def main():
usage = 'usage: %prog [options] arg'
parser = OptionParser(usage)
parser.add_option('-d', dest='downstream', type='int', default=0, help='Downstream promoter length [Default: %default]')
parser.add_option('-u', dest='upstream', type='int', default=2000, help='Upstream promoter length [Default: %default]')
parser.add_option('-o', dest='output_pre', default='promoter', help='Output file prefix [Default: %default]')
(options,args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide gtf file')
else:
gtf_file = args[0]
gff.promoters(gtf_file, options.upstream, options.downstream, '%s.gff'%options.output_pre)
p = subprocess.Popen('gff2fa.py %s.gff > %s.fa' % (options.output_pre,options.output_pre), shell=True)
os.waitpid(p.pid,0)
def intersect_gene_te(gtf_file, upstream, downstream):
# focus on promoter
tmp_fd, tmp_file = tempfile.mkstemp()
gff.promoters(gtf_file, upstream, downstream, tmp_file)
# intersect genes w/ repeats
# hash transposon nt by gene
gene_trans = {}
p = subprocess.Popen('intersectBed -wo -a %s -b %s' %
(tmp_file, hg19_reps_gff),
shell=True,
stdout=subprocess.PIPE)
line = p.stdout.readline()
while line:
a = line.split('\t')
# get names
gene = gff.gtf_kv(a[8])['transcript_id']
rep_kv = gff.gtf_kv(a[17])
rep = rep_kv['repeat']
fam = rep_kv['family']
# add nt
if gene not in gene_trans:
gene_trans[gene] = {}
gene_trans[gene][(rep, fam)] = gene_trans[gene].get(
(rep, fam), 0) + int(a[18])
gene_trans[gene][('*', fam)] = gene_trans[gene].get(
('*', fam), 0) + int(a[18])
gene_trans[gene][('*', '*')] = gene_trans[gene].get(
('*', '*'), 0) + int(a[18])
line = p.stdout.readline()
p.communicate()
# create a fake family for dTE-lncRNAs
for line in open(gtf_file):
a = line.split('\t')
tid = gff.gtf_kv(a[8])['transcript_id']
if tid not in gene_trans:
gene_trans[tid] = {('n', 'n'): 1}
return gene_trans
def intersect_gene_te(gtf_file, upstream, downstream):
# focus on promoter
tmp_fd, tmp_file = tempfile.mkstemp()
gff.promoters(gtf_file, upstream, downstream, tmp_file)
# intersect genes w/ repeats
# hash transposon nt by gene
gene_trans = {}
p = subprocess.Popen('intersectBed -wo -a %s -b %s' % (tmp_file,hg19_reps_gff), shell=True, stdout=subprocess.PIPE)
line = p.stdout.readline()
while line:
a = line.split('\t')
# get names
gene = gff.gtf_kv(a[8])['transcript_id']
rep_kv = gff.gtf_kv(a[17])
rep = rep_kv['repeat']
fam = rep_kv['family']
# add nt
if gene not in gene_trans:
gene_trans[gene] = {}
gene_trans[gene][(rep,fam)] = gene_trans[gene].get((rep,fam),0) + int(a[18])
gene_trans[gene][('*',fam)] = gene_trans[gene].get(('*',fam),0) + int(a[18])
gene_trans[gene][('*','*')] = gene_trans[gene].get(('*','*'),0) + int(a[18])
line = p.stdout.readline()
p.communicate()
# create a fake family for dTE-lncRNAs
for line in open(gtf_file):
a = line.split('\t')
tid = gff.gtf_kv(a[8])['transcript_id']
if tid not in gene_trans:
gene_trans[tid] = {('n','n'):1}
return gene_trans
