mioXpektron.analysis.plots

Visualization helpers for downstream statistical analysis.

Functions

`plot_heatmap_top_features`(X, y, res, savepath, *)	Heatmap of top differential features (z-scored), samples ordered by group.
`plot_pca`(X_scaled, y, savepath, *[, ...])	PCA scatter plot coloured by group labels.
`plot_tsne`(X_scaled, y, savepath, *[, ...])	t-SNE scatter plot coloured by group labels.
`plot_umap`(X_scaled, y, savepath, *[, ...])	UMAP embedding plot when umap-learn is installed.
`plot_volcano`(res, savepath, *[, group_a, ...])	Volcano plot of log2 fold-change versus -log10(p-value).

mioXpektron.analysis.plots.plot_volcano(res, savepath, *, group_a=None, group_b=None, q_thresh=0.05, fc_thresh=1.0)[source]

Volcano plot of log2 fold-change versus -log10(p-value).

Parameters:

Return type:

None

mioXpektron.analysis.plots.plot_pca(X_scaled, y, savepath, *, random_state=0)[source]

PCA scatter plot coloured by group labels.

Parameters:

Return type:

Tuple[ndarray, ndarray]

mioXpektron.analysis.plots.plot_umap(X_scaled, y, savepath, *, n_neighbors=15, min_dist=0.1, random_state=0)[source]

UMAP embedding plot when umap-learn is installed.

Parameters:

Return type:

ndarray | None

mioXpektron.analysis.plots.plot_tsne(X_scaled, y, savepath, *, perplexity=30.0, random_state=0)[source]

t-SNE scatter plot coloured by group labels.

Parameters:

Return type:

ndarray

mioXpektron.analysis.plots.plot_heatmap_top_features(X, y, res, savepath, *, top_n=25, label_col='Group')[source]

Heatmap of top differential features (z-scored), samples ordered by group.

Parameters:

Return type:

None