def test_random_importance():
# check that when aggregating using random importance, all values that
# are in a higher resolution tile are also in the lower resolution
f = tempfile.NamedTemporaryFile(delete=False)
runner = clt.CliRunner()
input_file = op.join(testdir, "sample_data",
"25435_PM15-000877_SM-7QK6O.seg")
result = runner.invoke(
cca.bedfile,
[
input_file,
"--max-per-tile",
"2",
"--importance-column",
"random",
"--assembly",
"b37",
"--has-header",
"--output-file",
f.name,
],
)
# import traceback
a, b, tb = result.exc_info
"""
print("exc_info:", result.exc_info)
print("result:", result)
print("result.output", result.output)
print("result.error", traceback.print_tb(tb))
print("Exception:", a,b)
"""
tsinfo = ctb.tileset_info(f.name)
assert "version" in tsinfo
assert len(tsinfo["header"]) > 0
# check to make sure that tiles in the higher zoom levels
# are all present in lower zoom levels
found = {}
for rect in ctb.tiles(f.name, ["x.5.15"])[0][1]:
found[rect["xStart"]] = False
for rect in ctb.tiles(f.name, ["x.6.30"])[0][1]:
if rect["xStart"] in found:
found[rect["xStart"]] = True
for rect in ctb.tiles(f.name, ["x.6.31"])[0][1]:
if rect["xStart"] in found:
found[rect["xStart"]] = True
for key, value in found.items():
assert value
pass
def test_chromosome_limit():
f = tempfile.NamedTemporaryFile(delete=False)
runner = clt.CliRunner()
input_file = op.join(testdir, "sample_data",
"geneAnnotationsExonsUnions.short.bed")
runner.invoke(
cca.bedfile,
[
input_file,
"--max-per-tile",
"60",
"--importance-column",
"5",
"--assembly",
"hg19",
"--chromosome",
"chr14",
"--output-file",
f.name,
],
)
# TODO: Make assertions about result
# print('output:', result.output, result)
rows = ctb.tiles(f.name, ["x.0.0"])[0][1]
for row in rows:
assert row["fields"][0] == "chr14"
os.remove(f.name)
pass
def test_gene_annotations():
runner = clt.CliRunner()
input_file = op.join(testdir, "sample_data", "exon_unions_mm10.bed")
f = tempfile.NamedTemporaryFile(delete=False)
result = runner.invoke(
cca.bedfile,
[
input_file,
"--max-per-tile",
"20",
"--importance-column",
"5",
"--delimiter",
"\t",
"--assembly",
"mm10",
"--output-file",
f.name,
],
)
# import traceback
a, b, tb = result.exc_info
"""
print("exc_info:", result.exc_info)
print("result:", result)
print("result.output", result.output)
print("result.error", traceback.print_tb(tb))
print("Exception:", a,b)
"""
rows = ctb.tiles(f.name, ["x.0.0"])[0][1]
assert len(rows) == 2
rows = ctb.tiles(f.name, ["x.11.113"])[0][1]
assert rows[0]["fields"][3] == "Lrp1b"
rows = ctb.tiles(f.name, ["x.11.112"])[0][1]
assert rows[0]["fields"][3] == "Lrp1b"
def test_no_chromosome_limit():
f = tempfile.NamedTemporaryFile(delete=False)
runner = clt.CliRunner()
input_file = op.join(testdir, "sample_data",
"geneAnnotationsExonsUnions.short.bed")
result = runner.invoke(
cca.bedfile,
[
input_file,
"--max-per-tile",
"60",
"--importance-column",
"5",
"--assembly",
"hg19",
"--output-file",
f.name,
],
)
# import traceback
"""
print("exc_info:", result.exc_info)
print("result:", result)
print("result.output", result.output)
print("result.error", traceback.print_tb(tb))
print("Exception:", a,b)
"""
a, b, tb = result.exc_info
rows = ctb.tiles(f.name, ["x.0.0"])[0][1]
foundOther = False
for row in rows:
if row["fields"][0] != "chr1":
# print("row", row)
assert row["xStart"] > 200000000
if row["fields"][0] != "chr14":
foundOther = True
break
# make sure there's chromosome other than 14 in the output
assert foundOther
os.remove(f.name)
pass
def generate_tiles(tileset_tile_ids):
'''
Generate a tiles for the give tile_ids.
All of the tile_ids must come from the same tileset. This function
will determine the appropriate handler this tile given the tileset's
filetype and datatype
Parameters
----------
tileset: tilesets.models.Tileset object
The tileset that the tile ids should be retrieved from
tile_ids: [str,...]
A list of tile_ids (e.g. xyx.0.0.1) identifying the tiles
to be retrieved
Returns
-------
tile_list: [(tile_id, tile_data),...]
