom']
else :
other_args.append(arg)
opts, args = parser.parse_args(wqsub_args)
if len(other_args) == 0 :
parser.error('Must provide a command')
command = ' '.join(other_args)
runscript_tmpl = templates[opts.drm]
# set up job parameters
cmd_exe = os.path.basename(other_args[0])
jobname = opts.wqsub_name+'_'+cmd_exe
stdout_fn = jobname+opts.wqsub_ext
stdout = os.path.abspath(stdout_fn)
fpath,fname,fbase,fext = get_file_parts(stdout)
stderr = os.path.abspath(os.path.join(jobname+'.err'))
# get the user's current environment and put it into the execute script
if opts.wqsub_no_env :
env_str = '# local environment variables omitted'
else :
env_str = '#%s -V'%drm_symb[opts.drm]
# construct the script
addnl_params = []
for addnl in opts.drm_args :
addnl_params.append('#%s %s'%(drm_symb[opts.drm],addnl))
addnl_params = '\n'.join(addnl_params)
job_dict = {'jobname':fname,
