kmeans_clustering: Kmeans Clustering - returns classification result

In tinglab/redPATH: Reconstructing the pseudo development time of cell lineages in single cell RNA-Seq data and applications in cancer.

Description

This function performs imple kmeans clustering and prepares as input for identification of G0 cells

Usage

kmeans_clustering(mean_scores, k = 5, nstart = 100)

Arguments

mean_scores	The mean score results returned from the reCAT software, "get_score"
k	The number of clusters, defaults to 5. ie G0, G1, S, G2, M cycle stages
nstart	Defaults to 100. Number of times to start the kmeans clustering, ensure stability of clustering results.

Examples

cycle_mean_scores <- get_score(t(test_exp))$mean_score
kmean_classification <- kmeans_clustering(cycle_mean_scores)
statistical_test(cycle_mean_scores, kmean_classification, threshold = 0.001)
# Sample output
#"Possible group of G0-like cells is: 2"

tinglab/redPATH documentation built on May 31, 2019, 10:37 a.m.