API

Import SpaRED:

import spared

Datasets

datasets.get_dataset(dataset_name[, visualize])

Get a dataset from name.

`filtering.filter_by_moran`(adata, n_keep, ...)	Filter prediction genes by Moran's I.
`filtering.filter_dataset`(adata, param_dict)	Perform complete filtering pipeline of a slide collection.
`filtering.get_slide_from_collection`(...)	Retrieve a slide from a collection of slides.
`filtering.get_slides_adata`(collection, ...)	Get list of slides from collection

`gene_features.get_exp_frac`(adata)	Compute the expression fraction for all genes.
`gene_features.get_glob_exp_frac`(adata)	Compute the global expression fraction for all genes.
`gene_features.compute_moran`(adata, ...)	Compute Moran's I statistic for each gene.

`spot_features.compute_patches_embeddings`(adata)	Compute embeddings for patches.
`spot_features.compute_patches_predictions`(adata)	Compute predictions for patches.
`spot_features.compute_dim_red`(adata, from_layer)	Compute dimensionality reductions and clusters
`spot_features.get_spatial_neighbors`(adata, ...)	Compute neighbors dictionary for an AnnData object.

`layer_operations.tpm_normalization`(organism, ...)	Normalize expression using TPM normalization.
`layer_operations.log1p_transformation`(adata, ...)	Perform \(\log_2(x+1)\) transformation
`layer_operations.combat_transformation`(...)	Perform batch correction with ComBat
`layer_operations.get_deltas`(adata, ...)	Get expression deltas from the mean.
`layer_operations.add_noisy_layer`(adata, ...)	Add an artificial noisy layer.
`layer_operations.process_dataset`(adata, ...)	Perform complete processing pipeline.

`denoising.median_cleaner`(collection, ...)	Remove noise with adaptive median filter.
`denoising.spackle_cleaner`(adata, dataset, ...)

`graph_operations.get_graphs_one_slide`(adata, ...)	Get neighbor graphs for a single slide.
`graph_operations.get_sin_cos_positional_embeddings`(...)	Get positional encodings for a neighbor graph.
`graph_operations.get_graphs`(adata, n_hops, layer)	Get graphs for all the slides in a dataset.

`plotting.plot_all_slides`(dataset, ...)	Plot all the whole slide images
`plotting.plot_exp_frac`(param_dict, dataset, ...)	Plot heatmap of expression fraction
`plotting.plot_histograms`(processed_adata, ...)	Plot filtering histograms
`plotting.plot_random_patches`(dataset, ...[, ...])	Plot random set of patches
`plotting.visualize_moran_filtering`(...[, top])	Plot the most or least auto-correlated genes
`plotting.visualize_gene_expression`(...)	Plot specific gene expression
`plotting.plot_clusters`(dataset, param_dict, ...)	Plot clusters spatially
`plotting.plot_mean_std`(dataset, ...)	Plot mean and std of all genes
`plotting.plot_data_distribution_stats`(...)	Plot dataset's general stats
`plotting.plot_mean_std_partitions`(dataset, ...)	Plot mean and std of genes by data split
`plotting.plot_tests`(patch_size, dataset, ...)	Plot all quality control plots

`dataloaders.get_pretrain_dataloaders`(adata)	Get dataloaders for pretraining an image encoder.
`dataloaders.get_graph_dataloaders`(adata[, ...])	Get dataloaders for the graphs of a dataset.

`metrics.get_pearsonr`(gt_mat, pred_mat, mask, ...)	This function receives 2 matrices of shapes (n_observations, n_variables) and computes the average Pearson correlation.
`metrics.get_r2_score`(gt_mat, pred_mat, mask)	This function receives 2 matrices of shapes (n_observations, n_variables) and computes the average R2 score.
`metrics.get_metrics`(gt_mat, pred_mat, mask)	Get general regression metrics