def normalize(adata: scanpy.AnnData,
filter_min_counts=None,
size_factors=False,
scale_input=False,
logtrans_input=False):
if filter_min_counts:
scanpy.pp.filter_genes(adata, min_counts=filter_min_counts)
scanpy.pp.filter_cells(adata, min_counts=filter_min_counts)
adata.raw = adata
dataset = GeneExpressionDataset()
dataset.from_data(adata.X, raw=adata.raw.X)
if size_factors:
scanpy.pp.normalize_per_cell(adata)
size_factor_cell = dataset.nb_cell_counts / np.median(
dataset.nb_cell_counts)
dataset.initialize_cell_attribute("size_factor",
size_factor_cell.reshape((-1, 1)))
if logtrans_input:
scanpy.pp.log1p(adata)
if scale_input:
scanpy.pp.scale(adata)
dataset.data = adata.X
obs_index = adata.obs.columns
for i, index in enumerate(obs_index):
dataset.initialize_cell_attribute(index, adata.obs.iloc[:, i].values)
return dataset
def postprocess_mnnpy(adata, bdata):
""" postprocessing to generate a newly functional AnnData object
After running mnnpy_mnncorrect we obtain ann AnnData object bdata. Since mnn_correct automatically
truncates all the genes contained in .raw to contain only the highly variable genes this function
creates a new AnnData object that contains .X from bdata but .raw from AnnData (which still contains all the
genes, not only the highly variable ones).
Before creation of the new AnnData object the matrices are sorted according to cellbarcode so
that we ensure the labelings are correct.
parameters
----------
adata:
the uncorrected AnnData object
bdata:
the batch correted AnnData object
returns
-------
AnnData
AnnData object with adata.X containing the corrected values and .raw all of the original values
"""
corrected_matrix = DataFrame(data = bdata.X, index = bdata.obs_names.tolist(), columns = bdata.var_names.tolist())
corrected_matrix.sort_index(inplace=True)
new_adata = AnnData(corrected_matrix.values)
new_adata.obs = bdata.obs.sort_index()
new_adata.var_names = bdata.var_names
new_adata.obs_names = bdata.obs_names.sort_values()
new_adata.var = bdata.var
#need to sort raw object to match the batch corrected order
raw_matrix = DataFrame(data=(adata.raw.X.todense() if scipy.sparse.issparse(adata.raw.X) else adata.raw.X), index=adata.obs_names.tolist(), columns=adata.raw.var_names.tolist())
raw_matrix.sort_index(inplace=True)
#recreate raw
raw = AnnData(raw_matrix.values)
raw.var_names = adata.raw.var_names
raw.obs_names = adata.obs_names.sort_values()
raw.var = adata.raw.var
#add raw back in
new_adata.raw = raw
#ensure that indices are preserved
adata.obs_names = adata.obs.CELL
adata.obs.index = adata.obs.CELL
return(new_adata)