def test_bigbed_tiles():
filename = op.join(
"data",
"masterlist_DHSs_733samples_WM20180608_all_mean_signal_colorsMax.bed.bb"
)
tileset_info = hgbb.tileset_info(filename)
num_chroms = len(tileset_info["chromsizes"])
base_tile = hgbb.tiles(filename, ["x.0.0"])
base_tile_data = base_tile[0][1]
assert (num_chroms * hgbb.MAX_ELEMENTS) == len(
base_tile_data
), "Number of chromosomes in bigBed file was {}\nExpected: {}\n".format(
len(base_tile_data), (num_chroms * hgbb.MAX_ELEMENTS))
signif_tile = hgbb.tiles(filename, ["x.0.0.significant"])
signif_tile_data = signif_tile[0][1]
assert (num_chroms * hgbb.MAX_ELEMENTS) == len(
signif_tile_data
), "Number of chromosomes in bigBed file was {}\nExpected: {}\n".format(
len(signif_tile_data), (num_chroms * hgbb.MAX_ELEMENTS))
max_elements = [5, 10, 25, 100]
for me in max_elements:
max_elems_tile = hgbb.tiles(filename, ["x.0.0|max:{}".format(me)])
max_elems_tile_data = max_elems_tile[0][1]
for mtd in max_elems_tile_data:
assert len(mtd) <= (
me * hgbb.MAX_ELEMENTS
), "Number of observed elements with max element threshold was {}\nExpected: {}\n".format(
len(mtd), (me * hgbb.MAX_ELEMENTS))
min_max_element_ranges = [(1, 5), (5, 10)]
for mmer in min_max_element_ranges:
min_element = mmer[0]
max_element = mmer[1]
min_max_elems_tile = hgbb.tiles(
filename, ["x.0.0|min:{}|max:{}".format(min_element, max_element)])
min_max_elems_tile_data = min_max_elems_tile[0][1]
mmtdl = len(min_max_elems_tile_data)
assert (
mmtdl >= min_element and mmtdl <= max_element * hgbb.MAX_ELEMENTS
), "Number of observed elements with min/max threshold was {}\nExpected: {} to {}\nAll data length: {}\nAll data: {}\n".format(
mmtdl, min_element, max_element, mmtdl, min_max_elems_tile_data)
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]