SPCAselect: SPCA gene selection
In lingxuez/SOUP: Semi-soft Clustering of Single Cell Data

Description Usage Arguments Value References

Select highly variable genes for clustering using Sparse Principal Component Analysis (SPCA).

1	SPCAselect(expr, type = "log", sumabs = 0.05, nPC = 3)

`expr`	a cell-by-gene expression matrix, either the raw counts or log-transformed expressions.
`type`	"log" if `expr` has been normalized and log-transformed (default), or "count" if `expr` contains the raw counts. SPCA works best on sub-Gaussian data, so log-transformation is highly recommended.
`sumabs`	a measurement of sparsity for SPCA, between `1/sqrt(n.gene)` and 1. Smaller values result in sparser results, hence fewer selected genes.
`nPC`	the number of sparse singular vectors to look into.

A list containing

select.genes: the names of selected genes, ordered by decreasing importance.
vectors: a gene-by-nPC matrix of the sparse eigen vectors.

Witten, DM and Tibshirani, R and T Hastie (2009) A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis. Biostatistics.

lingxuez/SOUP documentation built on May 28, 2019, 3:38 p.m.