scviva.model.GIMVI#

class scviva.model.GIMVI(adata_seq, adata_spatial, generative_distributions=None, model_library_size=None, n_latent=10, **model_kwargs)[source]#

Joint VAE for imputing missing genes in spatial data [Lopez et al., 2019].

Learns a joint latent space for paired scRNA-seq and spatial transcriptomics data, enabling imputation of spatially unmeasured genes.

Parameters:
adata_seq AnnData

AnnData object registered via setup_anndata() containing scRNA-seq data.

adata_spatial AnnData

AnnData object registered via setup_anndata() containing spatial transcriptomics data.

generative_distributions list[str] | None

List of generative distributions for seq and spatial data. Defaults to ['zinb', 'nb'].

model_library_size list[bool] | None

Whether to model library size per dataset. Defaults to [True, False].

n_latent int

Dimensionality of the latent space.

**model_kwargs

Keyword args for JVAE.

Examples

>>> adata_seq = anndata.read_h5ad(path_to_seq)
>>> adata_spatial = anndata.read_h5ad(path_to_spatial)
>>> scviva.model.GIMVI.setup_anndata(adata_seq)
>>> scviva.model.GIMVI.setup_anndata(adata_spatial)
>>> model = scviva.model.GIMVI(adata_seq, adata_spatial)
>>> model.train(max_epochs=200)

Notes

See further usage examples in the following tutorial:

  1. Introduction to gimVI

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.

get_normalized_function_name

What the get normalized functions name is

history

Returns computed metrics during training.

is_trained

Whether the model has been trained.

registry

Data attached to model instance.

run_id

Returns the run id of the model.

run_name

Returns the run name of the model.

summary_string

Summary string of the model.

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)

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

data_registry(registry_key)

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

deregister_manager([adata])

Deregisters the AnnDataManager instance associated with adata.

differential_abundance(*args, **kwargs)

Not implemented for this model class.

from_spatialdata(sdata[, table_key, region])

Convenience constructor from a SpatialData object.

get_anndata_manager(adata[, required])

Retrieves the AnnDataManager for a given AnnData object.

get_from_registry(adata, registry_key)

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

get_imputed_values([adatas, deterministic, ...])

Return imputed values for all genes for each dataset.

get_latent_representation([adatas, ...])

Return the latent space embedding for each dataset.

get_normalized_expression(*args, **kwargs)

Not implemented for this model class.

get_setup_arg(setup_arg)

Returns the string provided to setup of a specific setup_arg.

get_state_registry(registry_key)

Returns the state registry for the AnnDataField registered with this instance.

get_var_names([legacy_mudata_format])

Variable names of input data.

load(dir_path[, adata_seq, adata_spatial, ...])

Instantiate a model from the saved output.

load_registry(dir_path[, prefix])

Return the full registry saved with the model.

plot_spatial_embedding([adata, basis, color])

Plot latent embedding overlaid on tissue spatial coordinates.

register_manager(adata_manager)

Registers an AnnDataManager instance with this model class.

save(dir_path[, prefix, overwrite, ...])

Save the state of the model.

setup_annbatch([collection_path, paths, ...])

Set up a model from on-disk AnnData files via the annbatch streaming loader.

setup_anndata(adata[, batch_key, ...])

Sets up the AnnData object for this model.

setup_spatialdata(sdata[, table_key, region])

Register the spatial adata component from a SpatialData object.

to_device(device)

Move the model to the device.

train([max_epochs, accelerator, devices, ...])

Train the model.

transfer_fields(adata, **kwargs)

Transfer fields from a model to an AnnData object.

update_setup_method_args(setup_method_args)

Update setup method args.

view_anndata_setup([adata, ...])

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

view_registry([hide_state_registries])

Prints summary of the registry.

view_setup_args(dir_path[, prefix])

Print args used to setup a saved model.

view_setup_method_args()

Prints setup kwargs used to produce a given registry.

Attributes

GIMVI.adata#

Data attached to model instance.

GIMVI.adata_manager#

Manager instance associated with self.adata.

GIMVI.device#

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

GIMVI.get_normalized_function_name#

What the get normalized functions name is

GIMVI.history#

Returns computed metrics during training.

