Search code examples
rggplot2axis-labels

How to fit long labels on the x-axis into the ggplot2 window?

I'm trying to create an image for my GO enrichemnt categories. Unfortunately ggplot2 doesn't do what I would like it to do. My script is as follow:

sub <- readRDS("sub.RDS")
zsc.col <- c("firebrick1", "white", "dodgerblue1")

leg <- theme(legend.position = "bottom")
g <- ggplot(sub, aes(x = factor(term, levels = stats::reorder(term, adj_pval)), y = adj_pval, fill = zscore)) + 
  geom_bar(stat = "identity", colour = "black") + 
  scale_fill_gradient2("z-score", space = "Lab", low = zsc.col[3], mid = zsc.col[2], high = zsc.col[1], guide = guide_colourbar(title.position = "top", title.hjust = 0.5), breaks = c(min(sub$zscore), max(sub$zscore)), labels = c("decreasing", "increasing")) + 
  labs(title = "title", x = "", y = "-log (adj p-value)") + 
  leg + 
  theme(axis.text.x = element_text(angle = 45, vjust = 0.5 , hjust = 1), 
              axis.line = element_line(colour = "grey80"), axis.ticks = element_line(colour = "grey80"), 
              axis.title = element_text(size = 8, face = "bold"), axis.text = element_text(size = 8) #,
              #              panel.background = element_blank(), panel.border = element_blank(), 
              #              panel.grid.major = element_blank(), panel.grid.minor = element_blank(), 
              #              plot.background = element_blank()
  )

g

the results is displayed below. The first problem is the space between the x-axis and the plot. How can I eliminate this space to better fit the text to the plot? Than I would like the window to be big enough to fit the whole text on the x-axis? Is it possible?

thanks

Assa

the plot results: ggplot2 legend problem

Here is a dput() of the relevant columns of sub which are required to create the plot:

