multimil.model.MILClassifier

multimil.model.MILClassifier#

class multimil.model.MILClassifier(adata, sample_key, classification=None, regression=None, ordinal_regression=None, sample_batch_size=128, normalization='layer', dropout=0.2, scoring='gated_attn', attn_dim=16, n_layers_cell_aggregator=1, n_layers_classifier=2, n_layers_regressor=2, n_hidden_cell_aggregator=128, n_hidden_classifier=128, n_hidden_regressor=128, class_loss_coef=1.0, regression_loss_coef=1.0, activation='leaky_relu', initialization=None, anneal_class_loss=False)#

MultiMIL MIL prediction model.

Parameters:

  • adata – AnnData object containing embeddings and covariates.

  • sample_key – Key in adata.obs that corresponds to the sample covariate.

  • classification (default: None) – List of keys in adata.obs that correspond to the classification covariates.

  • regression (default: None) – List of keys in adata.obs that correspond to the regression covariates.

  • ordinal_regression (default: None) – List of keys in adata.obs that correspond to the ordinal regression covariates.

  • sample_batch_size (default: 128) – Number of samples per bag, i.e. sample. Default is 128.

  • normalization (default: 'layer') – One of “layer” or “batch”. Default is “layer”.

  • z_dim – Dimensionality of the input latent space. Default is 16.

  • dropout (default: 0.2) – Dropout rate. Default is 0.2.

  • scoring (default: 'gated_attn') – How to calculate attention scores. One of “gated_attn”, “attn”, “mean”, “max”, “sum”. Default is “gated_attn”.

  • attn_dim (default: 16) – Dimensionality of the hidden layer in attention calculation. Default is 16.

  • n_layers_cell_aggregator (int (default: 1)) – Number of layers in the cell aggregator. Default is 1.

  • n_layers_classifier (int (default: 2)) – Number of layers in the classifier. Default is 2.

  • n_layers_regressor (int (default: 2)) – Number of layers in the regressor. Default is 2.

  • n_hidden_cell_aggregator (int (default: 128)) – Number of hidden units in the cell aggregator. Default is 128.

  • n_hidden_classifier (int (default: 128)) – Number of hidden units in the classifier. Default is 128.

  • n_hidden_regressor (int (default: 128)) – Number of hidden units in the regressor. Default is 128.

  • class_loss_coef (default: 1.0) – Coefficient for the classification loss. Default is 1.0.

  • regression_loss_coef (default: 1.0) – Coefficient for the regression loss. Default is 1.0.

  • activation (default: 'leaky_relu') – Activation function. Default is ‘leaky_relu’.

  • initialization (default: None) – Initialization method for the weights. Default is None.

  • anneal_class_loss (default: False) – Whether to anneal the classification loss. Default is False.

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)

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.

differential_abundance(*args, **kwargs)

Not implemented for this model class.

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_model_output([adata, batch_size])

Save the attention scores and predictions in the adata object.

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, accelerator, device, ...])

Instantiate a model from the saved output.

load_query_data(adata, reference_model[, ...])

Online update of a reference model with scArches algorithm # TODO cite.

load_registry(dir_path[, prefix])

Return the full registry saved with the model.

plot_losses([save])

Plot losses.

prepare_query_anndata(adata, reference_model)

Prepare data for query integration.

prepare_query_mudata(mdata, reference_model)

Prepare multimodal dataset for query integration.

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[, ...])

Set up AnnData object.

to_device(device)

Move the model to the device.

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

Trains the model using amortized variational inference.

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#

MILClassifier.adata#

Data attached to model instance.

MILClassifier.adata_manager#

Manager instance associated with self.adata.

MILClassifier.device#

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

MILClassifier.get_normalized_function_name#

What the get normalized functions name is

MILClassifier.history#

Returns computed metrics during training.

MILClassifier.is_trained#

Whether the model has been trained.

MILClassifier.registry#

Data attached to model instance.

MILClassifier.run_id#

Returns the run id of the model. Used in MLFlow

MILClassifier.run_name#

Returns the run name of the model. Used in MLFlow

MILClassifier.summary_string#

Summary string of the model.

MILClassifier.test_indices#

Observations that are in test set.

MILClassifier.train_indices#

Observations that are in train set.