GIMVI.is_trained#

Whether the model has been trained.

GIMVI.registry#

Data attached to model instance.

GIMVI.run_id#

Returns the run id of the model. Used in MLFlow

GIMVI.run_name#

Returns the run name of the model. Used in MLFlow

GIMVI.summary_string#

Summary string of the model.

GIMVI.test_indices#

Observations that are in test set.

GIMVI.train_indices#

Observations that are in train set.

GIMVI.validation_indices#

Observations that are in validation set.

Methods

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

Convert a legacy saved GIMVI 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

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

prefix str | None

Prefix of saved file names.

**save_kwargs

Keyword arguments passed into save().

Return type:

None

GIMVI.data_registry(registry_key)[source]#

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

Parameters:
registry_key str

key of an object to get from self.data_registry

Return type:

ndarray | DataFrame

Returns:

The requested data.

GIMVI.deregister_manager(adata=None)[source]#

Deregisters the AnnDataManager instance associated with adata.

If adata is None, deregisters all AnnDataManager instances in both the class and instance-specific manager stores, except for the one associated with this model instance.

GIMVI.differential_abundance(*args, **kwargs)[source]#

Not implemented for this model class.

Available in models that inherit from VAEMixin.

Raises:

NotImplementedError –

classmethod GIMVI.from_spatialdata(sdata, table_key='table', region=None, **model_kwargs)[source]#

Convenience constructor from a SpatialData object.

Calls setup_spatialdata() then constructs and returns the model.

Parameters:
sdata

A spatialdata.SpatialData object.

table_key str

Key in sdata pointing to the AnnData table.

region str | None

Region name to subset.

**model_kwargs

Passed to the model constructor.

Returns:

Instantiated model.

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

Retrieves the AnnDataManager for a given AnnData object.

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

Parameters:
adata AnnData | MuData

AnnData object to find a manager instance for.

required bool

If True, errors on missing manager. Otherwise, returns None when manager is missing.

Return type:

AnnDataManager | None

GIMVI.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 the data registry.

adata AnnData | MuData

AnnData to pull data from.

Return type:

ndarray

Returns:

The requested data as a NumPy array.

GIMVI.get_imputed_values(adatas=None, deterministic=True, normalized=True, decode_mode=None, batch_size=128)[source]#

Return imputed values for all genes for each dataset.

Parameters:
adatas list[AnnData]

List of adata_seq and adata_spatial.

deterministic bool

If True, use the encoder mean.

normalized bool

Return normalized values or raw rates.

decode_mode int | None

If provided, use the decoder of this dataset id for all inputs.

batch_size int

Minibatch size.

Return type:

list[ndarray]

GIMVI.get_latent_representation(adatas=None, deterministic=True, batch_size=128, backend='cpu')[source]#

Return the latent space embedding for each dataset.

Parameters:
adatas list[AnnData]

List of [adata_seq, adata_spatial]. If None, uses the training adatas.

deterministic bool

If True, use the encoder mean instead of a Gaussian sample.

batch_size int

Minibatch size for data loading.

backend str

"cpu" returns numpy arrays. "rapids" transfers each latent array to a cupy array for GPU downstream processing (requires pip install cuml).

Return type:

list[ndarray]

Returns:

List of arrays, one per dataset (seq then spatial).

GIMVI.get_normalized_expression(*args, **kwargs)[source]#

Not implemented for this model class.

Available in RNA models that inherit from RNASeqMixin.

Raises:

NotImplementedError –

GIMVI.get_setup_arg(setup_arg)[source]#

Returns the string provided to setup of a specific setup_arg.

Return type:

attrdict

GIMVI.get_state_registry(registry_key)[source]#

Returns the state registry for the AnnDataField registered with this instance.

Return type:

attrdict

GIMVI.get_var_names(legacy_mudata_format=False)[source]#

Variable names of input data.

Return type:

dict

classmethod GIMVI.load(dir_path, adata_seq=None, adata_spatial=None, accelerator='auto', device='auto', prefix=None, backup_url=None)[source]#

Instantiate a model from the saved output.

