def test_anndata_colors_to_cxg_colors(self):
# test standard behavior
adata = self._get_h5ad()
self.assertEqual(convert_anndata_category_colors_to_cxg_category_colors(adata), pbmc3k_colors)
# test that invalid color formats raise an exception
adata.uns["louvain_colors"][0] = "#NOTCOOL"
with self.assertRaises(ColorFormatException):
convert_anndata_category_colors_to_cxg_category_colors(adata)
# test that colors without a matching obs category are skipped
adata = self._get_h5ad()
del adata.obs["louvain"]
self.assertEqual(convert_anndata_category_colors_to_cxg_category_colors(adata), {})
def generate_cxg_metadata(self, convert_anndata_colors_to_cxg_colors):
"""
Return a dictionary containing metadata about CXG dataset. This include data about the version as well as
Corpora schema properties if they exist, among other pieces of metadata.
"""
cxg_group_metadata = {
"cxg_version":
CxgConstants.CXG_VERSION,
"cxg_properties":
json.dumps({
"title": self.dataset_title,
"about": self.dataset_about
}),
}
if self.corpora_properties is not None:
cxg_group_metadata["corpora"] = json.dumps(self.corpora_properties)
if convert_anndata_colors_to_cxg_colors:
try:
cxg_group_metadata["cxg_category_colors"] = json.dumps(
convert_anndata_category_colors_to_cxg_category_colors(
self.anndata))
except ColorFormatException:
logging.warning(
"Failed to extract colors from H5AD file! Fix the H5AD file or rerun with "
"--disable-custom-colors. See help for more details.")
return cxg_group_metadata
def write_cxg(
adata, container, title, var_names=None, obs_names=None, about=None, extract_colors=False, sparse_threshold=5.0
):
if not adata.var.index.is_unique:
raise ValueError("Variable index is not unique - unable to convert.")
if not adata.obs.index.is_unique:
raise ValueError("Observation index is not unique - unable to convert.")
"""
TileDB bug TileDB-Inc/TileDB#1575 requires that we sanitize all column names
prior to saving. This can be reverted when the bug is fixed.
"""
log(0, "Warning: sanitizing all dataframe column names.")
clean_all_column_names(adata)
ctx = tiledb.Ctx(
{
"sm.num_reader_threads": 32,
"sm.num_writer_threads": 32,
"sm.consolidation.buffer_size": 1 * 1024 * 1024 * 1024,
}
)
tiledb.group_create(container, ctx=ctx)
log(1, f"\t...group created, with name {container}")
# dataset metadata
metadata_dict = dict(cxg_version=CXG_VERSION, cxg_properties=json.dumps({"title": title, "about": about}))
if extract_colors:
try:
metadata_dict["cxg_category_colors"] = json.dumps(
convert_anndata_category_colors_to_cxg_category_colors(adata)
)
except ColorFormatException:
log(
0,
"Warning: failed to extract colors from h5ad file! "
"Fix the h5ad file or rerun with --disable-custom-colors. See help for details.",
)
save_metadata(container, metadata_dict)
log(1, "\t...dataset metadata saved")
# var/gene dataframe
save_dataframe(container, "var", adata.var, var_names, ctx=ctx)
log(1, "\t...var dataframe created")
# obs/cell dataframe
save_dataframe(container, "obs", adata.obs, obs_names, ctx=ctx)
log(1, "\t...obs dataframe created")
# embeddings
e_container = f"{container}/emb"
tiledb.group_create(e_container, ctx=ctx)
save_embeddings(e_container, adata, ctx)
log(1, "\t...embeddings created")
# X matrix
save_X(container, adata.X, ctx, sparse_threshold)
log(1, "\t...X created")
def get_colors(self):
return convert_anndata_category_colors_to_cxg_category_colors(
self.data)
