scvi.model.JaxSCVI#

class scvi.model.JaxSCVI(adata, n_hidden=128, n_latent=10, dropout_rate=0.1, gene_likelihood='nb', **model_kwargs)[source]#

EXPERIMENTAL single-cell Variational Inference [Lopez18], but with a Jax backend.

This implementation is in a very experimental state. API is completely subject to change.

Parameters
adata : AnnData

AnnData object that has been registered via setup_anndata().

n_hidden : int (default: 128)

Number of nodes per hidden layer.

n_latent : int (default: 10)

Dimensionality of the latent space.

dropout_rate : float (default: 0.1)

Dropout rate for neural networks.

gene_likelihood : {‘nb’, ‘poisson’}Literal[‘nb’, ‘poisson’] (default: 'nb')

One of:

  • 'nb' - Negative binomial distribution

  • 'poisson' - Poisson distribution

**model_kwargs

Keyword args for JaxVAE

Examples

>>> adata = anndata.read_h5ad(path_to_anndata)
>>> scvi.model.JaxSCVI.setup_anndata(adata, batch_key="batch")
>>> vae = scvi.model.SCVI(adata)
>>> vae.train()
>>> adata.obsm["X_scVI"] = vae.get_latent_representation()

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.

module

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#

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.

get_latent_representation([adata, indices, ...])

Return the latent representation for each cell.

load()

Instantiate a model from the saved output.

register_manager(adata_manager)

Registers an AnnDataManager instance with this model class.

save()

Save the state of the model.

setup_anndata(adata[, layer, batch_key])

Sets up the AnnData object for this model.

to_device()

Move model to device.

train([max_epochs, check_val_every_n_epoch, ...])

Train 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#

JaxSCVI.adata#

Data attached to model instance.

Return type

AnnData

adata_manager#

JaxSCVI.adata_manager#

Manager instance associated with self.adata.

Return type

AnnDataManager

device#

JaxSCVI.device#

history#

JaxSCVI.history#

Returns computed metrics during training.

is_trained#

JaxSCVI.is_trained#

Whether the model has been trained.

Return type

bool

module#

JaxSCVI.module#

test_indices#

JaxSCVI.test_indices#

Observations that are in test set.

Return type

ndarray

train_indices#

JaxSCVI.train_indices#

Observations that are in train set.

Return type

ndarray

validation_indices#

JaxSCVI.validation_indices#

Observations that are in validation set.

Return type

ndarray

Methods#

get_anndata_manager#

JaxSCVI.get_anndata_manager(adata, required=False)#

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 : AnnData

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

AnnDataManager | NoneOptional[AnnDataManager]

get_from_registry#

JaxSCVI.get_from_registry(adata, registry_key)#

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 : AnnData

AnnData to pull data from.

Return type

ndarray

Returns

The requested data as a NumPy array.

get_latent_representation#

JaxSCVI.get_latent_representation(adata=None, indices=None, give_mean=True, mc_samples=1, batch_size=None)[source]#

Return the latent representation for each cell.

This is denoted as \(z_n\) in our manuscripts.

Parameters
adata : AnnData | NoneOptional[AnnData] (default: None)

AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.

indices : Sequence[int] | NoneOptional[Sequence[int]] (default: None)

Indices of cells in adata to use. If None, all cells are used.

batch_size : int | NoneOptional[int] (default: None)

Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.

Return type

ndarray

Returns

-latent_representation (ndarray) Low-dimensional representation for each cell

load#

JaxSCVI.load()[source]#

Instantiate a model from the saved output.

Parameters
dir_path

Path to saved outputs.

adata

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

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

Prefix of saved file names.

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_....

register_manager#

classmethod JaxSCVI.register_manager(adata_manager)#

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#

JaxSCVI.save()[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

Path to a directory.

prefix

Prefix to prepend to saved file names.

overwrite

Overwrite existing data or not. If False and directory already exists at dir_path, error will be raised.

save_anndata

If True, also saves the anndata

anndata_write_kwargs

Kwargs for write()

setup_anndata#

classmethod JaxSCVI.setup_anndata(adata, layer=None, batch_key=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
layer : str | NoneOptional[str] (default: None)

if not None, uses this as the key in adata.layers for raw count data.

batch_key : str | NoneOptional[str] (default: None)

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.

to_device#

JaxSCVI.to_device()[source]#

Move model to device.

Parameters
device

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#

JaxSCVI.train(max_epochs=None, check_val_every_n_epoch=None, use_gpu=None, train_size=0.9, validation_size=None, batch_size=128, lr=0.001)[source]#

Train the model.

Parameters
max_epochs : int | NoneOptional[int] (default: None)

Number of passes through the dataset. If None, defaults to np.min([round((20000 / n_cells) * 400), 400])

use_gpu : str | int | bool | NoneUnion[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 : float | NoneOptional[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: 128)

Minibatch size to use during training.

view_anndata_setup#

JaxSCVI.view_anndata_setup(adata=None, hide_state_registries=False)#

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

Parameters
adata : AnnData | NoneOptional[AnnData] (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 JaxSCVI.view_setup_args(dir_path, prefix=None)#

Print args used to setup a saved model.

Parameters
dir_path : str

Path to saved outputs.

prefix : str | NoneOptional[str] (default: None)

Prefix of saved file names.

Return type

None