Parameters:
dir_path str

Path to saved outputs.

adata_seq AnnData | None

scRNA-seq AnnData. If None, will check for saved anndata.

adata_spatial AnnData | None

Spatial AnnData. If None, will check for saved anndata.

accelerator str

Supports passing different accelerator types ("cpu", "gpu", "tpu", "ipu", "hpu", "mps, "auto") as well as custom accelerator instances.

device int | str

The device to use. Can be set to a non-negative index (int or str) or "auto" for automatic selection based on the chosen accelerator. If set to "auto" and accelerator is not determined to be "cpu", then device will be set to the first available device.

prefix str | None

Prefix of saved file names.

backup_url str | None

URL to retrieve saved outputs from if not present on disk.

Returns:

Model with loaded state dictionaries.

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

Return the full registry saved with the model.

Parameters:
dir_path str

Path to saved outputs.

prefix str | None

Prefix of saved file names.

Return type:

dict

Returns:

The full registry saved with the model

GIMVI.plot_spatial_embedding(adata=None, basis='spatial', color=None, **kwargs)[source]#

Plot latent embedding overlaid on tissue spatial coordinates.

A thin wrapper around scanpy.pl.embedding() that defaults basis to the spatial coordinate key so cells are displayed in tissue space.

Parameters:
adata

AnnData object. If None, uses the model’s registered adata.

basis str

Key in adata.obsm containing 2D spatial coordinates.

color

Keys to color cells by (obs columns, gene names, etc.).

**kwargs

Forwarded to scanpy.pl.embedding().

classmethod GIMVI.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.

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

Save the state of the model.

Parameters:
dir_path str

Path to a directory.

prefix str | None

Prefix to prepend to saved file names.

overwrite bool

Overwrite existing data or not.

save_anndata bool

If True, also saves the anndata objects.

save_kwargs dict | None

Keyword arguments passed into save().

**anndata_write_kwargs

Keyword arguments passed into write() when save_anndata=True.

classmethod GIMVI.setup_annbatch(collection_path=None, paths=None, batch_key=None, labels_key=None, sample_key=None, unlabeled_category='Unknown', layer=None, categorical_covariate_keys=None, continuous_covariate_keys=None, rebuild=True, batch_size=4096, chunk_size=256, preload_nchunks=32, preload_to_gpu=True, dataset_size='20GB', shuffle=False, var_subset=None, merge=None, adatas=None, use_class_sampler=False, class_sampler_key=None, class_weights=None)[source]#

Set up a model from on-disk AnnData files via the annbatch streaming loader.

Builds (or reuses) a zarr-backed DatasetCollection from the supplied h5ad file paths, then wraps it in a AnnbatchDataModule ready for training.

Parameters:
collection_path str | None

Directory where the zarr collection is written (or already exists). If None (default), a path is auto-generated as "./{ModelName}_annbatch.zarr" in the current working directory.

paths list[str] | None

Paths to h5ad files that make up the training dataset. If None, an existing collection at collection_path is opened without rebuilding — useful when the zarr store was created by a previous call. Must be provided when the store does not exist yet.

batch_key str | None

Column in obs to use as the batch variable.

labels_key str | None

Column in obs to use as the cell-type / label variable.

sample_key str | None

Column in obs to use as the sample variable. Used by models like MrVI.

unlabeled_category str

Value used to mark unlabeled cells in labels_key. Required by semi-supervised models such as SCANVI. Defaults to "Unknown".

layer str | None

Layer in the h5ad files to use as the count matrix. None uses adata.X (falling back to adata.raw.X when a raw slot exists).

categorical_covariate_keys list[str] | None

Additional categorical covariate columns in obs.

continuous_covariate_keys list[str] | None

Additional continuous covariate columns in obs.

rebuild bool

If True, always rebuild the zarr collection even if it already exists on disk. If False (default), reuse an existing collection and skip the (potentially expensive) add_adatas step.

batch_size int

Number of cells per batch yielded by the Loader.

chunk_size int

Number of cells loaded from disk contiguously per read.

preload_nchunks int

Number of chunks to preload and shuffle in memory.

preload_to_gpu bool

Whether the loader should move data to GPU before yielding.

dataset_size int | str

Number of observations to load into memory for shuffling / pre-processing when building the collection, or annbatch’s human-readable size strings, e.g. "20GB".

shuffle bool

Whether to pre-shuffle cells when building the collection.

var_subset list[str] | None

Optional list of gene names to restrict the collection to (passed as var_subset to add_adatas).

merge Optional[Literal['same', 'unique', 'first', 'only']]

How annbatch should merge var metadata across inputs. Passed through to annbatch.DatasetCollection.add_adatas().

