Creation: cytof_data

class cytomulate.creation.cytof_data.CreationCytofData(n_batches=1, n_types=10, n_markers=20, n_trees=2, background_noise_model=None)

Bases: GeneralCytofData

generate_cell_graph(**kwargs)

Generate cell differentiation paths

This method is part of complex simulation’s cellular trajectory simulation. It generates differentiation paths, which will be used at the sampling stage.

Parameters:

kwargs – Parameters used for trajectory generation

Return type:

None

initialize_cell_types(L=4, scale=0.5, n_components=1, variance_mode=0.01)

Initialize cell type models.

This method initialzes the models for each cell type. Namely, a Gaussian Mixture Model is generated for each cell type at this stage according to the parameters specified.

Parameters:

• L (int) – Number of levels of expressions. The levels are used to differentiate between cell types whose expressions for the same marker may be different. We recommend at least 2, but not too many.

• scale (float) – The scale parameter used in generating expression levels’ mean, which comes from a truncated normal distribution on the positive reals. The scale is the standard the deviation of the distribution. When the scale is large, the levels of expressions are more spead out, and vice versa.

• n_components (int) – Number of components in a GMM.

• variance_mode (float) – The mode of the variance of the inverse wishart distribution.

Return type:

None