simple_scvi.MyModel

Contents

simple_scvi.MyModel#

class simple_scvi.MyModel(adata, n_hidden=128, n_latent=10, n_layers=1, **model_kwargs)#

Skeleton for an scvi-tools model.

Please use this skeleton to create new models. This is a simple implementation of the scVI model [LRC+18].

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.

  • n_layers (int (default: 1)) – Number of hidden layers used for encoder and decoder NNs.

  • **model_kwargs – Keyword args for MyModule

Examples

>>> adata = anndata.read_h5ad(path_to_anndata)
>>> mypackage.MyModel.setup_anndata(adata, batch_key="batch")
>>> vae = mypackage.MyModel(adata)
>>> vae.train()
>>> adata.obsm["X_mymodel"] = 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.

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.

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)

Converts a legacy saved 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.

get_anndata_manager(adata[, required])

Retrieves the AnnDataManager for a given AnnData object.

get_elbo([adata, indices, batch_size, ...])

Compute the evidence lower bound (ELBO) on the data.

get_from_registry(adata, registry_key)

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

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

Compute the latent representation of the data.

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

Compute the marginal log-likehood of the data.

get_normalized_expression(*args, **kwargs)

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

Compute the reconstruction error on the data.

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, accelerator, device, ...])

Instantiate a model from the saved output.

load_registry(dir_path[, prefix])

Return the full registry saved with the model.

register_manager(adata_manager)

Registers an AnnDataManager instance with this model class.

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

Save the state of the model.

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

Sets up the AnnData object for this model.

to_device(device)

Move model to 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#

adata#

MyModel.adata#

Data attached to model instance.

adata_manager#

MyModel.adata_manager#

Manager instance associated with self.adata.

device#

MyModel.device#

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

get_normalized_function_name#

MyModel.get_normalized_function_name#

What the get normalized functions name is

history#

MyModel.history#

Returns computed metrics during training.

is_trained#

MyModel.is_trained#

Whether the model has been trained.

registry#

MyModel.registry#

Data attached to model instance.

summary_string#

MyModel.summary_string#

Summary string of the model.

test_indices#

MyModel.test_indices#

Observations that are in test set.

train_indices#

MyModel.train_indices#

Observations that are in train set.

validation_indices#

MyModel.validation_indices#

Observations that are in validation set.

Methods#

convert_legacy_save#

classmethod MyModel.convert_legacy_save(dir_path, output_dir_path, overwrite=False, prefix=None, **save_kwargs)#

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.

  • **save_kwargs – Keyword arguments passed into save().

Return type:

None

data_registry#

MyModel.data_registry(registry_key)#

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

Parameters:

registry_key (str) – key of object to get from self.data_registry

Return type:

ndarray | DataFrame

Returns:

: The requested data.

deregister_manager#

MyModel.deregister_manager(adata=None)#

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.

get_anndata_manager#

MyModel.get_anndata_manager(adata, required=False)#

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 manager instance for.

  • required (bool (default: False)) – If True, errors on missing manager. Otherwise, returns None when manager is missing.

Return type:

AnnDataManager | None

get_elbo#

MyModel.get_elbo(adata=None, indices=None, batch_size=None, dataloader=None, return_mean=True, **kwargs)#

Compute the evidence lower bound (ELBO) on the data.

The ELBO is the reconstruction error plus the Kullback-Leibler (KL) divergences between the variational distributions and the priors. It is different from the marginal log-likelihood; specifically, it is a lower bound on the marginal log-likelihood plus a term that is constant with respect to the variational distribution. It still gives good insights on the modeling of the data and is fast to compute.

Parameters:

  • adata (Optional[AnnData] (default: None)) – AnnData object with var_names in the same order as the ones used to train the model. If None and dataloader is also None, it defaults to the object used to initialize the model.

  • indices (Optional[Sequence[int]] (default: None)) – Indices of observations in adata to use. If None, defaults to all observations. Ignored if dataloader is not None.

  • batch_size (Optional[int] (default: None)) – Minibatch size for the forward pass. If None, defaults to scvi.settings.batch_size. Ignored if dataloader is not None.

