velovi.VELOVI

velovi.VELOVI#

class velovi.VELOVI(adata, n_hidden=256, n_latent=10, n_layers=1, dropout_rate=0.1, gamma_init_data=False, linear_decoder=False, **model_kwargs)[source]#

Velocity Variational Inference.

Parameters:

adata (AnnData) – AnnData object that has been registered via setup_anndata().
n_hidden (int) – Number of nodes per hidden layer.
n_latent (int) – Dimensionality of the latent space.
n_layers (int) – Number of hidden layers used for encoder and decoder NNs.
dropout_rate (float) – Dropout rate for neural networks.
gamma_init_data (bool) – Initialize gamma using the data-driven technique.
linear_decoder (bool) – Use a linear decoder from latent space to time.
**model_kwargs – Keyword args for VELOVAE

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 specific to this model instance.
`get_directional_uncertainty`([adata, ...])
`get_elbo`([adata, indices, batch_size])	Return the ELBO for the data.
`get_expression_fit`([adata, indices, ...])	Returns the fitted spliced and unspliced abundance (s(t) and u(t)).
`get_from_registry`(adata, registry_key)	Returns the object in AnnData associated with the key in the data registry.
`get_gene_likelihood`([adata, indices, ...])	Returns the likelihood per gene.
`get_latent_representation`([adata, indices, ...])	Return the latent representation for each cell.
`get_latent_time`([adata, indices, gene_list, ...])	Returns the cells by genes latent time.
`get_marginal_ll`([adata, indices, ...])	Return the marginal LL for the data.
`get_permutation_scores`(labels_key[, adata])	Compute permutation scores.
`get_rates`()
`get_reconstruction_error`([adata, indices, ...])	Return the reconstruction error for the data.
`get_state_assignment`([adata, indices, ...])	Returns cells by genes by states probabilities.
`get_velocity`([adata, indices, gene_list, ...])	Returns cells by genes velocity estimates.
`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, spliced_layer, ...)	Sets up the `AnnData` object for this model.
`to_device`(device)	Move model to device.
`train`([max_epochs, lr, weight_decay, ...])	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#

VELOVI.adata[source]#: Data attached to model instance.

VELOVI.adata_manager[source]#: Manager instance associated with self.adata.

VELOVI.device[source]#: The current device that the module’s params are on.

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

VELOVI.is_trained[source]#: Whether the model has been trained.

VELOVI.summary_string[source]#: Summary string of the model.

VELOVI.test_indices[source]#: Observations that are in test set.

VELOVI.train_indices[source]#: Observations that are in train set.

VELOVI.validation_indices[source]#: Observations that are in validation set.

Methods#

classmethod VELOVI.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) – 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

VELOVI.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.

Parameters:: adata (AnnData | None) –

VELOVI.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 (AnnData | MuData) – AnnData object to find manager instance for.
required (bool) – If True, errors on missing manager. Otherwise, returns None when manager is missing.

Return type:

AnnDataManager | None

VELOVI.get_directional_uncertainty(adata=None, n_samples=50, gene_list=None, n_jobs=-1)[source]#

Parameters:

adata (AnnData | None) –
n_samples (int) –
gene_list (Iterable[str] | None) –
n_jobs (int) –

VELOVI.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) – AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.
indices (Sequence[int] | None) – Indices of cells in adata to use. If None, all cells are used.
batch_size (int | None) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.

Return type:

float

VELOVI.get_expression_fit(adata=None, indices=None, gene_list=None, n_samples=1, batch_size=None, return_mean=True, return_numpy=None, restrict_to_latent_dim=None)[source]#

Returns the fitted spliced and unspliced abundance (s(t) and u(t)).

Parameters:

adata (AnnData | 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) – Indices of cells in adata to use. If None, all cells are used.
gene_list (Sequence[str] | None) – Return frequencies of expression for a subset of genes. This can save memory when working with large datasets and few genes are of interest.
n_samples (int) – Number of posterior samples to use for estimation.
batch_size (int | None) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
return_mean (bool) – Whether to return the mean of the samples.
return_numpy (bool | None) – Return a ndarray instead of a DataFrame. DataFrame includes gene names as columns. If either n_samples=1 or return_mean=True, defaults to False. Otherwise, it defaults to True.
restrict_to_latent_dim (int | None) –

Returns:

If n_samples > 1 and return_mean is False, then the shape is (samples, cells, genes). Otherwise, shape is (cells, genes). In this case, return type is DataFrame unless return_numpy is True.

Return type:

ndarray | DataFrame

VELOVI.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.

Returns:

The requested data as a NumPy array.

