scvi.external.METHYLVI#
- class scvi.external.METHYLVI(mdata, n_hidden=128, n_latent=10, n_layers=1, **model_kwargs)[source]#
Model class for methylVI [Weinberger and Lee, 2023]
- Parameters:
mdata (
MuData
) – MuData object that has been registered viasetup_mudata()
.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
METHYLVAE
Examples
>>> mdata = mudata.read_h5mu(path_to_mudata) >>> MethylVI.setup_mudata(mdata, batch_key="batch") >>> vae = MethylVI(mdata) >>> vae.train() >>> mdata.obsm["X_methylVI"] = vae.get_latent_representation()
Attributes table#
Data attached to model instance. |
|
Manager instance associated with self.adata. |
|
The current device that the module's params are on. |
|
Returns computed metrics during training. |
|
Whether the model has been trained. |
|
Summary string of the model. |
|
Observations that are in test set. |
|
Observations that are in train set. |
|
Observations that are in validation set. |
Methods table#
|
Converts a legacy saved model (<v0.15.0) to the updated save format. |
|
Deregisters the |
|
. |
|
Retrieves the |
|
Compute the evidence lower bound (ELBO) on the data. |
|
Returns the object in AnnData associated with the key in the data registry. |
|
Compute the latent representation of the data. |
|
Compute the marginal log-likehood of the data. |
|
Returns the normalized (decoded) methylation. |
|
Compute the reconstruction error on the data. |
|
Convenience function to obtain normalized methylation values for a single context. |
|
Instantiate a model from the saved output. |
|
Online update of a reference model with scArches algorithm [Lotfollahi et al., 2021]. |
|
Return the full registry saved with the model. |
|
Generate observation samples from the posterior predictive distribution. |
|
Prepare data for query integration. |
|
Prepare multimodal dataset for query integration. |
|
Registers an |
|
Save the state of the model. |
|
Sets up the |
|
Sets up the |
|
Move model to device. |
|
Train the model. |
|
Print summary of the setup for the initial AnnData or a given AnnData object. |
|
Print args used to setup a saved model. |
Attributes#
Methods#
- classmethod METHYLVI.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. IfFalse
and directory already exists atoutput_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:
- METHYLVI.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.
- METHYLVI.differential_methylation(mdata=None, groupby=None, group1=None, group2=None, idx1=None, idx2=None, mode='vanilla', delta=0.05, batch_size=None, all_stats=True, batch_correction=False, batchid1=None, batchid2=None, fdr_target=0.05, silent=False, two_sided=True, **kwargs)[source]#
.
A unified method for differential methylation analysis.
Implements “vanilla” DE [Lopez et al., 2018]. and “change” mode DE [Boyeau et al., 2019].
- Parameters:
%(de_mdata)s
%(de_modality)s
%(de_groupby)s
%(de_group1)s
%(de_group2)s
%(de_idx1)s
%(de_idx2)s
%(de_mode)s
%(de_delta)s
%(de_batch_size)s
%(de_all_stats)s
%(de_batch_correction)s
%(de_batchid1)s
%(de_batchid2)s
%(de_fdr_target)s
%(de_silent)s
two_sided (
bool
(default:True
)) – Whether to perform a two-sided test, or a one-sided test.**kwargs – Keyword args for
scvi.model.base.DifferentialComputation.get_bayes_factors()
- Return type:
- Returns:
Differential methylation DataFrame with the following columns: proba_de
the probability of the region being differentially methylated
- is_de_fdr
whether the region passes a multiple hypothesis correction procedure with the target_fdr threshold
- bayes_factor
Bayes Factor indicating the level of significance of the analysis
- effect_size
the effect size, computed as (accessibility in population 2) - (accessibility in population 1)
- emp_effect
the empirical effect, based on observed detection rates instead of the estimated accessibility scores from the methylVI model
- scale1
the estimated methylation level in population 1
- scale2
the estimated methylation level in population 2
- emp_mean1
the empirical (observed) methylation level in population 1
- emp_mean2
the empirical (observed) methylation level in population 2
- METHYLVI.get_anndata_manager(adata, required=False)[source]#
Retrieves the
AnnDataManager
for a given AnnData object.Requires
self.id
has been set. Checks for anAnnDataManager
specific to this model instance.- Parameters:
- Return type:
- METHYLVI.get_elbo(adata=None, indices=None, batch_size=None, dataloader=None, return_mean=True, **kwargs)[source]#
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 (
AnnData
|None
(default:None
)) –AnnData
object withvar_names
in the same order as the ones used to train the model. IfNone
anddataloader
is alsoNone
, it defaults to the object used to initialize the model.indices (
Sequence
[int
] |None
(default:None
)) – Indices of observations inadata
to use. IfNone
, defaults to all observations. Ignored ifdataloader
is notNone
.batch_size (
int
|None
(default:None
)) – Minibatch size for the forward pass. IfNone
, defaults toscvi.settings.batch_size
. Ignored ifdataloader
is notNone
.dataloader (
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 ofTensor
with keys as expected by the model. IfNone
, a dataloader is created fromadata
.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:
- Returns:
Evidence lower bound (ELBO) of the data.
