SIngle-cell eMBedding Along with features

API

Import simba as:

import simba as si

Configuration for SIMBA

settings.set_figure_params([context, style, ...])	Set global parameters for figures.
settings.set_pbg_params([config])	Set PBG parameters
settings.set_workdir([workdir])	Set working directory.

Reading

read_csv(filename[, delimiter, ...])	Read .csv file.
read_h5ad(filename[, backed, as_sparse, ...])	Read .h5ad-formatted hdf5 file.
read_10x_h5(filename[, genome, gex_only])	Read 10x-Genomics-formatted hdf5 file.
read_mtx(filename[, dtype])	Read .mtx file.
read_embedding([path_emb, path_entity, ...])	Read in entity embeddings from pbg training
load_pbg_config([path])	Load PBG configuration into global setting
load_graph_stats([path])	Load graph statistics into global setting

See more at anndata

Preprocessing

pp.log_transform(adata)	Return the natural logarithm of one plus the input array, element-wise.
pp.normalize(adata[, method, scale_factor, ...])	Normalize count matrix.
pp.binarize(adata[, threshold])	Binarize an array.
pp.cal_qc(adata[, expr_cutoff])	Calculate quality control metrics.
pp.cal_qc_rna(adata[, expr_cutoff])	Calculate quality control metrics.
pp.cal_qc_atac(adata[, expr_cutoff])	Calculate quality control metrics.
pp.filter_samples(adata[, min_n_features, ...])	Filter out samples based on different metrics.
pp.filter_cells_rna(adata[, min_n_genes, ...])	Filter out cells for RNA-seq based on different metrics.
pp.filter_cells_atac(adata[, min_n_peaks, ...])	Filter out cells for ATAC-seq based on different metrics.
pp.filter_features(adata[, min_n_samples, ...])	Filter out features based on different metrics.
pp.filter_genes(adata[, min_n_cells, ...])	Filter out features based on different metrics.
pp.filter_peaks(adata[, min_n_cells, ...])	Filter out features based on different metrics.
pp.pca(adata[, n_components, algorithm, ...])	perform Principal Component Analysis (PCA)
pp.select_pcs(adata[, n_pcs, S, curve, ...])	select top PCs based on variance_ratio
pp.select_pcs_features(adata[, S, curve, ...])	select features that contribute to the top PCs
pp.select_variable_genes(adata[, layer, ...])	Select highly variable genes.

Tools

tl.discretize(adata[, layer, n_bins, max_bins])	Discretize continous values
tl.umap(adata[, n_neighbors, n_components, ...])	perform UMAP :param adata: Annotated data matrix.
tl.gene_scores(adata, genome[, gene_anno, ...])	Calculate gene scores
tl.infer_edges(adata_ref, adata_query[, ...])	Infer edges between reference and query observations
tl.trim_edges(adata_ref_query[, cutoff, n_edges])	Trim edges based on the similarity scores
tl.gen_graph([list_CP, list_PM, list_PK, ...])	Generate graph for PBG training.
tl.pbg_train([dirname, pbg_params, output, ...])	PBG training
tl.softmax(adata_ref, adata_query[, T, ...])	Softmax-based transformation
tl.embed(adata_ref, list_adata_query[, T, ...])	Embed a list of query datasets along with reference dataset into the same space
tl.compare_entities(adata_ref, adata_query)	Compare the embeddings of two entities by calculating
tl.query(adata[, obsm, layer, metric, ...])	Query the "database" of entites
tl.find_master_regulators(adata_all[, ...])	Find all the master regulators
tl.find_target_genes(adata_all, adata_PM[, ...])	For a given TF, infer its target genes

Plotting

pl.pca_variance_ratio(adata[, log, ...])	Plot the variance ratio.
pl.pcs_features(adata[, log, size, ...])	Plot features that contribute to the top PCs.
pl.variable_genes(adata[, show_texts, ...])	Plot highly variable genes.
pl.violin(adata[, list_obs, list_var, ...])	Violin plot
pl.hist(adata[, list_obs, list_var, kde, ...])	histogram plot
pl.umap(adata[, color, dict_palette, ...])	Plot coordinates in UMAP
pl.discretize(adata[, kde, fig_size, pad, ...])	Plot original data VS discretized data
pl.node_similarity(adata[, bins, log, ...])	Plot similarity scores of nodes
pl.svd_nodes(adata[, comp1, comp2, color, ...])	Plot SVD coordinates
pl.pbg_metrics([metrics, path_emb, ...])	Plot PBG training metrics
pl.entity_metrics(adata_cmp, x, y[, ...])	Plot entity metrics
pl.entity_barcode(adata_cmp, entities[, ...])	Plot query entity barcode
pl.query(adata[, comp1, comp2, obsm, layer, ...])	Plot query output

Datasets

datasets.rna_10xpmbc3k()	10X human peripheral blood mononuclear cells (PBMCs) scRNA-seq data
datasets.rna_han2018()	single-cell microwell-seq mouse cell atlas data
datasets.rna_tmc2018()	single-cell Smart-Seq2 mouse cell atlas data
datasets.rna_baron2016()	single-cell RNA-seq human pancreas data
datasets.rna_muraro2016()	single-cell RNA-seq human pancreas data
datasets.rna_segerstolpe2016()	single-cell RNA-seq human pancreas data
datasets.rna_wang2016()	single-cell RNA-seq human pancreas data
datasets.rna_xin2016()	single-cell RNA-seq human pancreas data
datasets.atac_buenrostro2018()	single cell ATAC-seq human blood data
datasets.atac_10xpbmc5k()	10X human peripheral blood mononuclear cells (PBMCs) scATAC-seq data
datasets.atac_chen2019()	simulated scATAC-seq bone marrow data with a noise level of 0.4 and a coverage of 2500 fragments
datasets.atac_cusanovich2018_subset()	downsampled sci-ATAC-seq mouse tissue data
datasets.multiome_ma2020_fig4()	single cell multiome mouse skin data (SHARE-seq)
datasets.multiome_chen2019()	single cell multiome neonatal mouse cerebral cortex data (SNARE-seq)
datasets.multiome_10xpbmc10k()	single cell 10X human peripheral blood mononuclear cells (PBMCs) multiome data