Single Cell

BioAlpha single-cell is an algorithmic framework that can run full single-cell analysis pipeline on Python for large biological datasets in realtime.

Import BioAlpha single-cell as:

from bioalpha import singlecell as sc

or:

from bioalpha import sc

Following the BioAlpha Tutorial and AUCell Tutorial to see how to use it.

Preprocessing: pp

bioalpha.singlecell.pp provides basic transformation on data.

`preprocessing.filter_cells`	Filter cell outliers based on counts and numbers of genes expressed.
`preprocessing.filter_genes`	Filter genes based on number of cells or counts.
`preprocessing.calculate_qc_metrics`	Calculate quality control metrics.
`preprocessing.log_normalize`	Normalize counts per cell and calculate log1p.
`preprocessing.log1p`	Logarithmize the data matrix.
`preprocessing.highly_variable_genes`	Annotate highly variable genes.
`preprocessing.regress_out`	Regress out (mostly) unwanted sources of variation.
`preprocessing.scale`	Scale data to unit variance and zero mean.
`preprocessing.pca`	Principal component analysis.
`preprocessing.subsample`	Subsample to a fraction of the number of observations.
`preprocessing.harmony_integrate`	Use harmony algorithm to integrate different experiments.
`preprocessing.combine_keys`	Combine keys in `adata.obs`.
`preprocessing.neighbors`	Compute a neighborhood graph of observations.

Provide methods for an interpretable annotation and visualizing with parallel module on bioalpha.sc.pl.

`tools.kmeans`	Cluster cells into subgroups.
`tools.louvain`	Cluster cells into subgroups.
`tools.tsne`	Run t-SNE t-distributed stochastic neighborhood embedding (tSNE).
`tools.umap`	Embed the neighborhood graph using UMAP (Uniform Manifold Approximation and Projection).
`tools.rank_genes_groups`	Rank genes for characterizing groups.
`tools.aucell`	Calculate enrichment of gene signatures for single cells.

`plotting.highest_expr_genes`	Fraction of counts assigned to each gene over all cells.
`plotting.highly_variable_genes`	Plot dispersions or normalized variance versus means for genes.
`plotting.tsne`	Scatter plot in tSNE basis.
`plotting.umap`	Scatter plot in UMAP basis.
`plotting.rank_genes_groups_volcano`	Plot ranking of genes using volcano plot.
`plotting.aucell_heatmap`	Plotting AUC scores of cells and gene_sets.
`plotting.aucell`	Plotting AUC scores of cells and gene_sets.

`read_10x_mtx`	Fast read `10x-Genomics-formatted mtx` directory.
`read_10x_h5`	Read 10x-Genomics-formatted hdf5 file.
`read_h5ad`	Read .h5ad-formatted hdf5 file.
`read_mtx`	Fast reading algorithm for `mtx` files.
`read_gene_signatures`	Read gene signatures from `JSON` file.
`read_gene_signatures_gmt`	Read gene signatures from `GMT` file.
`read_gene_signatures_GSEA`	Read gene signatures from `GSEA` (https://www.gsea-msigdb.org/).
`get_gene_signatures_name_from_GSEA`	Get gene signature name from `GSEA` (https://www.gsea-msigdb.org/).
`download_GEO_data`	Download suplementary file of data from GEO (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi).

Write Bioturing format.

`experimental.tools.find_marker`	Identifies marker genes.
`experimental.tools.thresholding`	Find threshold to cut-off and smooth the expression matrix.