scvi.external.CellAssign#

class scvi.external.CellAssign(adata, cell_type_markers, **model_kwargs)[source]#

Reimplementation of CellAssign for reference-based annotation [Zhang et al., 2019].

Parameters:

adata (AnnData) – single-cell AnnData object that has been registered via setup_anndata(). The object should be subset to contain the same genes as the cell type marker dataframe.
cell_type_markers (DataFrame) – Binary marker gene DataFrame of genes by cell types. Gene names corresponding to adata.var_names should be in DataFrame index, and cell type labels should be the columns.
**model_kwargs – Keyword args for CellAssignModule

Examples

>>> adata = scvi.data.read_h5ad(path_to_anndata)
>>> library_size = adata.X.sum(1)
>>> adata.obs["size_factor"] = library_size / np.mean(library_size)
>>> marker_gene_mat = pd.read_csv(path_to_marker_gene_csv)
>>> bdata = adata[:, adata.var.index.isin(marker_gene_mat.index)].copy()
>>> CellAssign.setup_anndata(bdata, size_factor_key="size_factor")
>>> model = CellAssign(bdata, marker_gene_mat)
>>> model.train()
>>> predictions = model.predict(bdata)

Notes

Size factors in the R implementation of CellAssign are computed using scran. An approximate approach computes the sum of UMI counts (library size) over all genes and divides by the mean library size.

Attributes table#

`adata`	Data attached to model instance.
`adata_manager`	Manager instance associated with self.adata.
`device`	The current device that the module's params are on.
`history`	Returns computed metrics during training.
`is_trained`	Whether the model has been trained.
`test_indices`	Observations that are in test set.
`train_indices`	Observations that are in train set.
`validation_indices`	Observations that are in validation set.

Methods table#

`convert_legacy_save`(dir_path, output_dir_path)	Converts a legacy saved model (<v0.15.0) to the updated save format.
`get_anndata_manager`(adata[, required])	Retrieves the `AnnDataManager` for a given AnnData object specific to this model instance.
`get_from_registry`(adata, registry_key)	Returns the object in AnnData associated with the key in the data registry.
`load`(dir_path[, adata, use_gpu, prefix, ...])	Instantiate a model from the saved output.
`load_registry`(dir_path[, prefix])	Return the full registry saved with the model.
`predict`()	Predict soft cell type assignment probability for each cell.
`register_manager`(adata_manager)	Registers an `AnnDataManager` instance with this model class.
`save`(dir_path[, prefix, overwrite, save_anndata])	Save the state of the model.
`setup_anndata`(adata, size_factor_key[, ...])	Sets up the `AnnData` object for this model.
`to_device`(device)	Move model to device.
`train`([max_epochs, lr, use_gpu, train_size, ...])	Trains the model.
`view_anndata_setup`([adata, ...])	Print summary of the setup for the initial AnnData or a given AnnData object.
`view_setup_args`(dir_path[, prefix])	Print args used to setup a saved model.

Attributes#

adata

CellAssign.adata[source]#

Data attached to model instance.

Return type:: Union[AnnData, MuData]

adata_manager

CellAssign.adata_manager[source]#

Manager instance associated with self.adata.

Return type:: AnnDataManager

device

CellAssign.device[source]#

The current device that the module’s params are on.

Return type:: str

history

CellAssign.history[source]#: Returns computed metrics during training.

is_trained

CellAssign.is_trained[source]#

Whether the model has been trained.

Return type:: bool

test_indices

CellAssign.test_indices[source]#

Observations that are in test set.

Return type:: ndarray

train_indices

CellAssign.train_indices[source]#

Observations that are in train set.

Return type:: ndarray

validation_indices

CellAssign.validation_indices[source]#

Observations that are in validation set.

Return type:: ndarray

Methods#

convert_legacy_save

classmethod CellAssign.convert_legacy_save(dir_path, output_dir_path, overwrite=False, prefix=None)[source]#

Converts a legacy saved model (<v0.15.0) to the updated save format.

