runTrex: Trex single cell calculation

In ncborcherding/Trex: Methods for TCR single-cell embedding

Trex single cell calculation

Description

Run Trex algorithm with Seurat or SingleCellExperiment pipelines

Usage

runTrex(
  sc,
  chains = "TRA",
  method = "encoder",
  encoder.model = "VAE",
  encoder.input = "AF",
  theta = pi,
  reduction.name = "Trex"
)

Arguments

sc	Single Cell Object in Seurat or SingleCell Experiment format
chains	TRA or TRB
method	"encoder" = using deep learning autoencoders or "geometric" = geomteric transformations based on BLOSUM62 matrix
encoder.model	"AE" = dense autoencoder or "VAE" = variation autoencoder
encoder.input	Atchley factors (AF), Kidera factors ((AF)), or or One-Hot Encoder (OHE).
theta	angle to use for geometric transformation
reduction.name	Keyword to save Trex reduction. Useful if you want to try Trex with multiple parameters

Value

Seurat or SingleCellExperiment object with Trex dimensions placed into the dimensional reduction slot.

Examples

trex_example <- runTrex(trex_example, 
                        chains = "TRA",
                        method = "encoder",
                        encoder.model = "VAE",
                        encoder.input = "AF")
                        

ncborcherding/Trex documentation built on Nov. 4, 2024, 10:31 p.m.