MILClassifier.validation_indices#

Observations that are in validation set.

Methods#

classmethod MILClassifier.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 the directory where the 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, an error will be raised.

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

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

Return type:

None

MILClassifier.data_registry(registry_key)#

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.

MILClassifier.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.

MILClassifier.differential_abundance(*args, **kwargs)#

Not implemented for this model class.

Available in models that inherit from VAEMixin.

Raises:

NotImplementedError –

MILClassifier.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 a manager instance for.

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

Return type:

AnnDataManager | None

MILClassifier.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 the data registry.

  • adata (AnnData | MuData) – AnnData to pull data from.

Return type:

ndarray

Returns:

The requested data as a NumPy array.

MILClassifier.get_model_output(adata=None, batch_size=256)#

Save the attention scores and predictions in the adata object.

Parameters:

  • adata (default: None) – AnnData object to run the model on. If None, the model’s AnnData object is used.

  • batch_size (default: 256) – Minibatch size to use. Default is 256.

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

Not implemented for this model class.

Available in RNA models that inherit from RNASeqMixin.

Raises:

NotImplementedError –

MILClassifier.get_setup_arg(setup_arg)#

Returns the string provided to setup of a specific setup_arg.

Return type:

attrdict

MILClassifier.get_state_registry(registry_key)#

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

Return type:

attrdict

MILClassifier.get_var_names(legacy_mudata_format=False)#

Variable names of input data.

Return type:

dict

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

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. 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 (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.

  • datamodule (LightningDataModule | None (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.

  • allowed_classes_names_list (list[str] | None (default: None)) – list of allowed classes names to be loaded (besides the original class name)

Returns:

Model with loaded state dictionaries.

Examples

>>> model = ModelClass.load(save_path, adata)
>>> model.get_....
classmethod MILClassifier.load_query_data(adata, reference_model, accelerator='auto', devices='auto')#

Online update of a reference model with scArches algorithm # TODO cite.

Parameters:

  • adata (AnnData) – 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 registry.

  • reference_model (BaseModelClass) – Already instantiated model of the same class.

  • accelerator (str (default: 'auto')) – Supports passing different accelerator types (“cpu”, “gpu”, “tpu”, “mps”, “auto”). Default is “auto”.

  • devices (int | list[int] | str (default: 'auto')) – Number of devices (int), list of device indices (list[int]), or "auto".

Return type:

BaseModelClass

Returns:

Model with updated architecture and weights.

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

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

MILClassifier.plot_losses(save=None)#

Plot losses.

Parameters:

save (default: None) – If not None, save the plot to this location.

static MILClassifier.prepare_query_anndata(adata, reference_model, return_reference_var_names=False, inplace=True)#

Prepare data for query integration.

This function will return a new AnnData object with padded zeros for missing features, as well as correctly sorted features.

Parameters:

  • adata (AnnData) – 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 registry.

  • reference_model (str | BaseModelClass) – Either an already instantiated model of the same class or a path to saved outputs for the reference model.

  • return_reference_var_names (bool (default: False)) – Only load and return reference var names if True.

  • inplace (bool (default: True)) – Whether to subset and rearrange query vars inplace or return new AnnData.

Return type:

AnnData | Index | None

Returns:

Query adata ready to use in load_query_data unless return_reference_var_names in which case a pd.Index of reference var names is returned.

static MILClassifier.prepare_query_mudata(mdata, reference_model, return_reference_var_names=False, inplace=True)#

Prepare multimodal dataset for query integration.

This function will return a new MuData object such that the AnnData objects for individual modalities are given padded zeros for missing features, as well as correctly sorted features.

Parameters:

  • mdata (MuData) – MuData organized in the same way as data used to train the model. It is not necessary to run setup_mudata, as MuData is validated against the registry.

  • reference_model (str | BaseModelClass) – Either an already instantiated model of the same class or a path to saved outputs for the reference model.

  • return_reference_var_names (bool (default: False)) – Only load and return reference var names if True.

  • inplace (bool (default: True)) – Whether to subset and rearrange query vars inplace or return new MuData.

Return type:

MuData | dict[str, Index] | None

Returns:

Query mudata ready to use in load_query_data unless return_reference_var_names in which case a dictionary of pd.Index of reference var names is returned.

classmethod MILClassifier.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.

