Tools: tl

Image Embedding

tl.feature_extraction	Extract features from WSI tiles using a pre-trained vision models.
tl.feature_aggregation	Aggregate features by groups.
tl.spatial_features	Integrate spatial tile graph context with vision model features using spatial feature smoothing.

Tissue/Tile Properties

tl.tissue_props	Compute a series of geometric features of tissue pieces
tl.tile_prediction	Predict tiles using a tile prediction model.

Tissue Spatial Domain

tl.spatial_domain	Perform unsupervised spatial domain segmentation on a WSI using feature embeddings.
tl.tile_shaper	Return the domain shapes of the WSI by merging tiles with the same types that are spatially aggregated into polygons using geopandas dissolve.

Multi-Modal Analysis

tl.text_embedding	Embed the text into a vector in the text-vision co-embedding using
tl.text_image_similarity	Compute the similarity between text and image.
tl.RNALinker	Link the aggregated WSI features with other omics data.

Zero-shot Learning

tl.zero_shot_score	Perform zero-shot learning classification on the WSI
tl.slide_caption	Generate captions for the slide.

Generative Modeling

tl.virtual_stain	Translate the H&E images to multiplexed images.
tl.image_generation	Generation of tile images unconditionally or conditionally.