  • dataloader (Optional[Iterator[dict[str, Tensor | None]]] (default: None)) – An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of Tensor with keys as expected by the model. If None, a dataloader is created from adata.

  • return_mean (bool (default: True)) – Whether to return the mean of the ELBO or the ELBO for each observation.

  • **kwargs – Additional keyword arguments to pass into the forward method of the module.

Return type:

float

Returns:

: Evidence lower bound (ELBO) of the data.

Notes

This is not the negative ELBO, so higher is better.

get_from_registry#

MyModel.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 | MuData) – AnnData to pull data from.

Return type:

ndarray

Returns:

: The requested data as a NumPy array.

get_latent_representation#

MyModel.get_latent_representation(adata=None, indices=None, give_mean=True, mc_samples=5000, batch_size=None, return_dist=False, dataloader=None)#

Compute the latent representation of the data.

This is typically denoted as \(z_n\).

Parameters:

  • adata (Optional[AnnData] (default: None)) – AnnData object with var_names in the same order as the ones used to train the model. If None and dataloader is also None, it defaults to the object used to initialize the model.

  • indices (Optional[Sequence[int]] (default: None)) – Indices of observations in adata to use. If None, defaults to all observations. Ignored if dataloader is not None

  • give_mean (bool (default: True)) – If True, returns the mean of the latent distribution. If False, returns an estimate of the mean using mc_samples Monte Carlo samples.

  • mc_samples (int (default: 5000)) – Number of Monte Carlo samples to use for the estimator for distributions with no closed-form mean (e.g., the logistic normal distribution). Not used if give_mean is True or if return_dist is True.

  • batch_size (Optional[int] (default: None)) – Minibatch size for the forward pass. If None, defaults to scvi.settings.batch_size. Ignored if dataloader is not None

  • return_dist (bool (default: False)) – If True, returns the mean and variance of the latent distribution. Otherwise, returns the mean of the latent distribution.

  • dataloader (Optional[Iterator[dict[str, Tensor | None]]] (default: None)) – An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of Tensor with keys as expected by the model. If None, a dataloader is created from adata.

Return type:

ndarray[tuple[int, ...], dtype[TypeVar(_ScalarType_co, bound= generic, covariant=True)]] | tuple[ndarray[tuple[int, ...], dtype[TypeVar(_ScalarType_co, bound= generic, covariant=True)]], ndarray[tuple[int, ...], dtype[TypeVar(_ScalarType_co, bound= generic, covariant=True)]]]

Returns:

: An array of shape (n_obs, n_latent) if return_dist is False. Otherwise, returns a tuple of arrays (n_obs, n_latent) with the mean and variance of the latent distribution.

get_marginal_ll#

MyModel.get_marginal_ll(adata=None, indices=None, n_mc_samples=1000, batch_size=None, return_mean=True, dataloader=None, **kwargs)#

Compute the marginal log-likehood of the data.

The computation here is a biased estimator of the marginal log-likelihood of the data.

Parameters:

  • adata (Optional[AnnData] (default: None)) – AnnData object with var_names in the same order as the ones used to train the model. If None and dataloader is also None, it defaults to the object used to initialize the model.

  • indices (Optional[Sequence[int]] (default: None)) – Indices of observations in adata to use. If None, defaults to all observations. Ignored if dataloader is not None.

  • n_mc_samples (int (default: 1000)) – Number of Monte Carlo samples to use for the estimator. Passed into the module’s marginal_ll method.

  • batch_size (Optional[int] (default: None)) – Minibatch size for the forward pass. If None, defaults to scvi.settings.batch_size. Ignored if dataloader is not None.

  • return_mean (bool (default: True)) – Whether to return the mean of the marginal log-likelihood or the marginal-log likelihood for each observation.

  • dataloader (Optional[Iterator[dict[str, Tensor | None]]] (default: None)) – An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of Tensor with keys as expected by the model. If None, a dataloader is created from adata.

  • **kwargs – Additional keyword arguments to pass into the module’s marginal_ll method.

Return type:

float | Tensor

Returns:

: If True, returns the mean marginal log-likelihood. Otherwise returns a tensor of shape (n_obs,) with the marginal log-likelihood for each observation.

