moscot.problems.generic.GENOTLinProblem

class moscot.problems.generic.GENOTLinProblem(adata, **kwargs)[source]

Class for solving Conditional Parameterized Monge Map problems / Conditional Neural OT problems.

Methods

cell_transition(source, target[, ...])

Aggregate the transport matrix.

compute_entropy(source, target[, forward, ...])

Compute the conditional entropy per cell.

compute_feature_correlation(obs_key[, ...])

Compute correlation of push-forward or pull-back distribution with features.

load(path)

Load the model from a file.

prepare(key, joint_attr, conditional_attr[, ...])

Prepare the moscot.problems.generic.GENOTLinProblem.

pull(source, target[, data, subset, ...])

Pull mass from target to source.

push(source, target[, data, subset, ...])

Push mass from source to target.

save(path[, overwrite])

Save the problem to a file.

solve([batch_size, seed, iterations, ...])

Solve.

Attributes

adata

Source annotated data object.

batch_key

Batch key in obs.

distributions

Collection of distributions.

policy

Policy used to subset the data.

problem_kind

Kind of the underlying problem.

solution

Solution of the optimal transport problem.

solver

Solver of the optimal transport problem.

stage

Problem stage.

Parameters: