reformat_LASSO: summarise bootstrap runs for Lasso model, from 'n' bootstraps

In scGPS: A complete analysis of single cell subpopulations, from identifying subpopulations to analysing their relationship (scGPS = single cell Global Predictions of Subpopulation)

Description

the training and prediction results from bootstrap were written to the object LSOLDA_dat, the reformat_LASSO summarises prediction for n bootstrap runs

Usage

reformat_LASSO(c_selectID = NULL, mp_selectID = NULL,
  LSOLDA_dat = NULL, nPredSubpop = NULL, Nodes_group = "#7570b3",
  nboots = 2)

Arguments

c_selectID	is the original cluster to be projected
mp_selectID	is the target mixedpop to project to
LSOLDA_dat	is the results from the bootstrap
nPredSubpop	is the number of clusters in the target mixedpop row_cluster <-length(unique(target_cluster))
Nodes_group	string representation of hexidecimal color code for node
nboots	is an integer for how many bootstraps are run

Value

a dataframe containg information for the Lasso prediction results, each column contains prediction results for all subpopulations from each bootstrap run

Examples

c_selectID<-1
day2 <- day_2_cardio_cell_sample
mixedpop1 <-new_scGPS_object(ExpressionMatrix = day2$dat2_counts, 
    GeneMetadata = day2$dat2geneInfo, CellMetadata = day2$dat2_clusters)
day5 <- day_5_cardio_cell_sample
mixedpop2 <-new_scGPS_object(ExpressionMatrix = day5$dat5_counts, 
    GeneMetadata = day5$dat5geneInfo, CellMetadata = day5$dat5_clusters)
genes <-training_gene_sample
genes <-genes$Merged_unique
LSOLDA_dat <- bootstrap_prediction(nboots = 2, mixedpop1 = mixedpop1, 
    mixedpop2 = mixedpop2, genes=genes, c_selectID, listData =list(),
    cluster_mixedpop1 = colData(mixedpop1)[,1],
    cluster_mixedpop2=colData(mixedpop2)[,1])
reformat_LASSO(LSOLDA_dat=LSOLDA_dat, 
    nPredSubpop=length(unique(colData(mixedpop2)[,1])), c_selectID = 1, 
    mp_selectID =2, nboots = 2)

scGPS documentation built on Nov. 8, 2020, 5:22 p.m.