scallops.features.rank.rank_features

scallops.features.rank.rank_features(data, perturbation_column, reference_value, by=None, method='welch_t', min_labels=None, iqr_multiplier=None)

Rank features for characterizing perturbations.

Parameters:

  • data (AnnData) – Annotated data matrix.

  • perturbation_column (str) – Column in data.obs containing perturbation.

  • reference_value (str | None) – Reference value (e.g. NTC).

  • method (Literal['welch_t', 'student_t', 'mannwhitney']) – Statistical method to use.

  • by (Sequence[str] | str | None) – Column(s) in data.obs to stratify by.

  • min_labels (int | None) – Include perturbations with at least this many observations.

  • iqr_multiplier (float | None) – Multiplier for interquartile range outlier removal.

Returns:

A DataFrame with statistics for each comparison.