scvi.model.AmortizedLDA#

class scvi.model.AmortizedLDA(adata, n_topics=20, n_hidden=128, cell_topic_prior=None, topic_feature_prior=None)[source]#

Amortized Latent Dirichlet Allocation [Blei et al., 2003].

Parameters:
  • adata (AnnData) – AnnData object that has been registered via setup_anndata().

  • n_topics (int (default: 20)) – Number of topics to model.

  • n_hidden (int (default: 128)) – Number of nodes in the hidden layer of the encoder.

  • cell_topic_prior (float | Sequence[float] | None (default: None)) – Prior of cell topic distribution. If None, defaults to 1 / n_topics.

  • topic_feature_prior (float | Sequence[float] | None (default: None)) – Prior of topic feature distribution. If None, defaults to 1 / n_topics.

Examples

>>> adata = anndata.read_h5ad(path_to_anndata)
>>> scvi.model.AmortizedLDA.setup_anndata(adata)
>>> model = scvi.model.AmortizedLDA(adata)
>>> model.train()
>>> feature_by_topic = model.get_feature_by_topic()
>>> adata.obsm["X_LDA"] = model.get_latent_representation()

Notes

See further usage examples in the following tutorial:

  1. Topic Modeling with Amortized LDA

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.

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.

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])

Return the ELBO for the data.

get_feature_by_topic([n_samples])

Gets a Monte-Carlo estimate of the expectation of the feature by topic matrix.

get_from_registry(adata, registry_key)

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

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

Converts a count matrix to an inferred topic distribution.

get_perplexity([adata, indices, batch_size])

Computes approximate perplexity for adata.

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[, layer])

Sets up the AnnData object for this model.

to_device(device)

Move model to device.

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

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#

AmortizedLDA.adata[source]#

Data attached to model instance.

AmortizedLDA.adata_manager[source]#

Manager instance associated with self.adata.

AmortizedLDA.device[source]#

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

AmortizedLDA.history[source]#

Returns computed metrics during training.

AmortizedLDA.is_trained[source]#

Whether the model has been trained.

AmortizedLDA.summary_string[source]#

Summary string of the model.

AmortizedLDA.test_indices[source]#

Observations that are in test set.

AmortizedLDA.train_indices[source]#

Observations that are in train set.

AmortizedLDA.validation_indices[source]#

Observations that are in validation set.

Methods#

classmethod AmortizedLDA.convert_legacy_save(dir_path, output_dir_path, overwrite=False, prefix=None, **save_kwargs)[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 (str | None (default: None)) – Prefix of saved file names.

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

Return type:

None

AmortizedLDA.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.

AmortizedLDA.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 manager instance for.

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

Return type:

AnnDataManager | None

AmortizedLDA.get_elbo(adata=None, indices=None, batch_size=None)[source]#

Return the ELBO for the data.

The ELBO is a lower bound on the log likelihood of the data used for optimization of VAEs. Note, this is not the negative ELBO, higher is better.

Parameters:
  • adata (AnnData | None (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] | None (default: None)) – Indices of cells in adata to use. If None, all cells are used.

  • batch_size (int | None (default: None)) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.

Return type:

float

Returns:

The positive ELBO.

AmortizedLDA.get_feature_by_topic(n_samples=5000)[source]#

Gets a Monte-Carlo estimate of the expectation of the feature by topic matrix.

Parameters:
  • adata – AnnData to transform. If None, returns the feature by topic matrix for the source AnnData.

  • n_samples (default: 5000) – Number of samples to take for the Monte-Carlo estimate of the mean.

Return type:

DataFrame

Returns:

A n_var x n_topics Pandas DataFrame containing the feature by topic matrix.

AmortizedLDA.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 (AnnData | MuData) – AnnData to pull data from.

Return type:

ndarray

Returns:

The requested data as a NumPy array.

AmortizedLDA.get_latent_representation(adata=None, indices=None, batch_size=None, n_samples=5000)[source]#

Converts a count matrix to an inferred topic distribution.

Parameters:
  • adata (AnnData | None (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] | None (default: None)) – Indices of cells in adata to use. If None, all cells are used.

  • batch_size (int | None (default: None)) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.

  • n_samples (int (default: 5000)) – Number of samples to take for the Monte-Carlo estimate of the mean.

Return type:

DataFrame

Returns:

A n_obs x n_topics Pandas DataFrame containing the normalized estimate of the topic distribution for each observation.

AmortizedLDA.get_perplexity(adata=None, indices=None, batch_size=None)[source]#

Computes approximate perplexity for adata.

Perplexity is defined as exp(-1 * log-likelihood per count).

Parameters:
  • adata (AnnData | None (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] | None (default: None)) – Indices of cells in adata to use. If None, all cells are used.

  • batch_size (int | None (default: None)) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.

Return type:

float

Returns:

Perplexity.

classmethod AmortizedLDA.load(dir_path, adata=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 (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.

  • 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 (str | None (default: None)) – Prefix of saved file names.

  • backup_url (str | None (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)
>>> model.get_....
static AmortizedLDA.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 (default: None)) – Prefix of saved file names.

Return type:

dict

Returns:

The full registry saved with the model

classmethod AmortizedLDA.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.

AmortizedLDA.save(dir_path, prefix=None, overwrite=False, save_anndata=False, save_kwargs=None, legacy_mudata_format=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 (str | None (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 (dict | None (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.

  • anndata_write_kwargs – Kwargs for write()

classmethod AmortizedLDA.setup_anndata(adata, 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:
  • adata (AnnData) – AnnData object. Rows represent cells, columns represent features.

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

Return type:

AnnData | None

AmortizedLDA.to_device(device)[source]#

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
AmortizedLDA.train(max_epochs=None, accelerator='auto', device='auto', train_size=0.9, validation_size=None, shuffle_set_split=True, batch_size=128, early_stopping=False, lr=None, training_plan=None, datasplitter_kwargs=None, plan_kwargs=None, **trainer_kwargs)[source]#

Train the model.

Parameters:
  • max_epochs (int | None (default: None)) – Number of passes through the dataset. If None, defaults to np.min([round((20000 / n_cells) * 400), 400])

  • 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.

  • train_size (float (default: 0.9)) – Size of training set in the range [0.0, 1.0].

  • validation_size (float | None (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.

  • 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.

  • batch_size (int (default: 128)) – Minibatch size to use during training. If None, no minibatching occurs and all data is copied to device (e.g., GPU).

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

  • lr (float | None (default: None)) – Optimiser learning rate (default optimiser is ClippedAdam). Specifying optimiser via plan_kwargs overrides this choice of lr.

  • training_plan (PyroTrainingPlan | None (default: None)) – Training plan PyroTrainingPlan.

  • datasplitter_kwargs (dict | None (default: None)) – Additional keyword arguments passed into DataSplitter.

  • plan_kwargs (dict | None (default: None)) – Keyword args for PyroTrainingPlan. Keyword arguments passed to train() will overwrite values present in plan_kwargs, when appropriate.

  • **trainer_kwargs – Other keyword args for Trainer.

AmortizedLDA.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 (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

static AmortizedLDA.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 (default: None)) – Prefix of saved file names.

Return type:

None