Models

Models fit gene expression trends in pseudotime; they assume some parametric form for the gene trend and estimate parameters using an objective function. Note that some models require you to have R and rpy2 installed.

models.GAM(adata[, n_knots, spline_order, ...])	Fit Generalized Additive Models (GAMs) using pygam.
models.GAMR(adata[, n_knots, distribution, ...])	Wrapper around R's mgcv package for fitting GAMs.
models.SKLearnModel(adata, model[, ...])	Wrapper around BaseEstimator.

Signals

Signals identify the observation-aligned quantity a model is fit on. Pass them to cellrank.pl.gene_trends() or cellrank.models.BaseModel.prepare() to plot gene expression, an obs covariate (e.g. a gene module score), or a column of an obsm array.

models.Signal()	Continuous, observation-aligned signal to fit along a trajectory.
models.Gene(gene[, layer, use_raw])	Gene expression signal, fetched from X, a layer, or raw.
models.Obs(key)	A numeric per-cell covariate stored in obs, e.g. a gene module score.
models.Obsm(key, column)	A single column of an obsm array or DataFrame.