Notes

This is not the negative log-likelihood, so higher is better.

get_normalized_expression#

MyModel.get_normalized_expression(*args, **kwargs)#

get_reconstruction_error#

MyModel.get_reconstruction_error(adata=None, indices=None, batch_size=None, dataloader=None, return_mean=True, **kwargs)#

Compute the reconstruction error on the data.

The reconstruction error is the negative log likelihood of the data given the latent variables. It is different from the marginal log-likelihood, but still gives good insights on the modeling of the data and is fast to compute. This is typically written as \(p(x \mid z)\), the likelihood term given one posterior sample.

Parameters:

  • adata (Optional[AnnData] (default: None)) – AnnData object with var_names in the same order as the ones used to train the model. If None and dataloader is also None, it defaults to the object used to initialize the model.

  • indices (Optional[Sequence[int]] (default: None)) – Indices of observations in adata to use. If None, defaults to all observations. Ignored if dataloader is not None

  • batch_size (Optional[int] (default: None)) – Minibatch size for the forward pass. If None, defaults to scvi.settings.batch_size. Ignored if dataloader is not None

  • dataloader (Optional[Iterator[dict[str, Tensor | None]]] (default: None)) – An iterator over minibatches of data on which to compute the metric. The minibatches should be formatted as a dictionary of Tensor with keys as expected by the model. If None, a dataloader is created from adata.

  • return_mean (bool (default: True)) – Whether to return the mean reconstruction loss or the reconstruction loss for each observation.

  • **kwargs – Additional keyword arguments to pass into the forward method of the module.

Return type:

dict[str, float]

Returns:

: Reconstruction error for the data.

Notes

This is not the negative reconstruction error, so higher is better.

get_setup_arg#

MyModel.get_setup_arg(setup_arg)#

Returns the string provided to setup of a specific setup_arg.

Return type:

attrdict

get_state_registry#

MyModel.get_state_registry(registry_key)#

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

Return type:

attrdict

get_var_names#

MyModel.get_var_names(legacy_mudata_format=False)#

Variable names of input data.

Return type:

dict

load#

classmethod MyModel.load(dir_path, adata=None, accelerator='auto', device='auto', prefix=None, backup_url=None, datamodule=None)#

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. If False, will load the model without AnnData.

  • accelerator (str (default: 'auto')) – Supports passing different accelerator types ("cpu", "gpu", "tpu", "ipu", "hpu", "mps, "auto") as well as custom accelerator instances.

  • device (int | str (default: 'auto')) – 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 (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.

  • datamodule (Optional[LightningDataModule] (default: None)) – EXPERIMENTAL A LightningDataModule instance to use for training in place of the default DataSplitter. Can only be passed in if the model was not initialized with AnnData.

Returns:

: Model with loaded state dictionaries.

Examples

>>> model = ModelClass.load(save_path, adata)
>>> model.get_....

load_registry#

static MyModel.load_registry(dir_path, prefix=None)#

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

register_manager#

classmethod MyModel.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#

MyModel.save(dir_path, prefix=None, overwrite=False, save_anndata=False, save_kwargs=None, legacy_mudata_format=False, datamodule=None, **anndata_write_kwargs)#

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

  • save_kwargs (Optional[dict] (default: None)) – Keyword arguments passed into save().

  • legacy_mudata_format (bool (default: False)) – If True, saves the model var_names in the legacy format if the model was trained with a MuData object. The legacy format is a flat array with variable names across all modalities concatenated, while the new format is a dictionary with keys corresponding to the modality names and values corresponding to the variable names for each modality.

  • datamodule (Optional[LightningDataModule] (default: None)) – EXPERIMENTAL A LightningDataModule instance to use for training in place of the default DataSplitter. Can only be passed in if the model was not initialized with AnnData.

  • anndata_write_kwargs – Kwargs for write()

setup_anndata#

classmethod MyModel.setup_anndata(adata, batch_key=None, labels_key=None, layer=None, categorical_covariate_keys=None, continuous_covariate_keys=None, **kwargs)#

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:

  • adata (AnnData) – AnnData object. Rows represent cells, columns represent features.

