def main():
usage = 'usage: %prog [options] <gene/transcript id>'
parser = OptionParser(usage)
parser.add_option('-c', dest='cuff_dir', default='%s/research/common/data/lncrna'%os.environ['HOME'], help='Cufflinks output directory with .fpkm_tracking files [Default: %default]')
parser.add_option('-l', dest='lnc_gtf', default='%s/research/common/data/lncrna/lnc_catalog.gtf'%os.environ['HOME'], help='lncRNA catalog gtf file [Default: %default]')
parser.add_option('-t', dest='transcript_expr', default=False, action='store_true', help='Return transcript expression rather than gene [Default: %default]')
(options,args) = parser.parse_args()
if options.transcript_expr:
cuff = cufflinks.fpkm_tracking('%s/isoforms.fpkm_tracking' % options.cuff_dir)
if args[0].find('XLOC') != -1:
trans_ids = set()
for line in open(options.lnc_gtf):
a = line.split('\t')
kv = gff.gtf_kv(a[8])
if kv['gene_id'] == args[0]:
trans_ids.add(kv['transcript_id'])
else:
trans_ids = [args[0]]
for trans_id in trans_ids:
print '%s:' % trans_id
cuff.gene_expr_print(trans_id)
else:
cuff = cufflinks.fpkm_tracking('%s/genes.fpkm_tracking' % options.cuff_dir)
if args[0].find('XLOC') != -1:
gene_id = args[0]
else:
t2g = gff.t2g(options.lnc_gtf)
gene_id = t2g[args[0]]
cuff.gene_expr_print(gene_id)
def main():
usage = 'usage: %prog [options] <fpkm1_file> <fpkm2_file>'
parser = OptionParser(usage)
parser.add_option('-g', dest='gtf')
parser.add_option('-o', dest='out_dir', default='.')
parser.add_option('-p', dest='pseudocount', default=0.125, type='float')
(options, args) = parser.parse_args()
if len(args) != 2:
parser.error('Must provide two diff files')
else:
fpkm1_file = args[0]
fpkm2_file = args[1]
cuff1 = cufflinks.fpkm_tracking(fpkm1_file)
cuff2 = cufflinks.fpkm_tracking(fpkm2_file)
gtf_genes = set()
if options.gtf:
gtf_genes = gff.gtf_gene_set(options.gtf)
if not os.path.isdir(options.out_dir):
os.mkdir(options.out_dir)
for sample in cuff1.experiments:
# scatter plot fpkm
df = {'fpkm1': [], 'fpkm2': []}
for i in range(len(cuff1.genes)):
if len(gtf_genes) == 0 or cuff1.genes[i] in gtf_genes:
fpkm1 = cuff1.gene_expr_exp(i, sample)
fpkm2 = cuff2.gene_expr_exp(i, sample)
if not math.isnan(fpkm1) and not math.isnan(fpkm2):
df['fpkm1'].append(math.log(options.pseudocount + fpkm1,
2))
df['fpkm2'].append(math.log(options.pseudocount + fpkm2,
2))
r_script = '%s/fpkm_fpkm_scatter.r' % os.environ['RDIR']
out_pdf = '%s/%s_scatter.pdf' % (options.out_dir, sample)
ggplot.plot(r_script, df, [out_pdf])
# compute correlation
cor, p = spearmanr(df['fpkm1'], df['fpkm2'])
report_out = open('%s/%s_report.txt' % (options.out_dir, sample), 'w')
print >> report_out, 'Spearman correlation: %f (%e)' % (cor, p)
report_out.close()
def main():
usage = 'usage: %prog [options] <gtf file> <cell type>'
parser = OptionParser(usage)
parser.add_option('-t', dest='expr_t', type='float', default=.1, help='Minimum allowed fpkm value')
(options,args) = parser.parse_args()
if len(args) != 2:
parser.error('Must provide gtf file and cell type')
else:
gtf_file = args[0]
cell_type = args[1]
# get expression data
cuff = cufflinks.fpkm_tracking()
# find cell type experiment index
cell_indexes = [i for i in range(len(cuff.experiments)) if cuff.experiments[i]==cell_type]
if len(cell_indexes) == 0:
parser.error('Cell type %s does not match any quantified experiments' % cell_type)
else:
cell_i = cell_indexes[0]
# parser gtf file
for line in open(gtf_file):
a = line.split('\t')
gene_id = gff.gtf_kv(a[8])['gene_id']
expr_vec = cuff.gene_expr(gene_id)
if expr_vec[cell_i] > options.expr_t:
print line,
def main():
usage = 'usage: %prog [options] <fpkm1_file> <fpkm2_file>'
parser = OptionParser(usage)
parser.add_option('-g', dest='gtf')
parser.add_option('-o', dest='out_dir', default='.')
