bootstrap_prediction {scGPS} | R Documentation |
ElasticNet and LDA prediction for each of all the subpopulations in the new mixed population after training the model for a subpopulation in the first mixed population. The number of bootstraps to be run can be specified.
bootstrap_prediction( nboots = 1, genes = genes, mixedpop1 = mixedpop1, mixedpop2 = mixedpop2, c_selectID = NULL, listData = list(), cluster_mixedpop1 = NULL, cluster_mixedpop2 = NULL, trainset_ratio = 0.5, LDA_run = TRUE, verbose = FALSE, log_transform = FALSE )
nboots |
a number specifying how many bootstraps to be run |
genes |
a gene list to build the model |
mixedpop1 |
a SingleCellExperiment object from a mixed population for training |
mixedpop2 |
a SingleCellExperiment object from a target mixed population for prediction |
c_selectID |
the root cluster in mixedpop1 to becompared to clusters in mixedpop2 |
listData |
a |
cluster_mixedpop1 |
a vector of cluster assignment for mixedpop1 |
cluster_mixedpop2 |
a vector of cluster assignment for mixedpop2 |
trainset_ratio |
a number specifying the proportion of cells to be part of the training subpopulation |
LDA_run |
logical, if the LDA prediction is added to compare to ElasticNet |
verbose |
a logical whether to display additional messages |
log_transform |
boolean whether log transform should be computed |
a list
with prediction results written in to the index
out_idx
Quan Nguyen, 2017-11-25
bootstrap_parallel
for parallel options
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$Merged_unique cluster_mixedpop1 <- colData(mixedpop1)[,1] cluster_mixedpop2 <- colData(mixedpop2)[,1] c_selectID <- 2 test <- bootstrap_prediction(nboots = 1, mixedpop1 = mixedpop1, mixedpop2 = mixedpop2, genes=genes, listData =list(), cluster_mixedpop1 = cluster_mixedpop1, cluster_mixedpop2 = cluster_mixedpop2, c_selectID = c_selectID) names(test) test$ElasticNetPredict test$LDAPredict