mirror of
https://github.com/chanzuckerberg/cellxgene.git
synced 2026-09-17 05:47:58 +08:00
75cb513dd9
* fix mispelling * re-implement re-embedding * always load base embedding to fetch counts * format * lint * fix tests * lint * fix accept handling * test log * more debug * more * more * more * more * remove logging * logging * jsonify * remove debugging logs * lint * clean up errors a bit * fix issue found in PR review * PR review changes
54 lines
1.7 KiB
Python
54 lines
1.7 KiB
Python
import importlib
|
|
import numpy as np
|
|
|
|
"""
|
|
Wrapper for various scanpy modules. Will raise NotImplementedError if the scanpy
|
|
module is not installed/available
|
|
"""
|
|
|
|
|
|
def get_scanpy_module():
|
|
try:
|
|
sc = importlib.import_module("scanpy")
|
|
# Future: we could enforce versions here, eg, lookat sc.__version__
|
|
return sc
|
|
except ModuleNotFoundError as e:
|
|
raise NotImplementedError("Please install scanpy to enable UMAP re-embedding") from e
|
|
except Exception as e:
|
|
# will capture other ImportError corner cases
|
|
raise NotImplementedError() from e
|
|
|
|
|
|
def scanpy_umap(adata, obs_mask=None, pca_options={}, neighbors_options={}, umap_options={}):
|
|
"""
|
|
Given adata and an obs mask, return a new embedding for adata[obs_mask, :]
|
|
as an ndarray of shape (len(obs_mask), N), where N>=2.
|
|
|
|
Do NOT mutate adata.
|
|
"""
|
|
|
|
# backed mode is incompatible with the current implementation
|
|
if adata.isbacked:
|
|
raise NotImplementedError("Backed mode is incompatible with re-embedding")
|
|
|
|
# safely get scanpy module, which may not be present.
|
|
sc = get_scanpy_module()
|
|
|
|
# https://github.com/theislab/anndata/issues/311
|
|
obs_mask = slice(None) if obs_mask is None else obs_mask
|
|
adata = adata[obs_mask, :].copy()
|
|
|
|
for k in list(adata.obsm.keys()):
|
|
del adata.obsm[k]
|
|
for k in list(adata.uns.keys()):
|
|
del adata.uns[k]
|
|
|
|
sc.pp.pca(adata, zero_center=None, n_comps=min(adata.n_obs - 1, 50), **pca_options)
|
|
sc.pp.neighbors(adata, **neighbors_options)
|
|
sc.tl.umap(adata, **umap_options)
|
|
|
|
umap = adata.obsm["X_umap"]
|
|
result = np.full((obs_mask.shape[0], umap.shape[1]), np.NaN)
|
|
result[obs_mask] = umap
|
|
return result
|