parser.add_option('-p', dest='pseudocount', default=0.125, type='float')
(options,args) = parser.parse_args()
if len(args) != 2:
parser.error('Must provide two diff files')
else:
fpkm1_file = args[0]
fpkm2_file = args[1]
cuff1 = cufflinks.fpkm_tracking(fpkm1_file)
cuff2 = cufflinks.fpkm_tracking(fpkm2_file)
gtf_genes = set()
if options.gtf:
gtf_genes = gff.gtf_gene_set(options.gtf)
if not os.path.isdir(options.out_dir):
os.mkdir(options.out_dir)
for sample in cuff1.experiments:
# scatter plot fpkm
df = {'fpkm1':[], 'fpkm2':[]}
for i in range(len(cuff1.genes)):
if len(gtf_genes) == 0 or cuff1.genes[i] in gtf_genes:
fpkm1 = cuff1.gene_expr_exp(i, sample)
fpkm2 = cuff2.gene_expr_exp(i, sample)
if not math.isnan(fpkm1) and not math.isnan(fpkm2):
df['fpkm1'].append(math.log(options.pseudocount+fpkm1,2))
df['fpkm2'].append(math.log(options.pseudocount+fpkm2,2))
r_script = '%s/fpkm_fpkm_scatter.r' % os.environ['RDIR']
out_pdf = '%s/%s_scatter.pdf' % (options.out_dir, sample)
ggplot.plot(r_script, df, [out_pdf])
# compute correlation
cor, p = spearmanr(df['fpkm1'], df['fpkm2'])
report_out = open('%s/%s_report.txt' % (options.out_dir,sample), 'w')
print >> report_out, 'Spearman correlation: %f (%e)' % (cor, p)
report_out.close()
def cuff_fpkm(fpkm_file, pseudocount):
cuff = cufflinks.fpkm_tracking(fpkm_tracking_file)
gene_fpkm = {}
for gene_id in cuff.genes:
gene_fpkm[gene_id] = stats.mean([math.log(pseudocount+e,2) for e in cuff.gene_expr(gene_id, not_found=0, fail=0)])
return gene_fpkm
def cuff_fpkm(fpkm_file, pseudocount):
cuff = cufflinks.fpkm_tracking(fpkm_tracking_file)
gene_fpkm = {}
for gene_id in cuff.genes:
gene_fpkm[gene_id] = stats.mean([
math.log(pseudocount + e, 2)
for e in cuff.gene_expr(gene_id, not_found=0, fail=0)
])
return gene_fpkm
def main():
usage = "usage: %prog [options] <fpkm_tracking>"
parser = OptionParser(usage)
parser.add_option("-d", dest="diff_file", help="Limit to significantly differentially expressed genes")
parser.add_option("-g", dest="gtf", help="GTF file of genes to display")
parser.add_option("-m", dest="min_fpkm", default=0.125, help="Minimum FPKM (for logs) [Default: %default]")
parser.add_option("-o", dest="out_pdf", default="cuff_heat.pdf", help="Output PDF [Default: %default]")
parser.add_option("-s", dest="sample", default=1000, help="Sample genes rather than use all [Default: %default]")
(options, args) = parser.parse_args()
if len(args) != 1:
parser.error("Must provide fpkm_tracking")
else:
fpkm_tracking = args[0]
# load expression data
cuff = cufflinks.fpkm_tracking(fpkm_file=fpkm_tracking)
# determine genes
all_genes = set(cuff.genes)
if options.gtf:
all_genes = set()
for line in open(options.gtf):
a = line.split("\t")
all_genes.add(gff.gtf_kv(a[8])["gene_id"])
if options.diff_file:
# limit to differentially expressed genes
diff_genes = find_diff(options.diff_file)
all_genes &= diff_genes
# sample genes to display
if len(all_genes) <= options.sample:
display_genes = all_genes
else:
display_genes = random.sample(all_genes, options.sample)
# build data frame
df = {"Gene": [], "FPKM": [], "Sample": []}
for gene_id in display_genes:
ge = cuff.gene_expr(gene_id)
if not math.isnan(ge[0]):
for i in range(len(cuff.experiments)):
df["Gene"].append(gene_id)
df["Sample"].append(cuff.experiments[i])
df["FPKM"].append(math.log(ge[i] + options.min_fpkm, 2))
# plot
ggplot.plot("%s/cuff_heat.r" % os.environ["RDIR"], df, [options.out_pdf])
def main():
usage = 'usage: %prog [options] <gtf file> <fpkm tracking>'
