# parse the file with the known fusion genes
data = set()
d = [
line.upper().rstrip("\r\n").split("\t")[1]
for line in file(tmp_file, "r")
]
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), )
#
#
#
print "Reading the input file...", options.input
mygenes = [line.rstrip('\r\n').split('\t') for line in file(options.input,'r').readlines() if line.rstrip('\r\n')]
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)
for gg1 in g1:
for gg2 in g2:
if gg1 and gg2 and gg1 != gg2:
(gg1,gg2) = (gg2,gg1) if gg2 < gg1 else (gg1,gg2)
data.add((gg1,gg2))
print " - found",len(data),"fusions"
# 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]
print "Reading the input file...", options.input
mygenes = [
line.rstrip('\r\n').split('\t')
for line in file(options.input, 'r').readlines() if line.rstrip('\r\n')
]
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)