  • batch_key (Optional[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.

  • labels_key (Optional[str] (default: 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 (Optional[str] (default: None)) – if not None, uses this as the key in adata.layers for raw count data.

  • categorical_covariate_keys (Optional[List[str]] (default: None)) – 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 (Optional[List[str]] (default: None)) – 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.

Return type:

Optional[AnnData]

Returns:

: None. Adds the following fields:

.uns[‘_scvi’]

scvi setup dictionary

.obs[‘_scvi_labels’]

labels encoded as integers

.obs[‘_scvi_batch’]

batch encoded as integers

to_device#

MyModel.to_device(device)#

Move model to device.

Parameters:

device (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#

MyModel.train(max_epochs=None, accelerator='auto', devices='auto', train_size=None, validation_size=None, shuffle_set_split=True, load_sparse_tensor=False, batch_size=128, early_stopping=False, datasplitter_kwargs=None, plan_kwargs=None, datamodule=None, **trainer_kwargs)#

Train the model.

Parameters:

  • max_epochs (Optional[int] (default: None)) – The maximum number of epochs to train the model. The actual number of epochs may be less if early stopping is enabled. If None, defaults to a heuristic based on get_max_epochs_heuristic(). Must be passed in if datamodule is passed in, and it does not have an n_obs attribute.

  • accelerator (str (default: 'auto')) – Supports passing different accelerator types ("cpu", "gpu", "tpu", "ipu", "hpu", "mps, "auto") as well as custom accelerator instances.

  • devices (int | list[int] | str (default: 'auto')) – 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.

  • train_size (Optional[float] (default: None)) – Float, or None. Size of training set in the range [0.0, 1.0]. default is None, which is practicaly 0.9 and potentially adding small last batch to validation cells. Passed into DataSplitter. Not used if datamodule is passed in.

  • 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. Passed into DataSplitter. Not used if datamodule is passed in.

  • shuffle_set_split (bool (default: True)) – Whether to shuffle indices before splitting. If False, the val, train, and test set are split in the sequential order of the data according to validation_size and train_size percentages. Passed into DataSplitter. Not used if datamodule is passed in.

  • load_sparse_tensor (bool (default: False)) – EXPERIMENTAL If True, loads data with sparse CSR or CSC layout as a Tensor with the same layout. Can lead to speedups in data transfers to GPUs, depending on the sparsity of the data. Passed into DataSplitter. Not used if datamodule is passed in.

  • batch_size (int (default: 128)) – Minibatch size to use during training. Passed into DataSplitter. Not used if datamodule is passed in.

  • early_stopping (bool (default: False)) – Perform early stopping. Additional arguments can be passed in through **kwargs. See Trainer for further options.

  • datasplitter_kwargs (Optional[dict] (default: None)) – Additional keyword arguments passed into DataSplitter. Values in this argument can be overwritten by arguments directly passed into this method, when appropriate. Not used if datamodule is passed in.

  • plan_kwargs (Optional[dict] (default: None)) – Additional keyword arguments passed into TrainingPlan. Values in this argument can be overwritten by arguments directly passed into this method, when appropriate.

  • datamodule (Optional[LightningDataModule] (default: None)) – EXPERIMENTAL A LightningDataModule instance to use for training in place of the default DataSplitter. Can only be passed in if the model was not initialized with AnnData.

  • **kwargs – Additional keyword arguments passed into Trainer.

transfer_fields#

MyModel.transfer_fields(adata, **kwargs)#

Transfer fields from a model to an AnnData object.

Return type:

AnnData

update_setup_method_args#

MyModel.update_setup_method_args(setup_method_args)#

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.

view_anndata_setup#

MyModel.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 (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_registry#

MyModel.view_registry(hide_state_registries=False)#

Prints summary of the registry.

Parameters:

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 MyModel.view_setup_args(dir_path, prefix=None)#

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

view_setup_method_args#

MyModel.view_setup_method_args()#

Prints setup kwargs used to produce a given registry.

Parameters:

registry – Registry produced by an AnnDataManager.

Return type:

None

Contents