Returns:

AnnbatchDataModule A configured datamodule whose registry can be passed directly to the model constructor, e.g. model = SCVI(registry=dm.registry).

Notes

After training, saving and reloading the model requires reconstructing the datamodule manually and passing it to load() via the datamodule argument — the same pattern used by all custom datamodules.

classmethod GIMVI.setup_anndata(adata, batch_key=None, labels_key=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.

Call once for adata_seq and once for adata_spatial before constructing the model.

Parameters:
adata AnnData

AnnData object. Rows represent cells, columns represent features.

batch_key str | 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.

labels_key str | None

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

layer str | None

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

**kwargs

Keyword args for register_fields().

classmethod GIMVI.setup_spatialdata(sdata, table_key='table', region=None, **kwargs)[source]#

Register the spatial adata component from a SpatialData object.

Calls setup_anndata() on the extracted table. The scRNA-seq component must always be registered via setup_anndata() directly.

Parameters:
sdata

A spatialdata.SpatialData object.

table_key str

Key in sdata pointing to the spatial AnnData table.

region str | None

Region name to subset (stored in sdata[table_key].obs).

**kwargs

Passed to setup_anndata().

Return type:

None

GIMVI.to_device(device)[source]#

Move the model to the device.

Parameters:
device str | int | device

Device to move model to. Options: ‘cpu’ for CPU, integer GPU index (e.g., 0), ‘cuda:X’ where X is the GPU index (e.g. ‘cuda:0’), or a torch.device object (including XLA devices for TPU). 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
GIMVI.train(max_epochs=200, accelerator='auto', devices='auto', kappa=5, train_size=None, validation_size=None, shuffle_set_split=True, batch_size=128, datasplitter_kwargs=None, plan_kwargs=None, **kwargs)[source]#

Train the model.

Parameters:
max_epochs int

Number of passes through the dataset.

accelerator str

Supports passing different accelerator types ("cpu", "gpu", "tpu", "ipu", "hpu", "mps, "auto") as well as custom accelerator instances.

devices int | list[int] | str

The devices to use. Can be set to a non-negative index (int or str), a sequence of device indices (list or comma-separated str), the value -1 to indicate all available devices, or "auto" for automatic selection based on the chosen accelerator. If set to "auto" and accelerator is not determined to be "cpu", then devices will be set to the first available device.

kappa int

Scaling parameter for the discriminator loss.

train_size float | None

Size of training set in the range [0.0, 1.0].

validation_size float | None

Size of the test set.

shuffle_set_split bool

Whether to shuffle indices before splitting.

batch_size int

Minibatch size.

datasplitter_kwargs dict | None

Additional kwargs for DataSplitter.

plan_kwargs dict | None

Keyword args for the training plan.

**kwargs

Other keyword args for Trainer.

GIMVI.transfer_fields(adata, **kwargs)[source]#

Transfer fields from a model to an AnnData object.

Return type:

AnnData

GIMVI.update_setup_method_args(setup_method_args)[source]#

Update setup method args.

Parameters:
setup_method_args dict

This is a bit of a misnomer, this is a dict representing kwargs of the setup method that will be used to update the existing values in the registry of this instance.

GIMVI.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 AnnData | MuData | None

AnnData object setup with setup_anndata or transfer_fields().

hide_state_registries bool

If True, prints a shortened summary without details of each state registry.

Return type:

None

GIMVI.view_registry(hide_state_registries=False)[source]#

Prints summary of the registry.

Parameters:
hide_state_registries bool

If True, prints a shortened summary without details of each state registry.

Return type:

None

static GIMVI.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 str | None

Prefix of saved file names.

Return type:

None

GIMVI.view_setup_method_args()[source]#

Prints setup kwargs used to produce a given registry.

Parameters:
registry

Registry produced by an AnnDataManager.

Return type:

None