bento.tl.fluxmap¶
- bento.tl.fluxmap(sdata, points_key='transcripts', instance_key='cell_boundaries', n_clusters=range(2, 9), num_iterations=1000, min_count=50, train_size=1, res=1, random_state=11, plot_error=False)¶
Cluster flux embeddings using self-organizing maps (SOMs) and vectorize clusters as Polygon shapes.
- Parameters:
sdata (SpatialData) – Spatial formatted SpatialData object.
points_key (str) – key for points element that holds transcript coordinates
instance_key (str) – Key for cell_boundaries instances
n_clusters (int or list) – Number of clusters to use. If list, will pick best number of clusters using the elbow heuristic evaluated on the quantization error.
num_iterations (int) – Number of iterations to use for SOM training.
train_size (float) – Fraction of cells to use for SOM training. Default 0.2.
res (float) – Resolution used for rendering embedding. Default 0.05.
random_state (int) – Random state to use for SOM training. Default 11.
plot_error (bool) – Whether to plot quantization error. Default True.
- Returns:
sdata –
- .points[“points”]DataFrame
Adds “fluxmap” column denoting cluster membership.
- .shapes[“fluxmap#”]GeoSeries
Adds “fluxmap#” columns for each cluster rendered as (Multi)Polygon shapes.
- Return type:
SpatialData