print >> sys.stderr, "Fixing PSL..."
ft_name_1 = give_me_temp_filename(tmp_dir=options.tmp_dir)
fix_short_blocks(options.input_filename,
ft_name_1,
threshold=options.anchor,
mismatches=options.mismatches)
# for line in file(ft_name_1,'r'):
# os.write(2,line)
print >> sys.stderr, "Sorting PSL..."
ft_name_2 = give_me_temp_filename(tmp_dir=options.tmp_dir)
sort_ttdb.sort_columns(
ft_name_1,
ft_name_2,
columns=
'10,1nd,2n,18n,13', # sequence name, matches, mismatches, count blocks, target sequence
header=False,
ignore_case=False,
tmp_dir=options.tmp_dir,
parallel=cpus)
# for line in file(ft_name_2,'r'):
# os.write(3,line)
delete_file(ft_name_1)
print >> sys.stderr, "Processing PSL..."
data = []
ties = []
if options.same_gene: # or file(ft_name_2,'r').readline().find(';ge=')>-1:
data = contigs_unique_within_same_gene_from(ft_name_2)
else:
ties = ""
cpus = options.processes
if cpus == 0:
cpus = multiprocessing.cpu_count()
# running
print "Fixing..."
ft_name_1 = give_me_temp_filename(tmp_dir = options.tmp_dir)
fix_short_blocks(options.input_filename, ft_name_1, threshold = options.anchor, mismatches = options.mismatches)
print "Sorting..."
ft_name_2 = give_me_temp_filename(tmp_dir = options.tmp_dir)
sort_ttdb.sort_columns(ft_name_1,
ft_name_2,
columns = '10,1nd,2n,18n', # sequence name, matches, mismatches, count blocks
header = False,
ignore_case = False,
tmp_dir = options.tmp_dir,
parallel = cpus
)
delete_file(ft_name_1)
print "Processing..."
data=[]
if options.same_gene: # or file(ft_name_2,'r').readline().find(';ge=')>-1:
data = contigs_unique_within_same_gene_from(ft_name_2)
else:
data = contigs_unique_from(ft_name_2)
ft_name_3 = give_me_temp_filename(tmp_dir = options.tmp_dir)
file(ft_name_3,'w').writelines(data)
ft_name_4 = give_me_temp_filename(tmp_dir = options.tmp_dir)