Self Supervised Tools for Single Cell Data
Project description
scself
Self Supervised Tools for Single Cell Data
Molecular Cross-Validation for PCs arXiv manuscript
mcv(
count_data,
n=1,
n_pcs=100,
random_seed=800,
p=0.5,
metric='mse',
standardization_method='log',
metric_kwargs={},
silent=False,
verbose=None,
zero_center=False
)
Noise2Self for kNN selection arXiv manuscript
def noise2self(
count_data,
neighbors=None,
npcs=None,
metric='euclidean',
loss='mse',
loss_kwargs={},
return_errors=False,
connectivity=False,
standardization_method='log',
pc_data=None,
chunk_size=10000,
verbose=None
)
Implemented as in DEWÄKSS
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
scself-0.4.0.tar.gz
(26.1 kB
view hashes)
Built Distribution
scself-0.4.0-py3-none-any.whl
(36.4 kB
view hashes)