def call_cell_barcodes(umi_info_path, gem_group):
""" Call cell barcodes by UMI support.
Args: umi_info_path (str) - path to umi info h5
gem_group (int) - gem group
Returns: (bc_support, cell_bcs, rt, ut)
where bc_support = dict of { barcode: umi_count },
cell_bcs = list(str) of cell barcodes)
rt = read pair per umi threshold used
ut = umi threshold """
# Get umi info for this gem group only
bc_idx = vdj_umi_info.get_column(umi_info_path, 'barcode_idx')
bc_str = vdj_umi_info.get_column(umi_info_path, 'barcodes')
bc_gg = np.array([int(cr_utils.split_barcode_seq(bc)[1]) for bc in bc_str])
bc_in_gg = bc_gg == gem_group
umi_in_gg = bc_in_gg[bc_idx]
umi_read_pairs = vdj_umi_info.get_column(umi_info_path, 'reads')
rpu_threshold, umi_threshold, bc_support, confidence = vdj_stats.call_vdj_cells(
umi_barcode_idx=bc_idx[umi_in_gg],
umi_read_pairs=umi_read_pairs[umi_in_gg],
barcodes=bc_str,
rpu_mix_init_sd=RPU_MIX_INIT_SD,
umi_mix_init_sd=UMI_MIX_INIT_SD,
verbosity=1,
)
cell_bcs = [
bc for bc, umis in bc_support.iteritems() if umis >= umi_threshold
]
return bc_support, cell_bcs, rpu_threshold, umi_threshold, confidence
def call_cell_barcodes(umi_info_path, gem_group):
""" Call cell barcodes by UMI support.
Args: umi_info_path (str) - path to umi info h5
gem_group (int) - gem group
Returns: (bc_support, cell_bcs, rt, ut)
where bc_support = dict of { barcode: umi_count },
cell_bcs = list(str) of cell barcodes)
rt = read pair per umi threshold used
ut = umi threshold """
# Get umi info for this gem group only
bc_str = vdj_umi_info.get_column(umi_info_path, 'barcodes')
bc_gg = np.array([int(cr_utils.split_barcode_seq(bc)[1]) for bc in bc_str])
bc_in_gg = bc_gg == gem_group
umi_info = vdj_umi_info.read_umi_info(umi_info_path)
umi_barcode_idx = []
umi_read_pairs = []
for bc_idx, data_iter in itertools.groupby(itertools.izip(
umi_info['barcode_idx'], umi_info['umi_idx'], umi_info['reads']),
key=lambda x: x[0]):
if not bc_in_gg[bc_idx]:
continue
bc_umi_read_pairs = {}
for _, umi, reads in data_iter:
bc_umi_read_pairs[umi] = bc_umi_read_pairs.get(umi, 0) + reads
for r in bc_umi_read_pairs.itervalues():
umi_barcode_idx.append(bc_idx)
umi_read_pairs.append(r)
rpu_threshold, umi_threshold, bc_support, confidence = vdj_stats.call_vdj_cells(
umi_barcode_idx=np.array(umi_barcode_idx,
dtype=vdj_umi_info.get_dtype('barcode_idx')),
umi_read_pairs=np.array(umi_read_pairs,
dtype=vdj_umi_info.get_dtype('reads')),
barcodes=bc_str,
rpu_mix_init_sd=RPU_MIX_INIT_SD,
umi_mix_init_sd=UMI_MIX_INIT_SD,
verbosity=1,
)
cell_bcs = [
bc for bc, umis in bc_support.iteritems() if umis >= umi_threshold
]
return bc_support, cell_bcs, rpu_threshold, umi_threshold, confidence
def split(args):
""" Chunk the UMI info HDF5 file by gem group """
num_entries = vdj_umi_info.get_num_rows(args.umi_info)
if num_entries > 1e9:
print 'Warning: There are >1e9 entries in the umi_info - this could potentially cause an out-of-memory error.'
# This will cause an OOM if there are >1.5e9 UMIs
barcode_indices = vdj_umi_info.get_column(args.umi_info, 'barcode_idx')
barcodes = vdj_umi_info.get_column(args.umi_info, 'barcodes')
chunks = []
start_row = 0
prev_gem_group = None
prev_barcode_idx = None
for row, barcode_idx in enumerate(barcode_indices):
if barcode_idx == prev_barcode_idx:
continue
_, gem_group = cr_utils.split_barcode_seq(barcodes[barcode_idx])
if prev_gem_group is not None and gem_group != prev_gem_group:
# Write complete chunk
end_row = row
mem_gb = max(
cr_constants.MIN_MEM_GB, 2 * int(
np.ceil(
vdj_umi_info.get_mem_gb(args.umi_info,
start_row=start_row,
end_row=end_row))))
chunks.append({
'gem_group': prev_gem_group,
'start_row': start_row,
'end_row': end_row,
'__mem_gb': mem_gb,
})
start_row = end_row
prev_gem_group = gem_group
prev_barcode_idx = barcode_idx
# Write final chunk
end_row = vdj_umi_info.get_num_rows(args.umi_info)
mem_gb = max(
cr_constants.MIN_MEM_GB, 2 * int(
np.ceil(
vdj_umi_info.get_mem_gb(
args.umi_info, start_row=start_row, end_row=end_row))))
# Handle case where umi info is empty by supplying a dummy gem group
if prev_gem_group is None:
prev_gem_group = args.gem_groups[0]
chunks.append({
'gem_group': prev_gem_group,
'start_row': start_row,
'end_row': end_row,
'__mem_gb': mem_gb,
})
return {'chunks': chunks}