Notes
This is not the negative ELBO, so higher is better.
- METHYLVI.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.
- METHYLVI.get_latent_representation(adata=None, indices=None, give_mean=True, mc_samples=5000, batch_size=None, return_dist=False, dataloader=None)[source]#
Compute the latent representation of the data.
This is typically denoted as \(z_n\).
- Parameters:
adata (
AnnData
|None
(default:None
)) –AnnData
object withvar_names
in the same order as the ones used to train the model. IfNone
anddataloader
is alsoNone
, it defaults to the object used to initialize the model.indices (
Sequence
[int
] |None
(default:None
)) – Indices of observations inadata
to use. IfNone
, defaults to all observations. Ignored ifdataloader
is notNone
give_mean (
bool
(default:True
)) – IfTrue
, returns the mean of the latent distribution. IfFalse
, returns an estimate of the mean usingmc_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 ifgive_mean
isTrue
or ifreturn_dist
isTrue
.batch_size (
int
|None
(default:None
)) – Minibatch size for the forward pass. IfNone
, defaults toscvi.settings.batch_size
. Ignored ifdataloader
is notNone
return_dist (
bool
(default:False
)) – IfTrue
, returns the mean and variance of the latent distribution. Otherwise, returns the mean of the latent distribution.dataloader (
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 ofTensor
with keys as expected by the model. IfNone
, a dataloader is created fromadata
.
- Return type:
ndarray
[Any
,dtype
[TypeVar
(_ScalarType_co
, bound=generic
, covariant=True)]] |tuple
[ndarray
[Any
,dtype
[TypeVar
(_ScalarType_co
, bound=generic
, covariant=True)]],ndarray
[Any
,dtype
[TypeVar
(_ScalarType_co
, bound=generic
, covariant=True)]]]- Returns:
An array of shape
(n_obs, n_latent)
ifreturn_dist
isFalse
. Otherwise, returns a tuple of arrays(n_obs, n_latent)
with the mean and variance of the latent distribution.
- METHYLVI.get_marginal_ll(adata=None, indices=None, n_mc_samples=1000, batch_size=None, return_mean=True, dataloader=None, **kwargs)[source]#
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 (
AnnData
|None
(default:None
)) –AnnData
object withvar_names
in the same order as the ones used to train the model. IfNone
anddataloader
is alsoNone
, it defaults to the object used to initialize the model.indices (
Sequence
[int
] |None
(default:None
)) – Indices of observations inadata
to use. IfNone
, defaults to all observations. Ignored ifdataloader
is notNone
.n_mc_samples (
int
(default:1000
)) – Number of Monte Carlo samples to use for the estimator. Passed into the module’smarginal_ll
method.batch_size (
int
|None
(default:None
)) – Minibatch size for the forward pass. IfNone
, defaults toscvi.settings.batch_size
. Ignored ifdataloader
is notNone
.return_mean (
bool
(default:True
)) – Whether to return the mean of the marginal log-likelihood or the marginal-log likelihood for each observation.dataloader (
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 ofTensor
with keys as expected by the model. IfNone
, a dataloader is created fromadata
.**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.