parser = OptionParser(usage)
#parser.add_option('-m', dest='fpkm_min', type='float', default=0.25, help='Minimum FPKM [Default: %default]')
(options,args) = parser.parse_args()
if len(args) != 2:
parser.error(usage)
else:
gtf_file = args[0]
fpkm_tracking_file = args[1]
# get genes
genes = set()
for line in open(gtf_file):
a = line.split('\t')
genes.add(gff.gtf_kv(a[8])['gene_id'])
# get expression
cuff = cufflinks.fpkm_tracking(fpkm_tracking_file)
log_fpkms = []
for gene_id in genes:
max_fpkm = max(cuff.gene_expr(gene_id))
if max_fpkm > 0:
log_fpkms.append(math.log(max_fpkm,2))
# construct R data objects
fpkms_r = ro.FloatVector(log_fpkms)
df = ro.DataFrame({'fpkm':fpkms_r})
# construct plot
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='fpkm') + \
ggplot2.geom_histogram(binwidth=0.2)
# save to file
gtf_pre = os.path.splitext(gtf_file)[0]
grdevices.pdf(file='%s_fpkmhist.pdf' % gtf_pre)
gp.plot()
grdevices.dev_off()
def main():
usage = "usage: %prog [options] <gtf file> <fpkm tracking>"
parser = OptionParser(usage)
# parser.add_option('-m', dest='fpkm_min', type='float', default=0.25, help='Minimum FPKM [Default: %default]')
(options, args) = parser.parse_args()
if len(args) != 2:
parser.error(usage)
else:
gtf_file = args[0]
fpkm_tracking_file = args[1]
# get genes
genes = set()
for line in open(gtf_file):
a = line.split("\t")
genes.add(gff.gtf_kv(a[8])["gene_id"])
# get expression
cuff = cufflinks.fpkm_tracking(fpkm_tracking_file)
log_fpkms = []
for gene_id in genes:
max_fpkm = max(cuff.gene_expr(gene_id))
if max_fpkm > 0:
log_fpkms.append(math.log(max_fpkm, 2))
# construct R data objects
fpkms_r = ro.FloatVector(log_fpkms)
df = ro.DataFrame({"fpkm": fpkms_r})
# construct plot
gp = ggplot2.ggplot(df) + ggplot2.aes_string(x="fpkm") + ggplot2.geom_histogram(binwidth=0.2)
# save to file
gtf_pre = os.path.splitext(gtf_file)[0]
grdevices.pdf(file="%s_fpkmhist.pdf" % gtf_pre)
gp.plot()
grdevices.dev_off()
def main():
usage = 'usage: %prog [options] <gtf file> <cell type>'
parser = OptionParser(usage)
parser.add_option('-t',
dest='expr_t',
type='float',
default=.1,
help='Minimum allowed fpkm value')
(options, args) = parser.parse_args()
if len(args) != 2:
parser.error('Must provide gtf file and cell type')
else:
gtf_file = args[0]
cell_type = args[1]
# get expression data
cuff = cufflinks.fpkm_tracking()
# find cell type experiment index
cell_indexes = [
i for i in range(len(cuff.experiments))
if cuff.experiments[i] == cell_type
]
if len(cell_indexes) == 0:
parser.error('Cell type %s does not match any quantified experiments' %
cell_type)
else:
cell_i = cell_indexes[0]
# parser gtf file
for line in open(gtf_file):
a = line.split('\t')
gene_id = gff.gtf_kv(a[8])['gene_id']
expr_vec = cuff.gene_expr(gene_id)
if expr_vec[cell_i] > options.expr_t:
print line,
def main():
usage = 'usage: %prog [options] <ref_gtf>'
parser = OptionParser(usage)
#parser.add_option()
parser.add_option('-d', dest='downstream', type='int', default=1000, help='Downstream bp for promoters [Default: %default]')
parser.add_option('-f', dest='fpkm_tracking', help='Use cufflinks FPKM estimates to choose the most expressed isoform')
parser.add_option('-u', dest='upstream', type='int', default=1000, help='Upstream bp for promoters [Default: %default]')
(options,args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide reference GTF')
else:
ref_gtf = args[0]
g2t = gff.g2t(ref_gtf)
transcripts = gff.read_genes(ref_gtf)
source = open(ref_gtf).readline().split()[1]
