def test_clodius_aggregate_bedpe2():
'''Use galGal6 chromsizes file'''
input_file = op.join(testdir, 'sample_data', 'galGal6.bed')
chromsizes_file = op.join(testdir, 'sample_data', 'galGal6.chrom.sizes')
expected_file = op.join(testdir, 'sample_data', 'galGal6.bed.multires.db')
with tempfile.TemporaryDirectory() as tmpdirname:
output_file = op.join(tmpdirname, 'blah.bed2ddb')
# the test is here to ensure that this doesn't raise an error
cca._bedpe(input_file, output_file, None,
chr1_col=1, chr2_col=1,
from1_col=2, from2_col=2,
to1_col=3, to2_col=3,
importance_column=None,
chromosome=None,
chromsizes_filename=chromsizes_file,
max_per_tile=100,
tile_size=1024,
has_header=True)
tsinfo = cdt.get_tileset_info(output_file)
stat_output = os.stat(output_file)
stat_expected = os.stat(expected_file)
assert tsinfo['max_length'] == 1065365426
assert stat_output.st_size == stat_expected.st_size
def aggregate_file(filename, filetype, assembly, chromsizes_filename,
has_header):
if filetype == 'bedfile':
if assembly is None and chromsizes_filename is None:
print(
'An assembly or set of chromosome sizes is required when importing bed files. Please specify one or the other using the --assembly or --chromsizes-filename parameters',
file=sys.stderr)
return
with tempfile.TemporaryDirectory() as td:
output_file = op.join(td, filename + '.beddb')
print("Aggregating bedfile")
cca._bedfile(filename,
output_file,
assembly,
importance_column='random',
has_header=has_header,
chromosome=None,
max_per_tile=50,
delimiter=None,
chromsizes_filename=chromsizes_filename,
offset=0,
tile_size=1024)
to_import = output_file
# because we aggregated the file, the new filetype is beddb
filetype = 'beddb'
return (to_import, filetype)
elif filetype == 'bedpe':
if assembly is None and chromsizes_filename is None:
print(
'An assembly or set of chromosome sizes is required when importing bed files. Please specify one or the other using the --assembly or --chromsizes-filename parameters',
file=sys.stderr)
return
with tempfile.TemporaryDirectory() as td:
output_file = op.join(td, filename + '.beddb')
print("Aggregating bedfile")
cca._bedpe(filename,
output_file,
assembly,
importance_column='random',
has_header=has_header,
chromosome=None,
max_per_tile=50,
chromsizes_filename=chromsizes_filename,
tile_size=1024)
to_import = output_file
# because we aggregated the file, the new filetype is beddb
filetype = 'bed2ddb'
return (to_import, filetype)
else:
return (filename, filetype)
def test_clodius_aggregate_bedpe():
input_file = op.join(testdir, "sample_data", "isidro.bedpe")
with tempfile.TemporaryDirectory() as tmpdirname:
output_file = op.join(tmpdirname, "isidro.bed2ddb")
cca._bedpe(
input_file,
output_file,
"b37",
importance_column=None,
chromosome=None,
max_per_tile=100,
tile_size=1024,
has_header=True,
)
"""
runner = clt.CliRunner()
result = runner.invoke(
cca.bedpe,
[input_file,
'--output-file', output_file,
'--importance-column', 'random',
'--has-header',
'--assembly', 'b37'])
# print('output:', result.output, result)
assert(result.exit_code == 0)
"""
cdt.get_2d_tiles(output_file, 0, 0, 0)
# print("entries:", entries)
cdt.get_tileset_info(output_file)
# TODO: Make assertions about result
# print('tileset_info', tileset_info)
cdt.get_2d_tiles(output_file, 1, 0, 0, numx=2, numy=2)
# TODO: Make assertions about result
# print("entries:", entries)
cdt.get_tileset_info(output_file)
def test_clodius_aggregate_bedpe():
input_file = op.join(testdir, 'sample_data', 'isidro.bedpe')
output_file = '/tmp/isidro.bed2ddb'
cca._bedpe(input_file,
output_file,
'b37',
importance_column=None,
chromosome=None,
max_per_tile=100,
tile_size=1024,
has_header=True)
"""
runner = clt.CliRunner()
result = runner.invoke(
cca.bedpe,
[input_file,
'--output-file', output_file,
'--importance-column', 'random',
'--has-header',
'--assembly', 'b37'])
#print('output:', result.output, result)
assert(result.exit_code == 0)
"""
entries = cdt.get_2d_tiles(output_file, 0, 0, 0)
#print("entries:", entries)
tileset_info = cdt.get_tileset_info(output_file)
#print('tileset_info', tileset_info)
entries = cdt.get_2d_tiles(output_file, 1, 0, 0, numx=2, numy=2)
#print("entries:", entries)
tileset_info = cdt.get_tileset_info(output_file)
def aggregate_file(filename, filetype, assembly, chromsizes_filename,
has_header, no_upload, tmp_dir):
if filetype == 'bedfile':
if no_upload:
raise Exception(
"Bedfile files need to be aggregated and cannot be linked. Consider not using the --link-file option",
file=sys.stderr)
if assembly is None and chromsizes_filename is None:
print(
'An assembly or set of chromosome sizes is required when importing bed files. Please specify one or the other using the --assembly or --chromsizes-filename parameters',
file=sys.stderr)
return
output_file = op.join(tmp_dir, filename + '.beddb')
print("Aggregating bedfile")
cca._bedfile(filename,
output_file,
assembly,
importance_column='random',
has_header=has_header,
chromosome=None,
max_per_tile=50,
delimiter=None,
chromsizes_filename=chromsizes_filename,
offset=0,
tile_size=1024)
to_import = output_file
# because we aggregated the file, the new filetype is beddb
filetype = 'beddb'
return (to_import, filetype)
elif filetype == 'bedpe':
if no_upload:
raise Exception(
"Bedpe files need to be aggregated and cannot be linked. Consider not using the --link-file option",
file=sys.stderr)
if assembly is None and chromsizes_filename is None:
print(
'An assembly or set of chromosome sizes is required when importing bed files. Please specify one or the other using the --assembly or --chromsizes-filename parameters',
file=sys.stderr)
return
output_file = op.join(tmp_dir, filename + '.bed2ddb')
print("Aggregating bedpe")
cca._bedpe(filename,
output_file,
assembly,
importance_column='random',
has_header=has_header,
chromosome=None,
max_per_tile=50,
chromsizes_filename=chromsizes_filename,
tile_size=1024)
to_import = output_file
# because we aggregated the file, the new filetype is beddb
filetype = 'bed2ddb'
return (to_import, filetype)
else:
return (filename, filetype)