- METHYLVI.get_normalized_methylation(mdata=None, indices=None, region_list=None, n_samples=1, n_samples_overall=None, batch_size=None, return_mean=True, return_numpy=None, **importance_weighting_kwargs)[source]#
Returns the normalized (decoded) methylation.
This is denoted as \(\mu_n\) in the methylVI paper.
- Parameters:
mdata (
MuData
|None
(default:None
)) – MuData object with equivalent structure to initial Mudata. If None, defaults to the MuData object used to initialize the model.indices (
Sequence
[int
] |None
(default:None
)) – Indices of cells in mdata to use. If None, all cells are used.region_list (
Sequence
[str
] |None
(default:None
)) – Return frequencies of expression for a subset of regions. This can save memory when working with large datasets and few regions are of interest.n_samples (
int
(default:1
)) – Number of posterior samples to use for estimation.n_samples_overall (
int
(default:None
)) – Number of posterior samples to use for estimation. Overrides n_samples.batch_size (
int
|None
(default:None
)) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.return_mean (
bool
(default:True
)) – Whether to return the mean of the samples.return_numpy (
bool
|None
(default:None
)) – Return andarray
instead of aDataFrame
. DataFrame includes region names as columns. If either n_samples=1 or return_mean=True, defaults to False. Otherwise, it defaults to True.
- Return type:
- Returns:
If n_samples is provided and return_mean is False, this method returns a 3d tensor of shape (n_samples, n_cells, n_regions). If n_samples is provided and return_mean is True, it returns a 2d tensor of shape (n_cells, n_regions). In this case, return type is
DataFrame
unless return_numpy is True. Otherwise, the method expects n_samples_overall to be provided and returns a 2d tensor of shape (n_samples_overall, n_regions).If model was set up using a MuData object, a dictionary is returned with keys corresponding to individual methylation contexts with values determined as described above.
- METHYLVI.get_reconstruction_error(adata=None, indices=None, batch_size=None, dataloader=None, return_mean=True, **kwargs)[source]#
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 (
AnnData
|None
(default:None
)) –AnnData
object withvar_names
in the same order as the ones used to train the model. IfNone
anddataloader
is alsoNone
, it defaults to the object used to initialize the model.indices (
Sequence
[int
] |None
(default:None
)) – Indices of observations inadata
to use. IfNone
, defaults to all observations. Ignored ifdataloader
is notNone
batch_size (
int
|None
(default:None
)) – Minibatch size for the forward pass. IfNone
, defaults toscvi.settings.batch_size
. Ignored ifdataloader
is notNone
dataloader (
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 ofTensor
with keys as expected by the model. IfNone
, a dataloader is created fromadata
.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:
- Returns:
Reconstruction error for the data.
Notes
This is not the negative reconstruction error, so higher is better.
- METHYLVI.get_specific_normalized_methylation(mdata=None, context=None, indices=None, transform_batch=None, region_list=None, n_samples=1, n_samples_overall=None, weights=None, batch_size=None, return_mean=True, return_numpy=None, **importance_weighting_kwargs)[source]#
Convenience function to obtain normalized methylation values for a single context.
Only applicable to MuData models.
- Parameters:
mdata (
MuData
|None
(default:None
)) – MuData object with equivalent structure to initial MuData. If None, defaults to the MuData object used to initialize the model.context (
str
(default:None
)) – Methylation context for which to obtain normalized methylation levels.indices (
Sequence
[int
] |None
(default:None
)) – Indices of cells in mdata to use. If None, all cells are used.transform_batch (
Sequence
[int
|float
|str
] |None
(default:None
)) –Batch to condition on. If transform_batch is:
None, then real observed batch is used.
int, then batch transform_batch is used.