if options.fpkm_tracking:
iso_fpkm_tracking = cufflinks.fpkm_tracking(options.fpkm_tracking)
for gene_id in g2t:
gene_transcripts = list(g2t[gene_id])
gene_strand = transcripts[gene_transcripts[0]].strand
if gene_strand not in ['+','-']:
print('WARNING: %s discluded for lack of strand' % gene_id, file=sys.stderr)
continue
# choose TSS
if options.fpkm_tracking:
# find most expressed isoform
promoter_tid = gene_transcripts[0]
max_fpkm = stats.geo_mean([1+fpkm for fpkm in iso_fpkm_tracking.gene_expr(promoter_tid)])
for transcript_id in gene_transcripts[1:]:
transcript_fpkm = stats.geo_mean([1+fpkm for fpkm in iso_fpkm_tracking.gene_expr(transcript_id)])
if math.isnan(max_fpkm) or transcript_fpkm > max_fpkm:
promoter_tid = transcript_id
max_fpkm = transcript_fpkm
# get isoform tss
if gene_strand == '+':
tss = transcripts[promoter_tid].exons[0].start
else:
tss = transcripts[promoter_tid].exons[-1].end
else:
# find most upstream tss
promoter_tid = gene_transcripts[0]
if gene_strand == '+':
upstream_tss = transcripts[promoter_tid].exons[0].start
else:
upstream_tss = transcripts[promoter_tid].exons[-1].end
for transcript_id in gene_transcripts[1:]:
if gene_strand == '+':
transcript_pos = transcripts[transcript_id].exons[0].start
if transcript_pos < upstream_tss:
promoter_tid = transcript_id
upstream_tss = transcript_pos
else:
transcript_pos = transcripts[transcript_id].exons[-1].end
if transcript_pos > upstream_tss:
promoter_tid = transcript_id
upstream_tss = transcript_pos
tss = upstream_tss
# print promoter from the tss
if gene_strand == '+':
if tss - options.upstream < 1:
print('WARNING: %s discluded for nearness to chromosome end' % gene_id, file=sys.stderr)
else:
tx = transcripts[promoter_tid]
cols = [tx.chrom, source, 'promoter', str(tss-options.upstream), str(tss+options.downstream), '.', tx.strand, '.', gff.kv_gtf(tx.kv)]
print('\t'.join(cols))
else:
if tss - options.downstream < 1:
print('WARNING: %s discluded for nearness to chromosome end' % gene_id, file=sys.stderr)
else:
tx = transcripts[promoter_tid]
cols = [tx.chrom, source, 'promoter', str(tss-options.downstream), str(tss+options.upstream), '.', tx.strand, '.', gff.kv_gtf(tx.kv)]
print('\t'.join(cols))
def main():
usage = 'usage: %prog [options] <fpkm_tracking>'
parser = OptionParser(usage)
parser.add_option('-a', dest='max_fpkm', type='float', help='Maxium log2 FPKM to plot [Default: %d]')
parser.add_option('-d', dest='diff_file', help='Limit to significantly differentially expressed genes')
parser.add_option('-g', dest='gtf', help='GTF file of genes to display')
parser.add_option('-m', dest='min_fpkm', default=0, type='float', help='Minimum FPKM [Default: %default]')
parser.add_option('-p', dest='pseudocount', default=.125, type='float', help='Pseudocount for log FPKM [Default: %default]')
parser.add_option('-o', dest='out_pdf', default='cuff_heat.pdf', help='Output PDF [Default: %default]')
parser.add_option('-s', dest='sample', default=1000, type='int', help='Sample genes rather than use all [Default: %default]')
parser.add_option('-u', dest='uppercase', default=False, action='store_true', help='Uppercase sample labels [Default: %default]')
(options,args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide fpkm_tracking')
else:
fpkm_tracking = args[0]
# load expression data
cuff = cufflinks.fpkm_tracking(fpkm_file=fpkm_tracking)
# determine genes
all_genes = set(cuff.genes)
if options.gtf:
all_genes = set()
for line in open(options.gtf):
