Plotting: `pl`#

Functions to visualize your model’s predictions or contribution scores.

render_plot(fig[, width, height, title, ...])

Render a plot with customization options.

Patterns: Contribution scores and Modisco results#

`patterns.contribution_scores`(scores, ...[, ...])	Visualize interpretation scores with optional highlighted positions.
`patterns.modisco_results`(classes, ...[, ...])	Plot genomic contributions for the given classes.
`patterns.enhancer_design_steps_contribution_scores`(...)	Visualize enhancer design stepwise contribution scores.
`patterns.enhancer_design_steps_predictions`(...)	Visualize enhancer design prediction score progression.
`patterns.selected_instances`(pattern_dict, idcs)	Plot the patterns specified by the indices in `idcs` from the `pattern_dict`.
`patterns.class_instances`(pattern_dict, idx)	Plot instances of a specific pattern, either the representative pattern per class or all instances for a given pattern index.
`patterns.clustermap`(pattern_matrix, classes)	Create a clustermap from the given pattern matrix and class labels with customizable options.
`patterns.clustermap_with_pwm_logos`(...[, ...])	Create a clustermap with additional PWM logo plots below the heatmap.
`patterns.clustermap_tf_motif`(data[, ...])	Generate a heatmap where one modality is represented as color, and the other as dot size.
`patterns.tf_expression_per_cell_type`(df, tf_list)	Plot the expression levels of specified transcription factors (TFs) per cell type.
`patterns.similarity_heatmap`(...[, fig_size, ...])	Plot a similarity heatmap of all pattern indices.

`bar.region`(adata, region[, target])	Barplot of groundtruths or predictions for a specific region comparing classes.
`bar.region_predictions`(adata, region[, ...])	Barplots of all predictions in .layers vs the groundtruth for a specific region across comparing classes.
`bar.normalization_weights`(adata, **kwargs)	Plot the distribution of normalization scaling factors per cell type.

hist.distribution(adata[, target, ...])

Histogram of region distribution for specified classes.

`heatmap.correlations_self`(adata[, ...])	Plot self correlation heatmaps of ground truth for different cell types.
`heatmap.correlations_predictions`(adata[, ...])	Plot correlation heatmaps of predictions vs ground truth or target values for different cell types.

`locus.locus_scoring`(scores, range[, ...])	Plot the predictions as a line chart over the entire genomic input and optionally indicate the gene locus.
`locus.track`(scores[, range, title, ylim])	Plot a predicted locus track, like a Borzoi prediction or BigWig track.

scatter.class_density(adata[, class_name, ...])

Plot a density scatter plot of predictions vs ground truth for specified models and class.

violin.correlations(adata[, model_names, ...])

Plot correlation violinplots of predictions vs ground truth for different cell types.