optimalModel: Get the optimal LDA model

In JEFworks-Lab/STdeconvolve: Reference-free Cell-Type Deconvolution of Multi-Cellular Spatially Resolved Transcriptomics Data

Get the optimal LDA model

Description

Get the optimal LDA model

Usage

optimalModel(models, opt)

Arguments

models	list returned from fitLDA
opt	either "kneed" (kOpt1) or "min" (kOpt2), or designate a specific K. "kneed" = K vs perplexity inflection point. "min" = K corresponding to minimum perplexity "proportion" = K vs number of cell-type with mean proportion < 5% inflection point

Value

optimal LDA model fitted to the K based on opt parameter

Examples

data(mOB)
pos <- mOB$pos
cd <- mOB$counts
counts <- cleanCounts(cd, min.lib.size = 100)
corpus <- restrictCorpus(counts, removeAbove=1.0, removeBelow = 0.05)
ldas <- fitLDA(t(as.matrix(corpus)), Ks = seq(2,4), ncores=2)
optLDA <- optimalModel(models = ldas, opt = "min")

JEFworks-Lab/STdeconvolve documentation built on Nov. 14, 2024, 7:24 p.m.