a = line.split('\t')
all_genes.add(gff.gtf_kv(a[8])['gene_id'])
if options.diff_file:
# limit to differentially expressed genes
diff_genes = find_diff(options.diff_file)
all_genes &= diff_genes
else:
# at least limit to clean genes
clean_genes = set()
for gene_id in all_genes:
ge = cuff.gene_expr(gene_id)
clean = True
for i in range(len(ge)):
if math.isnan(ge[i]):
clean = False
break
if clean:
clean_genes.add(gene_id)
all_genes &= clean_genes
if options.min_fpkm > 0:
expressed_genes = set()
for gene_id in all_genes:
ge = cuff.gene_expr(gene_id, not_found=0, fail=0)
if max(ge) > options.min_fpkm:
expressed_genes.add(gene_id)
all_genes &= expressed_genes
# sample genes to display
if len(all_genes) <= options.sample:
display_genes = all_genes
else:
display_genes = random.sample(all_genes, options.sample)
# build data frame
df = {'Gene':[], 'FPKM':[], 'Sample':[]}
for gene_id in display_genes:
ge = cuff.gene_expr(gene_id, not_found=0, fail=0)
for i in range(len(cuff.experiments)):
df['Gene'].append(gene_id)
df['Sample'].append(cuff.experiments[i])
if options.uppercase:
df['Sample'][-1] = df['Sample'][-1].upper()
logfpkm = np.log2(ge[i]+options.pseudocount)
if options.max_fpkm:
logfpkm = min(options.max_fpkm, logfpkm)
df['FPKM'].append(logfpkm)
# plot
out_df = '%s.df' % options.out_pdf[:-4]
ggplot.plot('%s/cuff_heat.r' % os.environ['RDIR'], df, [options.out_pdf], df_file=out_df)
def main():
usage = 'usage: %prog [options] <fpkm_tracking>'
parser = OptionParser(usage)
parser.add_option('-a',
dest='max_fpkm',
type='float',
help='Maxium log2 FPKM to plot [Default: %d]')
parser.add_option(
'-d',
dest='diff_file',
help='Limit to significantly differentially expressed genes')
parser.add_option('-g', dest='gtf', help='GTF file of genes to display')
parser.add_option('-m',
dest='min_fpkm',
default=0,
type='float',
help='Minimum FPKM [Default: %default]')
parser.add_option('-p',
dest='pseudocount',
default=.125,
type='float',
help='Pseudocount for log FPKM [Default: %default]')
parser.add_option('-o',
dest='out_pdf',
default='cuff_heat.pdf',
help='Output PDF [Default: %default]')
parser.add_option(
'-s',
dest='sample',
default=1000,
type='int',
help='Sample genes rather than use all [Default: %default]')
parser.add_option('-u',
dest='uppercase',
default=False,
action='store_true',
help='Uppercase sample labels [Default: %default]')
(options, args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide fpkm_tracking')
else:
fpkm_tracking = args[0]
# load expression data
cuff = cufflinks.fpkm_tracking(fpkm_file=fpkm_tracking)
# determine genes
all_genes = set(cuff.genes)
if options.gtf:
all_genes = set()
for line in open(options.gtf):
a = line.split('\t')
all_genes.add(gff.gtf_kv(a[8])['gene_id'])
if options.diff_file:
# limit to differentially expressed genes
diff_genes = find_diff(options.diff_file)
all_genes &= diff_genes
else:
# at least limit to clean genes
clean_genes = set()
for gene_id in all_genes:
ge = cuff.gene_expr(gene_id)
clean = True
for i in range(len(ge)):
if math.isnan(ge[i]):
clean = False
break
if clean:
clean_genes.add(gene_id)
all_genes &= clean_genes
if options.min_fpkm > 0:
expressed_genes = set()
for gene_id in all_genes:
ge = cuff.gene_expr(gene_id, not_found=0, fail=0)
if max(ge) > options.min_fpkm:
expressed_genes.add(gene_id)
all_genes &= expressed_genes
# sample genes to display
if len(all_genes) <= options.sample:
display_genes = all_genes
else:
display_genes = random.sample(all_genes, options.sample)
