deepspatial.core.DeepSpatial

deepspatial.core.DeepSpatial#

class deepspatial.core.DeepSpatial[source]#

DeepSpatial: Reconstructing True 3D Spatial Omics at Single-Cell Resolution.

__init__()[source]#

Initializes an empty DeepSpatial instance. Configurations and paths are injected during functional method calls.

Methods

__init__()

Initializes an empty DeepSpatial instance.

build_model([patch_size, hidden_size, ...])

Instantiates the GiT network architecture and Flow Matching logic.

fit([max_epochs, save_dir, accelerator, ...])

Executes the training loop using PyTorch Lightning.

load_checkpoint(ckpt_path[, config_path, ...])

Loads model weights and metadata for inference or resuming.

reconstruct_between_slices(adata0, adata1, ...)

Generates a 3D volume segment between two specific AnnData slices.

reconstruct_full_volume(adata_list, thickness)

High-level API to reconstruct the entire 3D volume from a list of slices.

setup_data(adata_list[, spatial_key, z_key, ...])

Prepares the data pipeline and calculates physical normalization statistics.