External API

Note

More tools that integrate well with scanpy and anndata can be found on the ecosystem page.

Import Scanpy’s wrappers to external tools as:

import scanpy.external as sce

If you’d like to include a tool here, consider making a pull request (instructions). If the tool already uses scanpy or anndata, it may fit better in the ecosystem page.

Preprocessing: PP

Data integration

`pp.bbknn`(adata[, batch_key, use_rep, ...])	Batch balanced kNN [Polanski19].
`pp.harmony_integrate`(adata, key[, basis, ...])	Use harmonypy [Korunsky19] to integrate different experiments.
`pp.mnn_correct`(*datas[, var_index, ...])	Correct batch effects by matching mutual nearest neighbors [Haghverdi18] [Kang18].
`pp.scanorama_integrate`(adata, key[, basis, ...])	Use Scanorama [Hie19] to integrate different experiments.

Sample demultiplexing, Doublet detection

`pp.scrublet`(adata[, adata_sim, batch_key, ...])	Predict doublets using Scrublet [Wolock19].
`pp.scrublet_simulate_doublets`(adata[, ...])	Simulate doublets by adding the counts of random observed transcriptome pairs.
`pl.scrublet_score_distribution`(adata[, ...])	Plot histogram of doublet scores for observed transcriptomes and simulated doublets.
`pp.hashsolo`(adata, cell_hashing_columns[, ...])	Probabilistic demultiplexing of cell hashing data using HashSolo [Bernstein20].

Imputation

Note that the fundamental limitations of imputation are still under debate.

`pp.dca`(adata[, mode, ae_type, ...])	Deep count autoencoder [Eraslan18].
`pp.magic`(adata[, name_list, knn, decay, ...])	Markov Affinity-based Graph Imputation of Cells (MAGIC) API [vanDijk18].

Tools: TL

Embeddings

`tl.phate`(adata[, n_components, k, a, ...])	PHATE [Moon17].
`tl.palantir`(adata[, n_components, knn, ...])	Run Diffusion maps using the adaptive anisotropic kernel [Setty18].
`tl.trimap`(adata[, n_components, n_inliers, ...])	TriMap: Large-scale Dimensionality Reduction Using Triplets [Amid19].
`tl.sam`(adata[, max_iter, num_norm_avg, k, ...])	Self-Assembling Manifolds single-cell RNA sequencing analysis tool [Tarashansky19].

Clustering and trajectory inference

`tl.phenograph`(adata[, clustering_algo, k, ...])	PhenoGraph clustering [Levine15].
`tl.harmony_timeseries`(adata, tp[, ...])	Harmony time series for data visualization with augmented affinity matrix at discrete time points [Nowotschin18i].
`tl.wishbone`(adata, start_cell[, branch, k, ...])	Wishbone identifies bifurcating developmental trajectories from single-cell data [Setty16].
`tl.palantir`(adata[, n_components, knn, ...])	Run Diffusion maps using the adaptive anisotropic kernel [Setty18].
`tl.palantir_results`(adata, early_cell[, ...])	Running Palantir

Gene scores, Cell cycle

`tl.sandbag`(adata[, annotation, fraction, ...])	Calculate marker pairs of genes.
`tl.cyclone`(adata[, marker_pairs, ...])	Assigns scores and predicted class to observations [Scialdone15] [Fechtner18].

Plotting: PL

`pl.phate`(adata, **kwargs)	Scatter plot in PHATE basis.
`pl.trimap`(adata, **kwargs)	Scatter plot in TriMap basis.
`pl.sam`(adata[, projection, c, cmap, ...])	Scatter plot using the SAM projection or another input projection.
`pl.wishbone_marker_trajectory`(adata, markers)	Plot marker trends along trajectory, and return trajectory branches for further analysis and visualization (heatmap, etc..)

Exporting

`exporting.spring_project`(adata, project_dir, ...)	Exports to a SPRING project directory [Weinreb17].
`exporting.cellbrowser`(adata, data_dir, data_name)	Export adata to a UCSC Cell Browser project directory.