- class moscot.problems.time.LineageProblem(adata, **kwargs)#
Estimator for modelling time series single cell data based on [Lange et al., 2023].
add_problem(key, problem, *[, overwrite])
Add a subproblem.
cell_transition(source, target, ...[, ...])
Aggregate the transport matrix.
compute_batch_distances(time, batch_key[, ...])
Compute the average Wasserstein distance between batches for a specific time point.
Compute correlation of push-forward or pull-back distribution with features.
compute_interpolated_distance(source, ...[, ...])
compute_random_distance(source, ...[, ...])
Compute Wasserstein distance between randomly interpolated and intermediate cells.
compute_time_point_distances(source, ...[, ...])
Compute Wasserstein distance between time points.
Load the model from a file.
prepare(time_key[, lineage_attr, ...])
Prepare the lineage problem problem.
pull(source, target[, data, subset, ...])
Pull mass from target to source.
push(source, target[, data, subset, ...])
Push mass from source to target.
Remove a subproblem.
sankey(source, target, source_groups, ...[, ...])
Compute a Sankey diagram between cells across time points.
Save the problem to a file.
Compute gene scores to obtain prior knowledge about proliferation and apoptosis.
solve([alpha, epsilon, tau_a, tau_b, rank, ...])
Solve the lineage problem.
Annotated data object.
obswhere cell apoptosis is stored.
Cell cost obtained by the first dual potential.
Cell cost obtained by the second dual potential.
Posterior estimate of the source growth rates.
Prior estimate of the source growth rates.
Kind of the underlying problem.
OT subproblems that define the biological problem.
obswhere cell proliferation is stored.
Solutions to the
Temporal key in