Return type:

ndarray

VELOVI.get_gene_likelihood(adata=None, indices=None, gene_list=None, n_samples=1, batch_size=None, return_mean=True, return_numpy=None)[source]#

Returns the likelihood per gene. Higher is better.

This is denoted as \(\rho_n\) in the scVI paper.

Parameters:

adata (AnnData | 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) – Indices of cells in adata to use. If None, all cells are used.
transform_batch –
Batch to condition on. If transform_batch is:
- None, then real observed batch is used.
- int, then batch transform_batch is used.
gene_list (Sequence[str] | None) – Return frequencies of expression for a subset of genes. This can save memory when working with large datasets and few genes are of interest.
library_size – Scale the expression frequencies to a common library size. This allows gene expression levels to be interpreted on a common scale of relevant magnitude. If set to "latent", use the latent libary size.
n_samples (int) – Number of posterior samples to use for estimation.
batch_size (int | None) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
return_mean (bool) – Whether to return the mean of the samples.
return_numpy (bool | None) – Return a ndarray instead of a DataFrame. DataFrame includes gene names as columns. If either n_samples=1 or return_mean=True, defaults to False. Otherwise, it defaults to True.

Returns:

Return type:

ndarray | DataFrame

VELOVI.get_latent_representation(adata=None, indices=None, give_mean=True, mc_samples=5000, batch_size=None, return_dist=False)[source]#

Return the latent representation for each cell.

This is typically denoted as \(z_n\).

Parameters:

adata (AnnData | 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) – Indices of cells in adata to use. If None, all cells are used.
give_mean (bool) – Give mean of distribution or sample from it.
mc_samples (int) – For distributions with no closed-form mean (e.g., logistic normal), how many Monte Carlo samples to take for computing mean.
batch_size (int | None) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
return_dist (bool) – Return (mean, variance) of distributions instead of just the mean. If True, ignores give_mean and mc_samples. In the case of the latter, mc_samples is used to compute the mean of a transformed distribution. If return_dist is true the untransformed mean and variance are returned.

Returns:

Low-dimensional representation for each cell or a tuple containing its mean and variance.

Return type:

ndarray | tuple[ndarray, ndarray]

VELOVI.get_latent_time(adata=None, indices=None, gene_list=None, time_statistic='mean', n_samples=1, n_samples_overall=None, batch_size=None, return_mean=True, return_numpy=None)[source]#

Returns the cells by genes latent time.

Parameters:

adata (AnnData | 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) – Indices of cells in adata to use. If None, all cells are used.
gene_list (Sequence[str] | None) – Return frequencies of expression for a subset of genes. This can save memory when working with large datasets and few genes are of interest.
time_statistic (Literal['mean', 'max']) – Whether to compute expected time over states, or maximum a posteriori time over maximal probability state.
n_samples (int) – Number of posterior samples to use for estimation.
n_samples_overall (int | None) – Number of overall samples to return. Setting this forces n_samples=1.
batch_size (int | None) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
return_mean (bool) – Whether to return the mean of the samples.
return_numpy (bool | None) – Return a ndarray instead of a DataFrame. DataFrame includes gene names as columns. If either n_samples=1 or return_mean=True, defaults to False. Otherwise, it defaults to True.

Returns:

Return type:

ndarray | DataFrame

VELOVI.get_marginal_ll(adata=None, indices=None, n_mc_samples=1000, batch_size=None, return_mean=True, **kwargs)[source]#

Return the marginal LL for the data.

The computation here is a biased estimator of the marginal log likelihood of the data. Note, this is not the negative log likelihood, higher is better.

Parameters:

adata (AnnData | 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) – Indices of cells in adata to use. If None, all cells are used.
n_mc_samples (int) – Number of Monte Carlo samples to use for marginal LL estimation.
batch_size (int | None) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
return_mean (bool | None) – If False, return the marginal log likelihood for each observation. Otherwise, return the mmean arginal log likelihood.

Return type:

Tensor | float

VELOVI.get_permutation_scores(labels_key, adata=None)[source]#

Compute permutation scores.

Parameters:

labels_key (str) – Key in adata.obs encoding cell types
adata (AnnData | None) – AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model.

Returns:

Tuple of DataFrame and AnnData. DataFrame is genes by cell types with score per cell type. AnnData is the permutated version of the original AnnData.

Return type:

Tuple[DataFrame, AnnData]

VELOVI.get_rates()[source]#

VELOVI.get_reconstruction_error(adata=None, indices=None, batch_size=None)[source]#

Return the reconstruction error for the data.

This is typically written as \(p(x \mid z)\), the likelihood term given one posterior sample. Note, this is not the negative likelihood, higher is better.

