I would like to show the single cell gene expression. My question is which one is preferable, using mean standard error (Fig 1) or box plot (Fig 2) in my plot?

enter image description here

Any explanation (or paper) that suggest why one method is prefers to other?

This is the R code I use to generate those figs:

library(tidyverse)
library(ggpubr)

dat <- structure(list(gexp = c(
  4.2, 11.5, 7.3, 5.8, 6.4, 10, 11.2, 11.2,
  5.2, 7, 16.5, 16.5, 15.2, 17.3, 22.5, 17.3, 13.6, 14.5, 18.8,
  15.5, 23.6, 18.5, 33.9, 25.5, 26.4, 32.5, 26.7, 21.5, 23.3, 29.5,
  15.2, 21.5, 17.6, 9.7, 14.5, 10, 8.2, 9.4, 16.5, 9.7, 19.7, 23.3,
  23.6, 26.4, 20, 25.2, 25.8, 21.2, 14.5, 27.3, 25.5, 26.4, 22.4,
  24.5, 24.8, 30.9, 26.4, 27.3, 29.4, 23
), supp = structure(c(
  2L,
  2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
  2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L,
  1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
  1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L
), .Label = c(
  "OJ",
  "VC"
), class = "factor"), dose = c(
  0.5, 0.5, 0.5, 0.5, 0.5, 0.5,
  0.5, 0.5, 0.5, 0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2,
  2, 2, 2, 2, 2, 2, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5,
  0.5, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  2
)), row.names = c(NA, -60L), class = c("tbl_df", "tbl", "data.frame"))


p1 <- ggbarplot(dat, x = "dose", y = "gexp", 
          add = "mean_se")

p2 <- ggboxplot(dat, x = "dose", y = "gexp")

cowplot::plot_grid(p1, p2, labels =  c("Fig 1", "Fig 2"))



Source link