Plotting

Plotting functions return Matplotlib axes and do not modify the object.

Plates and quality control

pl.plate(adata, color[, plate, groupby, ...])	Well-grid heatmap of color, one panel per plate.
pl.cell_counts(adata[, groupby, ax, count_key])	Distribution of cells per well, split by groupby.
pl.feature_distributions(adata, features[, ...])	Per-feature distributions, before and after normalization when layer_before exists.
pl.nan_matrix(adata[, max_features, ax])	Fraction of missing values per feature, per plate.
pl.qc(adata[, figsize])	Two-by-two summary of the QC metrics calculate_qc_metrics() writes.
pl.plate_effects(adata[, feature, axes])	Row and column medians per plate, for spotting plate position artifacts.
pl.image_qc(adata[, ax])	Image quality score per image, with the flagged images marked.
pl.control_drift(adata[, groupby, ...])	Control wells projected onto principal components fitted on the controls alone.
pl.outliers(adata[, key, groupby, axes])	Outlier score distribution, and the flagged fraction per groupby group.

Features

pl.feature_correlation(adata[, key, ...])	Correlation heatmap with features ordered by their annotation.
pl.feature_groups(adata[, key, ax])	How many features each group contributes, split by channel.

Replicates and reproducibility

pl.map(adata[, key, label_top, ax])	Mean average precision against significance, with the strongest groups labeled.
pl.replicate_correlation(adata[, key, ax])	Observed replicate correlation against each group's permutation threshold.
pl.similarity(adata[, key, groupby, max_obs, ax])	Profile-by-profile similarity, ordered by groupby so blocks are visible.
pl.setting_agreement(adata[, key, by, ...])	Settings against settings: which plates, batches or laboratories agree with each other.
pl.transport(adata[, key, level, top, ax])	Agreement per perturbation, ranked, with the ones that reproduce colored.
pl.replicate_saturation(adata[, key, ax])	The saturation curve with its spread across draws.

Batch correction

pl.batch_variance(adata, keys[, use_rep, ...])	R^2 of each principal component on each covariate.
pl.metrics(table[, ax])	Grouped bars of an evaluate_correction() table.

Hits and effect sizes

pl.hits(adata[, key, label_top, ax])	Distance from the controls against significance, with the most distant groups labeled.
pl.effect_sizes(adata, group[, key, top, ax])	The largest effects for one group, colored by feature family.
pl.feature_volcano(adata, group[, key, ...])	Effect against significance, per feature, for one group.
pl.feature_signature(adata[, groupby, top, ...])	Heatmap of perturbations by feature families.
pl.cytotoxicity(adata[, key, label_top, ax])	Distance from the controls against viability, with the suspect groups marked.

Dose response

pl.dose_response(adata, compound[, key, ...])	One compound's response against dose, with the fitted curve when there is one.
pl.dose_direction(adata, compound[, key, ax])	One compound's ladder, with the background banded by what each concentration is doing.

Mechanism of action

pl.moa_confusion(adata[, key, normalize, ax])	The confusion matrix of nn_moa_classify(), as a heatmap.
pl.moa_enrichment(adata, group[, key, top, ax])	Which mechanisms one profile's neighborhood is enriched for.
pl.distance_heatmap(adata[, key, groupby, ax])	The group-by-group distance matrix, ordered so related groups sit together.

Feature sets

pl.sets_heatmap(adata, groupby[, score_key, ...])

Mean enrichment score per group per feature set.

Clusters and gene sets

pl.dendrogram(adata[, key, color_threshold, ax])	Draw the hierarchical clustering tree stored by cluster().
pl.pathway_coherence(adata[, key, top, ax])	Coherence per gene set, the significant ones marked.

Single cells

pl.cluster_composition(composition[, ...])	Stacked bars of cell-state fractions, averaged within each group.
pl.cell_cycle(adata, dna_feature[, by, key, ...])	Log DNA intensity per group, colored by assigned phase.
pl.density(adata, feature[, groupby, key, ...])	Local cell density against a feature, per group.
pl.subpopulation_hits(adata[, key, top, ax])	Cluster by group heatmap of significance, so an effect in one cell state stands out.