Parameters:

adata (AnnData | 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) – Indices of cells in adata to use. If None, all cells are used.
batch_size (int | None) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.

Return type:

float

VELOVI.get_state_assignment(adata=None, indices=None, gene_list=None, hard_assignment=False, n_samples=20, batch_size=None, return_mean=True, return_numpy=None)[source]#

Returns cells by genes by states probabilities.

Parameters:

adata (AnnData | 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) – Indices of cells in adata to use. If None, all cells are used.
gene_list (Sequence[str] | None) – Return frequencies of expression for a subset of genes. This can save memory when working with large datasets and few genes are of interest.
hard_assignment (bool) – Return a hard state assignment
n_samples (int) – Number of posterior samples to use for estimation.
batch_size (int | None) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
return_mean (bool) – Whether to return the mean of the samples.
return_numpy (bool | None) – Return a ndarray instead of a DataFrame. DataFrame includes gene names as columns. If either n_samples=1 or return_mean=True, defaults to False. Otherwise, it defaults to True.

Returns:

Return type:

Tuple[ndarray | DataFrame, List[str]]

VELOVI.get_velocity(adata=None, indices=None, gene_list=None, n_samples=1, n_samples_overall=None, batch_size=None, return_mean=True, return_numpy=None, velo_statistic='mean', velo_mode='spliced', clip=True)[source]#

Returns cells by genes velocity estimates.

Parameters:

adata (AnnData | 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) – Indices of cells in adata to use. If None, all cells are used.
gene_list (Sequence[str] | None) – Return velocities for a subset of genes. This can save memory when working with large datasets and few genes are of interest.
n_samples (int) – Number of posterior samples to use for estimation for each cell.
n_samples_overall (int | None) – Number of overall samples to return. Setting this forces n_samples=1.
batch_size (int | None) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
return_mean (bool) – Whether to return the mean of the samples.
return_numpy (bool | None) – Return a ndarray instead of a DataFrame. DataFrame includes gene names as columns. If either n_samples=1 or return_mean=True, defaults to False. Otherwise, it defaults to True.
velo_statistic (str) – Whether to compute expected velocity over states, or maximum a posteriori velocity over maximal probability state.
velo_mode (Literal['spliced', 'unspliced']) – Compute ds/dt or du/dt.
clip (bool) – Clip to minus spliced value

Returns:

Return type:

ndarray | DataFrame

classmethod VELOVI.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) – 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) – 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.

Examples

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

static VELOVI.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.

Returns:

The full registry saved with the model

Return type:

dict

classmethod VELOVI.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.

Parameters:: adata_manager (AnnDataManager) –

VELOVI.save(dir_path, prefix=None, overwrite=False, save_anndata=False, save_kwargs=None, **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) – Prefix to prepend to saved file names.
overwrite (bool) – Overwrite existing data or not. If False and directory already exists at dir_path, error will be raised.
save_anndata (bool) – If True, also saves the anndata
save_kwargs (dict | None) – Keyword arguments passed into save().
anndata_write_kwargs – Kwargs for write()

classmethod VELOVI.setup_anndata(adata, spliced_layer, unspliced_layer, **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.
spliced_layer (str) – Layer in adata with spliced normalized expression
unspliced_layer (str) – Layer in adata with unspliced normalized expression.

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

Return type:

AnnData | None

VELOVI.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

VELOVI.train(max_epochs=500, lr=0.01, weight_decay=0.01, accelerator='auto', devices='auto', train_size=0.9, validation_size=None, batch_size=256, early_stopping=True, gradient_clip_val=10, plan_kwargs=None, **trainer_kwargs)[source]#

Train the model.

Parameters:

max_epochs (int | None) – Number of passes through the dataset. If None, defaults to np.min([round((20000 / n_cells) * 400), 400])
lr (float) – Learning rate for optimization
weight_decay (float) – Weight decay for optimization
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.
train_size (float) – Size of training set in the range [0.0, 1.0].
validation_size (float | 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) – Minibatch size to use during training.
early_stopping (bool) – Perform early stopping. Additional arguments can be passed in **kwargs. See Trainer for further options.
gradient_clip_val (float) – Val for gradient clipping
plan_kwargs (dict | None) – Keyword args for TrainingPlan. Keyword arguments passed to train() will overwrite values present in plan_kwargs, when appropriate.
**trainer_kwargs – Other keyword args for Trainer.

VELOVI.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

static VELOVI.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

velovi.VELOVI

Contents

velovi.VELOVI#

Attributes table#

Methods table#

Attributes#

Methods#