plot_biplot: Make biplots of the multisnpnet results

In junyangq/multiSnpnet: Fit a sparse reduced rank regression model on large-scale SNP data and multivariate responses

Make biplots of the multisnpnet results

Description

Generate biplot visualization based on the decomposed coefficient matrix C.

Usage

plot_biplot(
  svd_obj,
  component = list(x = 1, y = 2),
  label = list(phenotype = NULL, variant = NULL),
  n_labels = list(phenotype = 5, variant = 5),
  color = list(phenotype = "orange", variant = "sky.blue"),
  shape = list(phenotype = 20, variant = 4),
  axis_label = list(main = "variant", sub = "phenotype"),
  use_ggrepel = TRUE
)

Arguments

svd_obj	A named list containing three matrices with u, d, and v as their names as in the output from base::svd() function. One can pass the results of base::svd(t(fit$C)) or tsvd_of_C_with_names(fit) Please note that this function assumes svd_obj$u and svd_obj$v corresponds to phenotypes and variants, respectively.
component	A named list that specifies the index of the components used in the plot.
label	A named list that specifies the phenotype and variant labels. The labels needs to be the same order as in svd_obj$u and svd_obj$v.
n_labels	A named list that specifies the number of phenotype and variant labels in the plot.
color	A named list that specifies the color in the plot.
shape	A named list that specifies the color in the plot.
axis_label	A named list that specifies the names used in the axis labels.
use_ggrepel	A binary variable that specifies whether we should use ggrepel to annotate the labels of the data points.

Examples

plot_biplot(svd(t(fit$C)), label=list('phenotype'=rownames(A_init), 'variant'=rownames(fit$C)))

junyangq/multiSnpnet documentation built on Oct. 19, 2023, 8:22 p.m.