crested.pl.patterns.enhancer_design_steps_contribution_scores

crested.pl.patterns.enhancer_design_steps_contribution_scores(intermediate, scores_all, seqs_one_hot_all, labels=None, zoom_n_bases=None, ylim=None, global_ylim='per_plot', method=None, **kwargs)

Visualize enhancer design stepwise contribution scores.

Contribution scores can be calculated using the calculate_contribution_scores_enhancer_design() method.

Parameters:

• intermediate (list[dict]) – Intermediate output from enhancer design when return_intermediate is True

• scores_all (ndarray) – An array of a list of arrays of contribution scores of shape (n_seqs, n_classes, n_bases, n_features).

• seqs_one_hot_all (ndarray) – An array of a list of arrays of one-hot encoded corresponding sequences of shape (n_seqs, n_bases, n_features).

• labels (Optional[list] (default: None)) – List of labels to add to the plot. Should have the same length as the number of classes.

• zoom_n_bases (Optional[int] (default: None)) – Number of center bases to zoom in on. Default is None (no zooming).

• ylim (Optional[tuple] (default: None)) – Y-axis limits, ignored if global_ylim is set. Default is None.

• global_ylim (str | None (default: 'per_plot')) – Used to set global y-axis limits across explanations. Can be one of ‘all’, ‘per_design’, ‘per_plot’ or None. Default is ‘per_plot’ ‘all’ makes the y-axis limit same across all of the explanations. ‘per_design’ makes the y-axis limit same across all of the steps and classes of a single designed sequence. ‘per_plot’ makes y-axis limits same across all the steps but not the classes of a single designed sequence. If None, each explanation has its y-axis limits seperately selected.

• method (Optional[str] (default: None)) – Method used for calculating contribution scores. If mutagenesis, specify.