]
d.pop(0) # remove the header
data = set(d)
print "%d known genes found (using gene symbols)" % (len(data), )
# read the gene symbols
file_symbols = os.path.join(options.output_directory,
'synonyms.txt')
loci = symbols.generate_loci(file_symbols)
genes = symbols.read_genes_symbols(file_symbols)
d = []
for g in data:
ens = symbols.ensembl(g.upper(), genes, loci)
if ens:
d.extend(ens)
data = [line + '\n' for line in d]
data = sorted(set(data))
print "%d known genes found (after conversion to Ensembl ids)" % (
len(data), )
file(os.path.join(options.output_directory, 'oncogenes_more.txt'),
'w').writelines(data)
if os.path.exists(tmp_file):
os.remove(tmp_file)
]
file(os.path.join(options.output_directory, 'version.txt'),
'a').writelines(txt)
#
# read the gene symbols
file_symbols = os.path.join(options.output_directory,
'synonyms.txt')
loci = symbols.generate_loci(file_symbols)
genes = symbols.read_genes_symbols(file_symbols)
d = []
for (g1, g2) in data:
if g1.upper() != g2.upper():
ens1 = symbols.ensembl(g1.upper(), genes, loci)
ens2 = symbols.ensembl(g2.upper(), genes, loci)
if ens1 and ens2:
for e1 in ens1:
for e2 in ens2:
if e1 != e2:
d.append([e1, e2])
data = ['\t'.join(sorted(line)) + '\n' for line in d]
data = sorted(set(data))
print "%d known fusion genes found" % (len(data), )
if not options.skip_filter_overlap:
ens2hugo = dict([
tuple(line.rstrip('\r\n').split('\t')) for line in file(
# read the gene symbols
file_symbols = os.path.join(options.output_directory,
'synonyms.txt')
genes = symbols.read_genes_symbols(file_symbols)
banned = set()
loci = symbols.generate_loci(file_symbols)
#for v in symbols.locus.values():
for v in loci.values():
if v:
n = len(v)
if n > 1:
for i in xrange(n - 1):
for j in xrange(i + 1, n):
if v[i].upper() != v[j].upper():
ens1 = symbols.ensembl(
v[i].upper(), genes, loci)
ens2 = symbols.ensembl(
v[j].upper(), genes, loci)
if ens1 and ens2:
for e1 in ens1:
for e2 in ens2:
if e1 != e2:
(e1, e2) = (
e2, e1
) if e2 < e1 else (e1,
e2)
banned.add((e1, e2))
d = []
for (g1, g2) in fusions:
if (g1.upper() == g2.upper()
# save version of
txt = ['Non-cancer tissues and cells (Babiceanu et al. Nucl. Acids Res. 2016) database version: %s\n' % (today.strftime("%Y-%m-%d"),)]
file(os.path.join(options.output_directory,'version.txt'),'a').writelines(txt)
#
# read the gene symbols
file_symbols = os.path.join(options.output_directory,'synonyms.txt')
loci = symbols.generate_loci(file_symbols)
genes = symbols.read_genes_symbols(file_symbols)
d = []
for (g1,g2) in data:
if g1.upper() != g2.upper():
ens1 = symbols.ensembl(g1.upper(),genes,loci)
ens2 = symbols.ensembl(g2.upper(),genes,loci)
if ens1 and ens2:
for e1 in ens1:
for e2 in ens2:
if e1 != e2:
d.append([e1,e2])
data = ['\t'.join(sorted(line)) + '\n' for line in d]
data = sorted(set(data))
print "%d known fusion genes found" % (len(data),)
if not options.skip_filter_overlap:
ens2hugo = dict([tuple(line.rstrip('\r\n').split('\t')) for line in file(os.path.join(options.output_directory,'genes_symbols.txt'),'r').readlines() if line.rstrip('\r\n')])
