runNMF: Compute NMF as a low-dim embedding for Seurat

In GeneNMF: Non-Negative Matrix Factorization for Single-Cell Omics

Compute NMF as a low-dim embedding for Seurat

Description

Compute NMF embeddings for single-cell dataset, and store them in the Seurat data structure. They can be used as an alternative to PCA for downstream analyses.

Usage

runNMF(
  obj,
  assay = "RNA",
  slot = "data",
  k = 10,
  new.reduction = "NMF",
  seed = 123,
  L1 = c(0, 0),
  hvg = NULL,
  center = FALSE,
  scale = FALSE
)

Arguments

obj	A seurat object
assay	Get data matrix from this assay
slot	Get data matrix from this slot (=layer)
k	Number of components for low-dim representation
new.reduction	Name of new dimensionality reduction
seed	Random seed
L1	L1 regularization term for NMF
hvg	Which genes to use for the reduction
center	Whether to center the data matrix
scale	Whether to scale the data matrix

Value

Returns a Seurat object with a new dimensionality reduction (NMF)

Examples

data(sampleObj)
sampleObj <- runNMF(sampleObj, k=8)

GeneNMF documentation built on June 8, 2025, 1:10 p.m.