A list of tile_id, tile_data tuples
'''
tileset, tile_ids, raw = tileset_tile_ids
if tileset.filetype == 'hitile':
return generate_hitile_tiles(tileset, tile_ids)
elif tileset.filetype == 'beddb':
return hgbe.tiles(tileset.datafile.path, tile_ids)
elif tileset.filetype == 'bed2ddb' or tileset.filetype == '2dannodb':
return generate_bed2ddb_tiles(tileset, tile_ids)
elif tileset.filetype == 'geodb':
return generate_bed2ddb_tiles(tileset, tile_ids, hggo.get_tiles)
elif tileset.filetype == 'hibed':
return generate_hibed_tiles(tileset, tile_ids)
elif tileset.filetype == 'cooler':
return hgco.generate_tiles(tileset.datafile.path, tile_ids)
elif tileset.filetype == 'bigwig':
chromsizes = get_chromsizes(tileset)
return hgbi.tiles(tileset.datafile.path, tile_ids, chromsizes=chromsizes)
elif tileset.filetype == 'multivec':
return generate_1d_tiles(
tileset.datafile.path,
tile_ids,
ctmu.get_single_tile)
elif tileset.filetype == 'imtiles':
return hgim.get_tiles(tileset.datafile.path, tile_ids, raw)
else:
return [(ti, {'error': 'Unknown tileset filetype: {}'.format(tileset.filetype)}) for ti in tile_ids]
def test_get_tiles():
filename = "test/sample_data/gene_annotations.short.db"
ctb.tiles(filename, ["x.18.169283"])
def generate_tiles(tileset_tile_ids):
'''
Generate a tiles for the give tile_ids.
All of the tile_ids must come from the same tileset. This function
will determine the appropriate handler this tile given the tileset's
filetype and datatype
Parameters
----------
tileset_tile_ids: tuple
A four-tuple containing the following parameters.
tileset: tilesets.models.Tileset object
The tileset that the tile ids should be retrieved from
tile_ids: [str,...]
A list of tile_ids (e.g. xyx.0.0.1) identifying the tiles
to be retrieved
raw: str or False
The value of the GET request parameter `raw`.
tileset_options: dict or None
An optional dict containing tileset options, including aggregation options.
Returns
-------
tile_list: [(tile_id, tile_data),...]
A list of tile_id, tile_data tuples
'''
tileset, tile_ids, raw, tileset_options = tileset_tile_ids
if tileset.filetype == 'hitile':
return generate_hitile_tiles(tileset, tile_ids)
elif tileset.filetype == 'beddb':
return hgbe.tiles(tileset.datafile.path, tile_ids)
elif tileset.filetype == 'bed2ddb' or tileset.filetype == '2dannodb':
return generate_bed2ddb_tiles(tileset, tile_ids)
elif tileset.filetype == 'geodb':
return generate_bed2ddb_tiles(tileset, tile_ids, hggo.get_tiles)
elif tileset.filetype == 'hibed':
return generate_hibed_tiles(tileset, tile_ids)
elif tileset.filetype == 'cooler':
return hgco.generate_tiles(tileset.datafile.path, tile_ids)
elif tileset.filetype == 'bigwig':
chromsizes = get_chromsizes(tileset)
return hgbi.tiles(tileset.datafile.path,
tile_ids,
chromsizes=chromsizes)
elif tileset.filetype == 'bigbed':
chromsizes = get_chromsizes(tileset)
return hgbb.tiles(tileset.datafile.path,
tile_ids,
chromsizes=chromsizes)
elif tileset.filetype == 'multivec':
return generate_1d_tiles(tileset.datafile.path, tile_ids,
ctmu.get_single_tile, tileset_options)
elif tileset.filetype == 'imtiles':
return hgim.get_tiles(tileset.datafile.path, tile_ids, raw)
elif tileset.filetype == 'bam':
return ctb.tiles(tileset.datafile.path,
tile_ids,
index_filename=tileset.indexfile.path,
max_tile_width=hss.MAX_BAM_TILE_WIDTH)
else:
filetype = tileset.filetype
filepath = tileset.datafile.path
if filetype in hgti.by_filetype:
return hgti.by_filetype[filetype](filepath).tiles(tile_ids)
return [(ti, {
'error':
'Unknown tileset filetype: {}'.format(tileset.filetype)
}) for ti in tile_ids]
def test_get_tiles():
filename = op.join("data", "corrected.geneListwithStrand.bed.multires")
hgbe.tiles(filename, ["x.1.0", "x.1.1"])
def test_name_in_tile():
filename = op.join("data", "geneAnnotationsExonUnions.1000.bed.v3.beddb")
tiles = hgbe.tiles(filename, ["x.1.0", "x.1.1"])
assert "name" in tiles[0][1][0]
def test_get_tiles():
filename = op.join('data', 'corrected.geneListwithStrand.bed.multires')
ret = hgbe.tiles(filename, ['x.1.0', 'x.1.1'])