Parameters:

dir_path (str) – Path to directory where legacy model is saved.
output_dir_path (str) – Path to save converted save files.
overwrite (bool (default: False)) – Overwrite existing data or not. If False and directory already exists at output_dir_path, error will be raised.
prefix (Optional[str] (default: None)) – Prefix of saved file names.

Return type:

None

get_anndata_manager

CellAssign.get_anndata_manager(adata, required=False)[source]#

Retrieves the AnnDataManager for a given AnnData object specific to this model instance.

Requires self.id has been set. Checks for an AnnDataManager specific to this model instance.

Parameters:

adata (Union[AnnData, MuData]) – AnnData object to find manager instance for.
required (bool (default: False)) – If True, errors on missing manager. Otherwise, returns None when manager is missing.

Return type:

Optional[AnnDataManager]

get_from_registry

CellAssign.get_from_registry(adata, registry_key)[source]#

Returns the object in AnnData associated with the key in the data registry.

AnnData object should be registered with the model prior to calling this function via the self._validate_anndata method.

Parameters:

registry_key (str) – key of object to get from data registry.
adata (Union[AnnData, MuData]) – AnnData to pull data from.

Return type:

ndarray

Returns:

The requested data as a NumPy array.

load

classmethod CellAssign.load(dir_path, adata=None, use_gpu=None, prefix=None, backup_url=None)[source]#

Instantiate a model from the saved output.

Parameters:

dir_path (str) – Path to saved outputs.
adata (Union[AnnData, MuData, None] (default: None)) – AnnData organized in the same way as data used to train model. It is not necessary to run setup_anndata, as AnnData is validated against the saved scvi setup dictionary. If None, will check for and load anndata saved with the model.
use_gpu (Union[str, int, bool, None] (default: None)) – Load model on default GPU if available (if None or True), or index of GPU to use (if int), or name of GPU (if str), or use CPU (if False).
prefix (Optional[str] (default: None)) – Prefix of saved file names.
backup_url (Optional[str] (default: None)) – URL to retrieve saved outputs from if not present on disk.

Returns:

Model with loaded state dictionaries.

Examples

>>> model = ModelClass.load(save_path, adata) # use the name of the model class used to save
>>> model.get_....

load_registry

static CellAssign.load_registry(dir_path, prefix=None)[source]#

Return the full registry saved with the model.

Parameters:

dir_path (str) – Path to saved outputs.
prefix (Optional[str] (default: None)) – Prefix of saved file names.

Return type:

dict

Returns:

The full registry saved with the model

predict

CellAssign.predict()[source]#

Predict soft cell type assignment probability for each cell.

Return type:: DataFrame

register_manager

classmethod CellAssign.register_manager(adata_manager)[source]#

Registers an AnnDataManager instance with this model class.

Stores the AnnDataManager reference in a class-specific manager store. Intended for use in the setup_anndata() class method followed up by retrieval of the AnnDataManager via the _get_most_recent_anndata_manager() method in the model init method.

Notes

Subsequent calls to this method with an AnnDataManager instance referring to the same underlying AnnData object will overwrite the reference to previous AnnDataManager.

save

CellAssign.save(dir_path, prefix=None, overwrite=False, save_anndata=False, **anndata_write_kwargs)[source]#

Save the state of the model.

Neither the trainer optimizer state nor the trainer history are saved. Model files are not expected to be reproducibly saved and loaded across versions until we reach version 1.0.

Parameters:

dir_path (str) – Path to a directory.
prefix (Optional[str] (default: None)) – Prefix to prepend to saved file names.
overwrite (bool (default: False)) – Overwrite existing data or not. If False and directory already exists at dir_path, error will be raised.
save_anndata (bool (default: False)) – If True, also saves the anndata
anndata_write_kwargs – Kwargs for write()

setup_anndata

classmethod CellAssign.setup_anndata(adata, size_factor_key, batch_key=None, categorical_covariate_keys=None, continuous_covariate_keys=None, layer=None, **kwargs)[source]#

Sets up the AnnData object for this model.

