scvi.model.base.DifferentialComputation#
- class scvi.model.base.DifferentialComputation(model_fn, representation_fn, adata_manager)[source]#
Unified class for differential computation.
This class takes a function from a model like
SCVIorTOTALVIand takes outputs from this function with respect to the adata input and computed Bayes factors as described in [Lopez et al., 2018], [Xu et al., 2021], or [Boyeau et al., 2019].- Parameters:
- model_fn
Callable Callable in model API to get values from.
- representation_fn
Callable Callable providing latent representations, e.g.,
get_latent_representation(), for scVI.- adata_manager
AnnDataManager AnnDataManager created by
setup_anndata().
- model_fn
Methods table#
|
Filters out cells that are outliers in the representation space. |
|
A unified method for differential expression inference. |
|
If selection is a mask, convert it to indices. |
|
Samples the posterior scale using the variational posterior distribution. |
Methods#
- DifferentialComputation.filter_outlier_cells(selection)[source]#
Filters out cells that are outliers in the representation space.
- DifferentialComputation.get_bayes_factors(idx1, idx2, mode='change', batchid1=None, batchid2=None, use_observed_batches=False, n_samples_overall=5000, use_permutation=False, m_permutation=10000, change_fn=None, m1_domain_fn=None, delta=0.5, pseudocounts=None, threshold_counts=0.01, test_mode='three', cred_interval_lvls=None)[source]#
A unified method for differential expression inference.
Two modes coexist:
The
'vanilla'mode follows protocol described in [Lopez et al., 2018] and [Xu et al., 2021].In this case, we perform hypothesis testing based on the hypotheses.
\[M_1: h_1 > h_2 ~\text{and}~ M_2: h_1 \leq h_2.\]DE can then be based on the study of the Bayes factors
\[\log p(M_1 | x_1, x_2) / p(M_2 | x_1, x_2).\]The
'change'mode (described in [Boyeau et al., 2019]).This mode consists of estimating an effect size random variable (e.g., log fold-change) and performing Bayesian hypothesis testing on this variable. The
change_fnfunction computes the effect size variable \(r\) based on two inputs corresponding to the posterior quantities (e.g., normalized expression) in both populations.
Hypotheses:
\[M_1: r \in R_1 ~\text{(effect size r in the region inducing differential expression)}\]\[M_2: r \notin R_1 ~\text{(no differential expression)}\]To characterize the region \(R_1\), which induces DE, the user has two choices.
A common case is when the region \([-\delta, \delta]\) does not induce differential expression. If the user specifies a threshold delta, we suppose that \(R_1 = \mathbb{R} \setminus [-\delta, \delta]\)
Specify a specific indicator function:
\[f: \mathbb{R} \mapsto \{0, 1\} ~\text{s.t.}~ r \in R_1 ~\text{iff.}~ f(r) = 1.\]Decision-making can then be based on the estimates of
\[p(M_1 \mid x_1, x_2).\]Both modes require sampling the posterior distributions. For that purpose, we sample the posterior in the following way:
The posterior is sampled
n_samples_overalltimes for each subpopulation.For computational efficiency (posterior sampling is quite expensive), instead of comparing the obtained samples element-wise, we can permute posterior samples. Remember that computing the Bayes Factor requires sampling \(q(z_A \mid x_A)\) and \(q(z_B \mid x_B)\).
Currently, the code covers several batch handling configurations:
If
use_observed_batches=True, then batches are considered as observations and cells’ normalized means are conditioned on real batch observations.If case (cell group 1) and control (cell group 2) are conditioned on the same batch ids. This requires
set(batchid1) == set(batchid2)orbatchid1 == batchid2 === None.If case and control are conditioned on different batch ids that do not intersect, i.e.,
set(batchid1) != set(batchid2)andlen(set(batchid1).intersection(set(batchid2))) == 0.
This function does not cover other cases yet and will warn users in such cases.
- Parameters:
- mode
Literal['vanilla','change'] (default:'change') one of [“vanilla”, “change”]
- idx1
list[bool] |ndarray bool array masking subpopulation cells 1. Should be True where cell is from associated population
- idx2
list[bool] |ndarray bool array masking subpopulation cells 2. Should be True where cell is from associated population
- batchid1
Sequence[int|float|str] |None(default:None) List of batch ids for which you want to perform DE Analysis for subpopulation 1. By default, all ids are taken into account
- batchid2
Sequence[int|float|str] |None(default:None) List of batch ids for which you want to perform DE Analysis for subpopulation 2. By default, all ids are taken into account
- use_observed_batches
bool|None(default:False) Whether posterior values are conditioned on observed batches
- n_samples_overall
int(default:5000) Number of overall posterior samples
- use_permutation
bool(default:False) Activates step 2 described above. Simply formulated, pairs obtained from posterior sampling will be randomly permuted so that the number of pairs used to compute Bayes Factors becomes
m_permutation.- m_permutation
int(default:10000) Number of times we will “mix” posterior samples in step 2. Only makes sense when
use_permutation=True- change_fn
str|Callable|None(default:None) function computing effect size based on both posterior values
- m1_domain_fn
Callable|None(default:None) custom indicator function of effect size regions inducing differential expression
- delta
float|None(default:0.5) specific case of region inducing differential expression. In this case, we suppose that \(R \setminus [-\delta, \delta]\) does not induce a differential expression (LFC case). If the provided value is
None, then a proper threshold is determined from the distribution of LFCs across genes.- pseudocounts
float|None(default:None) pseudocount offset used for the mode
change. When None, observations from non-expressed genes are used to estimate its value.- threshold_counts
float(default:0.01) mean expression threshold in a group to consider a gene as non-expressed
- test_mode
Literal['two','three'] (default:'three') consider down- and up-regulated genes separately (three) or all genes together (two)
- cred_interval_lvls
list[float] |ndarray|None(default:None) List of credible interval levels to compute for the posterior LFC distribution
- mode
- Return type:
- Returns:
Differential expression properties
- DifferentialComputation.process_selection(selection)[source]#
If selection is a mask, convert it to indices.
- Return type:
- DifferentialComputation.scale_sampler(selection, n_samples_overall=5000, n_samples_per_cell=None, batchid=None, use_observed_batches=False, give_mean=False)[source]#
Samples the posterior scale using the variational posterior distribution.
- Parameters:
- selection
list[bool] |ndarray Mask or list of cell ids to select
- n_samples_overall
int|None(default:5000) Number of samples in total per batch (fill either
n_samples_totalorn_samples_per_cell)- n_samples_per_cell
int|None(default:None) Number of time we sample from each observation per batch (fill either
n_samples_totalorn_samples_per_cell)- batchid
Sequence[int|float|str] |None(default:None) Biological batch for which to sample from. Default (None) sample from all batches
- use_observed_batches
bool|None(default:False) Whether normalized means are conditioned on observed batches or if observed batches are to be used
- give_mean
bool|None(default:False) Return mean of values
- selection
- Return type:
- Returns:
type Dictionary containing:
scalePosterior aggregated scale samples of shape (n_samples, n_vars) where n_samples correspond to either: - n_bio_batches * n_cells * n_samples_per_cell or - n_samples_totalbatchassociated batch ids