sub <- structure(list(term = c("mitochondrion", "ribosome", "nematode larval development", 
"embryo development ending in birth or egg hatching", "structural constituent of ribosome", 
"translation", "mitochondrial small ribosomal subunit", "receptor-mediated endocytosis", 
"reproduction", "mitochondrial translation", "mitochondrial large ribosomal subunit", 
"mitochondrial inner membrane", "intracellular ribonucleoprotein complex", 
"determination of adult lifespan", "mitochondrial respiratory chain complex I", 
"mitochondrial ribosome", "ATP synthesis coupled proton transport", 
"mitochondrial proton-transporting ATP synthase complex, coupling factor F(o)", 
"tRNA aminoacylation for protein translation", "aminoacyl-tRNA ligase activity", 
"respiratory chain", "NADH dehydrogenase (ubiquinone) activity", 
"protein import into mitochondrial matrix", "intracellular", 
"iron-sulfur cluster binding", "hydrogen ion transmembrane transporter activity", 
"NADH dehydrogenase activity", "oxidoreductase activity, acting on NAD(P)H", 
"rRNA binding", "proton-transporting ATP synthase activity, rotational mechanism", 
"ligase activity", "mitochondrial respiratory chain complex III assembly", 
"oxidation-reduction process", "4 iron, 4 sulfur cluster binding", 
"large ribosomal subunit", "mitochondrial membrane", "mitochondrial matrix", 
"hydrogen ion transmembrane transport", "RNA binding", "cytochrome-c oxidase activity", 
"mitochondrial electron transport, NADH to ubiquinone", "mitochondrial outer membrane", 
"electron carrier activity", "mitochondrion organization", "tricarboxylic acid cycle", 
"growth", "mitochondrial outer membrane translocase complex", 
"proton-transporting ATP synthase complex, coupling factor F(o)", 
"endoplasmic reticulum unfolded protein response", "mitochondrial fusion", 
"mitochondrial inner membrane presequence translocase complex", 
"integral component of mitochondrial outer membrane", "protein transport", 
"mitochondrial electron transport, ubiquinol to cytochrome c", 
"proton transport", "mitochondrial electron transport, cytochrome c to oxygen", 
"positive regulation of multicellular organism growth", "GTPase activity", 
"protein channel activity", "hermaphrodite genitalia development", 
"nucleotide binding", "ATP biosynthetic process", "tRNA aminoacylation"
), adj_pval = c(-1.84472129469146, -1.66688191109855, -1.62368742458875, 
-1.61251572036108, -1.49190847373791, -1.43330416336608, -1.3289293432033, 
-1.31769812469356, -1.29791331210987, -1.24849426411943, -1.13689595417821, 
-1.11242658986886, -1.05590022744309, -0.821808984933817, -0.816532663342381, 
-0.69535971673032, -0.60705167217058, -0.504866337850967, -0.50177430528028, 
-0.453524900193783, -0.445747643713484, -0.358775899528351, -0.279592150254413, 
-0.162917071897043, -0.150167590044187, -0.0852269401349886, 
-0.0807932210009663, -0.0135543009023059, 0.189719894742601, 
0.289792271789456, 0.291668388670687, 0.913510098585626, NaN, 
NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, 
NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, 
NaN, NaN, NaN, NaN), zscore = c(8.48528137423857, 6.557438524302, 
9.64365076099295, 10.3440804327886, 5.91607978309962, 6.08276253029822, 
4, 6.85565460040104, 8.60232526704263, 3.87298334620742, 3.46410161513775, 
4.24264068711929, 4.35889894354067, 5.91607978309962, 3, 2.44948974278318, 
2.64575131106459, 2.23606797749979, 2.64575131106459, 2.64575131106459, 
2.44948974278318, 2.44948974278318, 2.23606797749979, 3.87298334620742, 
2.44948974278318, 2.23606797749979, 2, 2, 2.23606797749979, 2, 
2.82842712474619, 1.73205080756888, 3.87298334620742, 2, 1.73205080756888, 
2, 2.23606797749979, 2, 3.16227766016838, 1.73205080756888, 1.73205080756888, 
1.73205080756888, 2, 1.73205080756888, 1.73205080756888, 2.44948974278318, 
1.41421356237309, 1.41421356237309, 2, 1.41421356237309, 1.41421356237309, 
1.41421356237309, 2.23606797749979, 1.41421356237309, 1.73205080756888, 
1.41421356237309, 2.82842712474619, 2, 1.41421356237309, 3.60555127546399, 
4, 1.41421356237309, 1.41421356237309)), .Names = c("term", "adj_pval", 
"zscore"), class = "data.frame", row.names = c(1L, 73L, 116L, 
209L, 316L, 351L, 388L, 404L, 451L, 525L, 540L, 552L, 570L, 589L, 
624L, 633L, 639L, 646L, 651L, 658L, 665L, 671L, 677L, 682L, 697L, 
703L, 708L, 712L, 716L, 721L, 725L, 733L, 736L, 751L, 755L, 758L, 
762L, 767L, 771L, 781L, 784L, 787L, 790L, 794L, 797L, 800L, 806L, 
808L, 810L, 814L, 816L, 818L, 820L, 825L, 827L, 830L, 832L, 840L, 
844L, 846L, 859L, 875L, 877L))
Solution

  • As suggested in the comments + using coord_flip (@Axeman):

    ggplot(sub, aes(x = factor(term, levels = stats::reorder(term, adj_pval)), y = adj_pval, fill = zscore)) + 
  geom_bar(stat = "identity", colour = "black") + 
  scale_fill_gradient2("z-score", space = "Lab", low = zsc.col[3], mid = zsc.col[2], high = zsc.col[1], guide = guide_colourbar(title.position = "top", title.hjust = 0.5), breaks = c(min(sub$zscore), max(sub$zscore)), labels = c("decreasing", "increasing")) + 
  labs(title = "title", x = "", y = "-log (adj p-value)") + 
  leg + coord_flip() +
  theme(axis.text.x = element_text(angle = 0, vjust = 1 , hjust = 1), 
        axis.line = element_line(colour = "grey80"), axis.ticks = element_line(colour = "grey80"), 
        axis.title = element_text(size = 8, face = "bold"), axis.text = element_text(size = 8),
        legend.position = "bottom",legend.margin = margin(t=0.5)#,
        #              panel.background = element_blank(), panel.border = element_blank(), 
        #              panel.grid.major = element_blank(), panel.grid.minor = element_blank(), 
        #              plot.background = element_blank()
  )

    revised plot