# build data frame
df = {'Gene': [], 'FPKM': [], 'Sample': []}
for gene_id in display_genes:
ge = cuff.gene_expr(gene_id, not_found=0, fail=0)
for i in range(len(cuff.experiments)):
df['Gene'].append(gene_id)
df['Sample'].append(cuff.experiments[i])
if options.uppercase:
df['Sample'][-1] = df['Sample'][-1].upper()
logfpkm = np.log2(ge[i] + options.pseudocount)
if options.max_fpkm:
logfpkm = min(options.max_fpkm, logfpkm)
df['FPKM'].append(logfpkm)
# plot
out_df = '%s.df' % options.out_pdf[:-4]
ggplot.plot('%s/cuff_heat.r' % os.environ['RDIR'],
df, [options.out_pdf],
df_file=out_df)
def main():
usage = 'usage: %prog [options] <ref_gtf>'
parser = OptionParser(usage)
#parser.add_option()
parser.add_option('-d',
dest='downstream',
type='int',
default=1000,
help='Downstream bp for promoters [Default: %default]')
parser.add_option(
'-f',
dest='fpkm_tracking',
help='Use cufflinks FPKM estimates to choose the most expressed isoform'
)
parser.add_option('-u',
dest='upstream',
type='int',
default=1000,
help='Upstream bp for promoters [Default: %default]')
(options, args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide reference GTF')
else:
ref_gtf = args[0]
g2t = gff.g2t(ref_gtf)
transcripts = gff.read_genes(ref_gtf)
source = open(ref_gtf).readline().split()[1]
if options.fpkm_tracking:
iso_fpkm_tracking = cufflinks.fpkm_tracking(options.fpkm_tracking)
for gene_id in g2t:
gene_transcripts = list(g2t[gene_id])
gene_strand = transcripts[gene_transcripts[0]].strand
if gene_strand not in ['+', '-']:
print >> sys.stderr, 'WARNING: %s discluded for lack of strand' % gene_id
continue
# choose TSS
if options.fpkm_tracking:
# find most expressed isoform
promoter_tid = gene_transcripts[0]
max_fpkm = stats.geo_mean([
1 + fpkm for fpkm in iso_fpkm_tracking.gene_expr(promoter_tid)
])
for transcript_id in gene_transcripts[1:]:
transcript_fpkm = stats.geo_mean([
1 + fpkm
for fpkm in iso_fpkm_tracking.gene_expr(transcript_id)
])
if math.isnan(max_fpkm) or transcript_fpkm > max_fpkm:
promoter_tid = transcript_id
max_fpkm = transcript_fpkm
# get isoform tss
if gene_strand == '+':
tss = transcripts[promoter_tid].exons[0].start
else:
tss = transcripts[promoter_tid].exons[-1].end
else:
# find most upstream tss
promoter_tid = gene_transcripts[0]
if gene_strand == '+':
upstream_tss = transcripts[promoter_tid].exons[0].start
else:
upstream_tss = transcripts[promoter_tid].exons[-1].end
for transcript_id in gene_transcripts[1:]:
if gene_strand == '+':
transcript_pos = transcripts[transcript_id].exons[0].start
if transcript_pos < upstream_tss:
promoter_tid = transcript_id
upstream_tss = transcript_pos
else:
transcript_pos = transcripts[transcript_id].exons[-1].end
if transcript_pos > upstream_tss:
promoter_tid = transcript_id
upstream_tss = transcript_pos
tss = upstream_tss
# print promoter from the tss
if gene_strand == '+':
if tss - options.upstream < 1:
print >> sys.stderr, 'WARNING: %s discluded for nearness to chromosome end' % gene_id
else:
tx = transcripts[promoter_tid]
cols = [
tx.chrom, source, 'promoter',
str(tss - options.upstream),
str(tss + options.downstream), '.', tx.strand, '.',
gff.kv_gtf(tx.kv)
]
print '\t'.join(cols)
else:
if tss - options.downstream < 1:
print >> sys.stderr, 'WARNING: %s discluded for nearness to chromosome end' % gene_id
else:
tx = transcripts[promoter_tid]
cols = [
tx.chrom, source, 'promoter',
str(tss - options.downstream),
str(tss + options.upstream), '.', tx.strand, '.',
gff.kv_gtf(tx.kv)
]
print '\t'.join(cols)