A mapping will be created between data fields used by this model to their respective locations in adata.

None of the data in adata are modified. Only adds fields to adata.

Parameters:

size_factor_key (str) –

key in adata.obs with continuous valued size factors. batch_key

key in adata.obs for batch information. Categories will automatically be converted into integer categories and saved to adata.obs[‘_scvi_batch’]. If None, assigns the same batch to all the data.

layer: if not None, uses this as the key in adata.layers for raw count data.
categorical_covariate_keys: keys in adata.obs that correspond to categorical data. These covariates can be added in addition to the batch covariate and are also treated as nuisance factors (i.e., the model tries to minimize their effects on the latent space). Thus, these should not be used for biologically-relevant factors that you do _not_ want to correct for.
continuous_covariate_keys: keys in adata.obs that correspond to continuous data. These covariates can be added in addition to the batch covariate and are also treated as nuisance factors (i.e., the model tries to minimize their effects on the latent space). Thus, these should not be used for biologically-relevant factors that you do _not_ want to correct for.

to_device

CellAssign.to_device(device)[source]#

Move model to device.

Parameters:: device (Union[str, int]) – Device to move model to. Options: ‘cpu’ for CPU, integer GPU index (eg. 0), or ‘cuda:X’ where X is the GPU index (eg. ‘cuda:0’). See torch.device for more info.

Examples

>>> adata = scvi.data.synthetic_iid()
>>> model = scvi.model.SCVI(adata)
>>> model.to_device('cpu')      # moves model to CPU
>>> model.to_device('cuda:0')   # moves model to GPU 0
>>> model.to_device(0)          # also moves model to GPU 0

train

CellAssign.train(max_epochs=400, lr=0.003, use_gpu=None, train_size=0.9, validation_size=None, batch_size=1024, plan_kwargs=None, early_stopping=True, early_stopping_patience=15, early_stopping_min_delta=0.0, **kwargs)[source]#

Trains the model.

Parameters:

max_epochs (int (default: 400)) – Number of epochs to train for
lr (float (default: 0.003)) – Learning rate for optimization.
use_gpu (Union[str, int, bool, None] (default: None)) – Use default GPU if available (if None or True), or index of GPU to use (if int), or name of GPU (if str, e.g., ‘cuda:0’), or use CPU (if False).
train_size (float (default: 0.9)) – Size of training set in the range [0.0, 1.0].
validation_size (Optional[float] (default: None)) – Size of the test set. If None, defaults to 1 - train_size. If train_size + validation_size < 1, the remaining cells belong to a test set.
batch_size (int (default: 1024)) – Minibatch size to use during training.
plan_kwargs (Optional[dict] (default: None)) – Keyword args for ClassifierTrainingPlan. Keyword arguments passed to
early_stopping (bool (default: True)) – Adds callback for early stopping on validation_loss
early_stopping_patience (int (default: 15)) – Number of times early stopping metric can not improve over early_stopping_min_delta
early_stopping_min_delta (float (default: 0.0)) – Threshold for counting an epoch torwards patience train() will overwrite values present in plan_kwargs, when appropriate.
**kwargs – Other keyword args for Trainer.

view_anndata_setup

CellAssign.view_anndata_setup(adata=None, hide_state_registries=False)[source]#

Print summary of the setup for the initial AnnData or a given AnnData object.

Parameters:

adata (Union[AnnData, MuData, None] (default: None)) – AnnData object setup with setup_anndata or transfer_fields().
hide_state_registries (bool (default: False)) – If True, prints a shortened summary without details of each state registry.

Return type:

None

view_setup_args

static CellAssign.view_setup_args(dir_path, prefix=None)[source]#

Print args used to setup a saved model.

Parameters:

dir_path (str) – Path to saved outputs.
prefix (Optional[str] (default: None)) – Prefix of saved file names.

Return type:

None