MILClassifier.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 (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, an 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.

  • datamodule (LightningDataModule | None (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()

classmethod MILClassifier.setup_anndata(adata, categorical_covariate_keys=None, continuous_covariate_keys=None, ordinal_regression_order=None, **kwargs)#

Set up AnnData object.

A mapping will be created between data fields used by scvi to their respective locations in adata. This method will also compute the log mean and log variance per batch for the library size prior. None of the data in adata are modified. Only adds fields to adata.

Parameters:

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

  • categorical_covariate_keys (list[str] | None (default: None)) – Keys in adata.obs that correspond to categorical data.

  • continuous_covariate_keys (list[str] | None (default: None)) – Keys in adata.obs that correspond to continuous data.

  • ordinal_regression_order (dict[str, list[str]] | None (default: None)) – Dictionary with regression classes as keys and order of classes as values.

  • kwargs – Additional parameters to pass to register_fields() of AnnDataManager.

MILClassifier.to_device(device)#

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
MILClassifier.train(max_epochs=200, lr=0.0005, accelerator='auto', devices='auto', train_size=0.9, validation_size=None, batch_size=256, weight_decay=0.001, eps=1e-08, early_stopping=True, save_best=True, check_val_every_n_epoch=None, n_epochs_kl_warmup=None, n_steps_kl_warmup=None, adversarial_mixing=False, plan_kwargs=None, early_stopping_monitor='accuracy_validation', early_stopping_mode='max', save_checkpoint_every_n_epochs=None, path_to_checkpoints=None, **kwargs)#

Trains the model using amortized variational inference.

Parameters:

  • max_epochs (int (default: 200)) – Number of passes through the dataset.

  • lr (float (default: 0.0005)) – Learning rate for optimization.

  • accelerator (str (default: 'auto')) – Supports passing different accelerator types (“cpu”, “gpu”, “tpu”, “mps”, “auto”). Default is “auto”, which automatically selects the best available accelerator.

  • devices (int | list[int] | str (default: 'auto')) – Number of devices to train on (int), list of device indices (list[int]), or "auto" (default) to use all available devices.

  • 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.

  • batch_size (int (default: 256)) – Minibatch size to use during training.

  • weight_decay (float (default: 0.001)) – weight decay regularization term for optimization

  • eps (float (default: 1e-08)) – Optimizer eps

  • early_stopping (bool (default: True)) – Whether to perform early stopping with respect to the validation set.

  • save_best (bool (default: True)) – Save the best model state with respect to the validation loss, or use the final state in the training procedure

  • check_val_every_n_epoch (int | None (default: None)) – Check val every n train epochs. By default, val is not checked, unless early_stopping is True. If so, val is checked every epoch.

  • n_epochs_kl_warmup (int | None (default: None)) – Number of epochs to scale weight on KL divergences from 0 to 1. Overrides n_steps_kl_warmup when both are not None. Default is 1/3 of max_epochs.

  • n_steps_kl_warmup (int | None (default: None)) – Number of training steps (minibatches) to scale weight on KL divergences from 0 to 1. Only activated when n_epochs_kl_warmup is set to None. If None, defaults to floor(0.75 * adata.n_obs)

  • adversarial_mixing (bool (default: False)) – Whether to use adversarial mixing. Default is False.

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

  • early_stopping_monitor (str | None (default: 'accuracy_validation')) – Metric to monitor for early stopping. Default is “accuracy_validation”.

  • early_stopping_mode (str | None (default: 'max')) – One of “min” or “max”. Default is “max”.

  • save_checkpoint_every_n_epochs (int | None (default: None)) – Save a checkpoint every n epochs.

  • path_to_checkpoints (str | None (default: None)) – Path to save checkpoints.

  • **kwargs – Other keyword args for Trainer.

Returns:

Trainer object.

MILClassifier.transfer_fields(adata, **kwargs)#

Transfer fields from a model to an AnnData object.

Return type:

AnnData

MILClassifier.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.

MILClassifier.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 | 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

MILClassifier.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

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

Return type:

None

MILClassifier.view_setup_method_args()#

Prints setup kwargs used to produce a given registry.

Parameters:

registry – Registry produced by an AnnDataManager.

Return type:

None