def get_feature_ref(self):
return FeatureReference.from_hdf5(self.h5[h5_constants.H5_FEATURE_REF_ATTR])
def load_feature_ref_from_h5_group(group):
'''Load just the FeatureRef from an h5py.Group.'''
feature_group = group[h5_constants.H5_FEATURE_REF_ATTR]
return FeatureReference.from_hdf5(feature_group)
def open(filename, mode, feature_ref=None, barcodes=None, library_info=None,
barcode_info=None):
"""Open a molecule info object.
Args:
filename (str): Filename to open or create
mode (str): 'r' for reading, 'w' for writing.
feature_ref (FeatureReference): Required when mode is 'w'.
barcodes (list of str): All possible barcode sequences. Required when mode is 'w'.
library_info (list of dict): Library metadata. Required when mode is 'w'.
barcode_info (BarcodeInfo): Per-barcode metadata.
Returns:
MoleculeInfo: A new object
"""
assert mode == 'r' or mode == 'w'
mc = MoleculeCounter()
if mode == 'w':
if feature_ref is None:
raise ValueError('Feature reference must be specified when opening a molecule info object for writing')
if barcodes is None:
raise ValueError('Barcodes must be specified when opening a molecule info object for writing')
if library_info is None:
raise ValueError('Library info must be specified when opening a molecule info object for writing')
if barcode_info is None:
raise ValueError('Barcode info must be specified when opening a molecule info object for writing')
mc.h5 = h5py.File(filename, 'w')
cr_io.set_hdf5_attr(mc.h5, FILE_VERSION_KEY, CURR_FILE_VERSION)
cr_io.set_hdf5_attr(mc.h5, h5_constants.H5_FILETYPE_KEY, MOLECULE_H5_FILETYPE)
cr_io.set_hdf5_attr(mc.h5, FILE_VERSION_KEY, CURR_FILE_VERSION)
mc.h5.create_group(METRICS_GROUP_NAME)
# Write feature reference
fref_group = mc.h5.create_group(h5_constants.H5_FEATURE_REF_ATTR)
feature_ref.to_hdf5(fref_group)
# Write barcodes
# If there are multiple barcode lengths, use the largest for the numpy dtype.
max_barcode_len = np.max(map(len, barcodes))
barcode_dtype = np.dtype('S%d' % max_barcode_len)
mc.h5.create_dataset('barcodes', data=np.fromiter(barcodes, barcode_dtype, count=len(barcodes)), compression=HDF5_COMPRESSION)
# Write library info
lib_info_json = json.dumps(library_info, indent=4, sort_keys=True)
cr_io.create_hdf5_string_dataset(mc.h5, 'library_info', [lib_info_json])
# Write barcode info
g = mc.h5.create_group(BARCODE_INFO_GROUP_NAME)
MoleculeCounter.save_barcode_info(barcode_info, g)
# Create empty per-molecule datasets
for name, col_type in MOLECULE_INFO_COLUMNS.iteritems():
mc.columns[name] = mc.h5.create_dataset(name, (0,),
maxshape=(None,),
dtype=col_type,
compression=HDF5_COMPRESSION,
chunks=(HDF5_CHUNK_SIZE,))
elif mode == 'r':
mc.h5 = h5py.File(filename, 'r')
try:
mc.file_version = mc.h5.attrs[FILE_VERSION_KEY]
except AttributeError:
mc.file_version = 1 # V1 doesn't have version field
if mc.file_version < CURR_FILE_VERSION:
raise ValueError('The molecule info HDF5 file (format version %d) was produced by an older version of Cell Ranger. Reading these files is unsupported.' % mc.file_version)
if mc.file_version > CURR_FILE_VERSION:
raise ValueError('The molecule info HDF5 file (format version %d) was produced by an newer version of Cell Ranger. Reading these files is unsupported.' % mc.file_version)
for key in mc.h5.keys():
if key in MOLECULE_INFO_COLUMNS:
mc.columns[key] = mc.h5[key]
elif key in MOLECULE_REF_COLUMNS:
mc.ref_columns[key] = mc.h5[key]
elif key == h5_constants.H5_FEATURE_REF_ATTR:
mc.feature_reference = FeatureReference.from_hdf5(mc.h5[key])
elif key == METRICS_GROUP_NAME \
or key == BARCODE_INFO_GROUP_NAME:
pass
else:
raise AttributeError("Unrecognized dataset key: %s" % key)
# Load library info
mc.library_info = json.loads(cr_io.read_hdf5_string_dataset(mc.h5['library_info'])[0])
return mc