region_list (
Sequence
[str
] |None
(default:None
)) – Return frequencies of expression for a subset of regions. This can save memory when working with large datasets and few regions are of interest.n_samples (
int
(default:1
)) – Number of posterior samples to use for estimation.n_samples_overall (
int
(default:None
)) – Number of posterior samples to use for estimation. Overrides n_samples.weights (
Optional
[Literal
['uniform'
,'importance'
]] (default:None
)) – Weights to use for sampling. If None, defaults to “uniform”.batch_size (
int
|None
(default:None
)) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.return_mean (
bool
(default:True
)) – Whether to return the mean of the samples.return_numpy (
bool
|None
(default:None
)) – Return andarray
instead of aDataFrame
. DataFrame includes region names as columns. If either n_samples=1 or return_mean=True, defaults to False. Otherwise, it defaults to True.importance_weighting_kwargs – Keyword arguments passed into
_get_importance_weights()
.
- Return type:
- Returns:
If n_samples is provided and return_mean is False, this method returns a 3d tensor of shape (n_samples, n_cells, n_regions). If n_samples is provided and return_mean is True, it returns a 2d tensor of shape (n_cells, n_regions). In this case, return type is
DataFrame
unless return_numpy is True. Otherwise, the method expects n_samples_overall to be provided and returns a 2d tensor of shape (n_samples_overall, n_regions).
- classmethod METHYLVI.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_....
- classmethod METHYLVI.load_query_data(adata, reference_model, inplace_subset_query_vars=False, accelerator='auto', device='auto', unfrozen=False, freeze_dropout=False, freeze_expression=True, freeze_decoder_first_layer=True, freeze_batchnorm_encoder=True, freeze_batchnorm_decoder=False, freeze_classifier=True)[source]#
Online update of a reference model with scArches algorithm [Lotfollahi et al., 2021].
- Parameters:
adata (
AnnData
|MuData
) – 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 theregistry
.reference_model (
str
|BaseModelClass
) – Either an already instantiated model of the same class, or a path to saved outputs for reference model.inplace_subset_query_vars (
bool
(default:False
)) – Whether to subset and rearrange query vars inplace based on vars used to train reference 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.unfrozen (
bool
(default:False
)) – Override all other freeze options for a fully unfrozen modelfreeze_dropout (
bool
(default:False
)) – Whether to freeze dropout during trainingfreeze_expression (
bool
(default:True
)) – Freeze neurons corersponding to expression in first layerfreeze_decoder_first_layer (
bool
(default:True
)) – Freeze neurons corersponding to first layer in decoderfreeze_batchnorm_encoder (
bool
(default:True
)) – Whether to freeze batchnorm weight and bias during training for encoderfreeze_batchnorm_decoder (
bool
(default:False
)) – Whether to freeze batchnorm weight and bias during training for decoderfreeze_classifier (
bool
(default:True
)) – Whether to freeze classifier completely. Only applies to SCANVI.
- static METHYLVI.load_registry(dir_path, prefix=None)[source]#
Return the full registry saved with the model.
- METHYLVI.posterior_predictive_sample(mdata=None, n_samples=1, batch_size=None)[source]#
Generate observation samples from the posterior predictive distribution.
The posterior predictive distribution is written as \(p(\hat{x} \mid x)\).
- Parameters:
mdata (
MuData
|None
(default:None
)) – MuData object with equivalent structure to initial MuData. If None, defaults to the MuData object used to initialize the model.n_samples (
int
(default:1
)) – Number of samples for each cell.batch_size (
int
|None
(default:None
)) – Minibatch size for data loading into model. Defaults to scvi.settings.batch_size.
- Return type:
- Returns:
x_new :
torch.Tensor
tensor with shape (n_cells, n_regions, n_samples)
- static METHYLVI.prepare_query_anndata(adata, reference_model, return_reference_var_names=False, inplace=True)[source]#
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 theregistry
.reference_model (
str
|BaseModelClass
) – Either an already instantiated model of the same class, or a path to saved outputs for 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:
- 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 METHYLVI.prepare_query_mudata(mdata, reference_model, return_reference_var_names=False, inplace=True)[source]#
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 model. It is not necessary to run setup_mudata, as MuData is validated against theregistry
.reference_model (
str
|BaseModelClass
) – Either an already instantiated model of the same class, or a path to saved outputs for 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:
- 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 METHYLVI.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 thesetup_anndata()
class method followed up by retrieval of theAnnDataManager
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 previousAnnDataManager
.