# read the gene symbols
file_symbols = os.path.join(options.output_directory,'synonyms.txt')
genes = symbols.read_genes_symbols(file_symbols)
banned = set()
loci = symbols.generate_loci(file_symbols)
#for v in symbols.locus.values():
for v in loci.values():
if v:
n = len(v)
if n > 1:
for i in xrange(n-1):
for j in xrange(i+1,n):
if v[i].upper() != v[j].upper():
ens1 = symbols.ensembl(v[i].upper(),genes,loci)
ens2 = symbols.ensembl(v[j].upper(),genes,loci)
if ens1 and ens2:
for e1 in ens1:
for e2 in ens2:
if e1 != e2:
(e1,e2) = (e2,e1) if e2 < e1 else (e1,e2)
banned.add((e1,e2))
d = []
for (g1,g2) in fusions:
if ( g1.upper() == g2.upper() or ((g1.endswith('@') and g2.endswith('@')) and g1.upper()[:2] == g2.upper()[:2])):
print "%s-%s skipped!" % (g1,g2)
continue
ens1 = symbols.ensembl(g1,genes,loci)
]
data = enlarge.get(options.organism.lower(),[])
if data:
#file_symbols = os.path.join(options.output_directory,'genes_symbols.txt')
file_symbols = os.path.join(options.output_directory,'synonyms.txt')
loci = symbols.generate_loci(file_symbols)
genes = symbols.read_genes_symbols(file_symbols)
d = []
for g in data:
ens = symbols.ensembl(g.upper(),genes,loci)
if ens:
for e in ens:
d.append(e)
else:
print " - Original:",g
data = [line + '\n' for line in d]
data = sorted(set(data))
print "%d genes to be enlarged and covered" % (len(data),)
file(os.path.join(options.output_directory,'enlarge.txt'),'w').writelines(data)
#
data = []
if mygenes:
file_symbols1 = os.path.join(os.path.dirname(options.output),'genes_symbols.txt')
file_symbols2 = os.path.join(os.path.dirname(options.output),'synonyms.txt')
loci1 = symbols.generate_loci(file_symbols1)
loci2 = symbols.generate_loci(file_symbols2)
genes1 = symbols.read_genes_symbols(file_symbols1)
genes2 = symbols.read_genes_symbols(file_symbols2)
d = []
for (g1,g2) in mygenes:
if g1 and g2 and g1.upper() != g2.upper():
ens1 = symbols.ensembl(g1.upper(),genes1,loci1)
ens2 = symbols.ensembl(g2.upper(),genes1,loci1)
if not ens1:
ens1 = symbols.ensembl(g1.upper(),genes2,loci2)
if not ens2:
ens2 = symbols.ensembl(g2.upper(),genes2,loci2)
if ens1 and ens2:
for e1 in ens1:
for e2 in ens2:
if e1 and e2 and e1 != e2:
d.append([e1,e2])
data = ['\t'.join(sorted(line)) + '\n' for line in d]
data = list(set(data))
data = sorted(data)
file_symbols1 = os.path.join(os.path.dirname(options.output),
'genes_symbols.txt')
file_symbols2 = os.path.join(os.path.dirname(options.output),
'synonyms.txt')
loci1 = symbols.generate_loci(file_symbols1)
loci2 = symbols.generate_loci(file_symbols2)
genes1 = symbols.read_genes_symbols(file_symbols1)
genes2 = symbols.read_genes_symbols(file_symbols2)
d = []
for (g1, g2) in mygenes:
if g1 and g2 and g1.upper() != g2.upper():
ens1 = symbols.ensembl(g1.upper(), genes1, loci1)
ens2 = symbols.ensembl(g2.upper(), genes1, loci1)
if not ens1:
ens1 = symbols.ensembl(g1.upper(), genes2, loci2)
if not ens2:
ens2 = symbols.ensembl(g2.upper(), genes2, loci2)
if ens1 and ens2:
for e1 in ens1:
for e2 in ens2:
if e1 and e2 and e1 != e2:
d.append([e1, e2])
data = ['\t'.join(sorted(line)) + '\n' for line in d]
data = list(set(data))
data = sorted(data)
