FACSPy.ml.supervisedGating

class FACSPy.ml.supervisedGating(adata)

Class for supervised gating. This class implements the learning of a gating strategy based on pregated samples with according prediction of ungated samples.

Parameters:

adata (AnnData) – The anndata object of shape n_obs x n_vars where rows correspond to cells and columns to the channels.

Return type:

A AnnData object where the identified populations are stored in adata.obsm[“gating”].

Examples

>>> adata = fp.create_dataset([...])
>>> gating = fp.ml.supervisedGating(dataset)
>>> gating.run_data_setup(
...     gated_samples = ["1", "2", "3"],
...     layer = "compensated",
...     scaling = "StandardScaler"
... )
>>> gating.setup_classifier("DecisionTreeClassifier")
>>> gating.tune_hyperparameters(
>>>     method = "HalvingRandomSearchCV",
...     grid = {"max_depth": [10,20,100]}
... )
>>> gating.setup_classifier("DecisionTreeClassifier")
>>> gating.train()
>>> gating.gate_dataset()

Methods

gate_dataset()	Method to apply the classifier to ungated samples and gate these samples.
get_dataset()	Returns a AnnData object
run_data_setup(gated_samples, layer[, ...])	Public method to run the data setup.
sample_cells(sampler)	Method to sample the cells.
setup_classifier(classifier, **kwargs)	Setup method.
train()	Trains the classifier.
tune_hyperparameters(method, grid, ...)	Method to tune hyperparameters of the classifier.