- METHYLVI.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 anndatasave_kwargs (
dict
|None
(default:None
)) – Keyword arguments passed intosave()
.legacy_mudata_format (
bool
(default:False
)) – IfTrue
, saves the modelvar_names
in the legacy format if the model was trained with aMuData
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 METHYLVI.setup_anndata(adata, **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.
- classmethod METHYLVI.setup_mudata(mdata, mc_layer, cov_layer, methylation_contexts, batch_key=None, categorical_covariate_keys=None, modalities=None, **kwargs)[source]#
Sets up the
MuData
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:
mdata (
MuData
) – MuData object. Rows represent cells, columns represent features.mc_layer (
str
) – Layer containing methylated cytosine counts for each set of methylation features.cov_layer (
str
) – Layer containing total coverage counts for each set of methylation features.methylation_contexts (
Iterable
[str
]) – List of modality fields in mdata object representing different methylation contexts. Each context must be equipped with a layer containing the number of methylated counts (specified by mc_layer) and total number of counts (specified by cov_layer) for each genomic region feature.batch_key (
str
|None
(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.%(param_categorical_covariate_keys)s
modalities (default:
None
) – Dictionary mapping parameters to modalities.
Examples
- MethylVI.setup_mudata(
mdata, mc_layer=”mc”, cov_layer=”cov”, batch_key=”Platform”, methylation_modalities=[‘mCG’, ‘mCH’], modalities={
“batch_key”: “mCG”
},
)
- METHYLVI.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
- METHYLVI.train(max_epochs=None, accelerator='auto', devices='auto', train_size=0.9, 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)[source]#
Train the model.
- Parameters:
max_epochs (
int
|None
(default:None
)) – The maximum number of epochs to train the model. The actual number of epochs may be less if early stopping is enabled. IfNone
, defaults to a heuristic based onget_max_epochs_heuristic()
. Must be passed in ifdatamodule
is passed in, and it does not have ann_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 (
float
(default:0.9
)) – Size of training set in the range[0.0, 1.0]
. Passed intoDataSplitter
. Not used ifdatamodule
is passed in.validation_size (
float
|None
(default:None
)) – Size of the test set. IfNone
, defaults to1 - train_size
. Iftrain_size + validation_size < 1
, the remaining cells belong to a test set. Passed intoDataSplitter
. Not used ifdatamodule
is passed in.shuffle_set_split (
bool
(default:True
)) – Whether to shuffle indices before splitting. IfFalse
, the val, train, and test set are split in the sequential order of the data according tovalidation_size
andtrain_size
percentages. Passed intoDataSplitter
. Not used ifdatamodule
is passed in.load_sparse_tensor (
bool
(default:False
)) –EXPERIMENTAL
IfTrue
, loads data with sparse CSR or CSC layout as aTensor
with the same layout. Can lead to speedups in data transfers to GPUs, depending on the sparsity of the data. Passed intoDataSplitter
. Not used ifdatamodule
is passed in.batch_size (
int
(default:128
)) – Minibatch size to use during training. Passed intoDataSplitter
. Not used ifdatamodule
is passed in.early_stopping (
bool
(default:False
)) – Perform early stopping. Additional arguments can be passed in through**kwargs
. SeeTrainer
for further options.datasplitter_kwargs (
dict
|None
(default:None
)) – Additional keyword arguments passed intoDataSplitter
. Values in this argument can be overwritten by arguments directly passed into this method, when appropriate. Not used ifdatamodule
is passed in.plan_kwargs (
dict
|None
(default:None
)) – Additional keyword arguments passed intoTrainingPlan
. Values in this argument can be overwritten by arguments directly passed into this method, when appropriate.datamodule (
LightningDataModule
|None
(default:None
)) –EXPERIMENTAL
ALightningDataModule
instance to use for training in place of the defaultDataSplitter
. Can only be passed in if the model was not initialized withAnnData
.**kwargs – Additional keyword arguments passed into
Trainer
.