I am trying to align significance asterisks (* or ** or ***) to the points of a geom point graph with position dodge to indicate the significance of a value using ggplot2. I wasn't able to find any similar questions and answers with similar issue.
Here is data frame 'df':
df<-data.frame(conc=c(1,10,100,1, 10,100,1, 10, 100),
mean=c( 0.9008428,0.8278645,0.7890388,0.9541905,
0.8537885,0.8212504,1.3828724,0.7165685, 0.7985398),
Treatment=c("A","A","A","B", "B", "B","C","C", "C"),
upper =c(1.0990144, 0.9505348, 0.8273494, 1.0389074, 0.9227461, 0.9657371, 1.6864420, 0.7401891, 0.9046951),
lower=c(0.7026713, 0.7051941, 0.7507282, 0.9528077, 0.7848309, 0.6767638, 1.0793029, 0.6929479, 0.6923846),
p.value=c(0.0003, 0.6500, 1,0.02,0.0400,
0.3301,0.100,0.023, 0.05))
I made a plot with an automatic asterisk, but it is not aligned how i want to, and i believe it's because of position_dodge, but i have too many points in one concentration, so i have to use it (given data frame is minimal).
legend_title <- "Treatment"
breaks_y =c(0, 0.25, 0.5, 0.75, 1, 1.25, 1.5)
breaks = c(1, 10, 100)
df$Label <- NA
df$Label[df$p.value<0.001]<-'***'
df$Label[df$p.value<0.01 & is.na(df$Label)]<-'**'
df$Label[df$p.value<0.05 & is.na(df$Label)]<-'*'
ggplot(df, aes(x = conc, y = mean, color = Treatment)) +
geom_errorbar(aes(ymax = upper, ymin = lower, width = 0),position = position_dodge(width=0.5)) +
geom_point(aes(shape = Treatment, fill = Treatment), size = 4, position = position_dodge(width=0.5)) +
geom_text(aes(label = Label),size = 4, position = position_dodge(width =0.5), color = "black") +
scale_shape_manual(values = c(22, 21, 23)) +
scale_color_manual(values=c('blue','coral1', 'darkgreen' )) +
scale_fill_manual(values=c('blue','coral1', 'darkgreen')) +
labs(x = "Concentration (\u03BCM)", y = "Abs", title = "Viability", fill = "Treatment") +
scale_x_continuous(trans="log10", limits = c(0.5, 170), breaks = breaks) +
scale_y_continuous(limits = c(0, 1.5), breaks = breaks_y) +
theme_light() +
ggpubr::rotate_x_text(angle = 70) +
theme(axis.text = element_text(size = 12, face = "bold"),
axis.title.y = element_text(size = 12, face ="bold"),
axis.title.x = element_text(size = 12, face ="bold"))
How can I align the asterisk automatically to be directly above the correct dot with position_dodge?
Related
I have dataframe which represents sales by model within 2 different years. 'change' column stands for absolute change by models from 2020 to 2021 while 'chng.percent' measures this change in percentages.
However, I am struggling to apply the given Code of slope plot to my data.
df <- data.frame (model = c("A", "A", "B","B"),
year = c(2020,2021,2020,2021),
sale =c(105,190,110,180),
chang = c(85,NA,70,NA),
chng.percent = c(80.9,NA, 63.6,NA))
Expected outcome (Like this)
Here's a way to do it all within ggplot using your existing data:
ggplot(df, aes(year, sale, color = model)) +
geom_line(arrow = arrow(type = "closed", angle = 20),
key_glyph = draw_key_point) +
geom_vline(aes(xintercept = year)) +
geom_text(aes(label = sale, hjust = ifelse(year == 2020, 1.3, -0.3)),
color = "black",
size = 6) +
geom_text(aes(x = min(df$year) + 0.25, y = 105,
label = paste0("+", chang[1], "; ", chng.percent[1], "%"),
color = "A"), size = 5) +
geom_text(aes(x = max(df$year) - 0.25, y = 150,
label = paste0("+", chang[3], "; ", chng.percent[3], "%"),
color = "B"), size = 5) +
theme_void(base_size = 16) +
coord_cartesian(clip = "off") +
scale_x_continuous(breaks = c(2020, 2021)) +
guides(color = guide_legend(override.aes = list(size = 5))) +
scale_color_brewer(palette = "Set1") +
theme(plot.margin = margin(30, 30, 30, 30),
aspect.ratio = 1.5,
axis.text.x = element_text(size = 20))
you can try something like this :
df <- data.frame(model = c("A", "B"),
sale_2020 =c(105,110),
sale_2021 =c(190,180),
chang = c(85,70),
chng.percent = c(80.9, 63.6))
df %>%
ggplot() +
geom_segment(aes(x = 1, xend = 2,
y = sale_2020,
yend = sale_2021,
group = model,
col = model),
size = 1.2) +
# set the colors
scale_color_manual(values = c("#468189", "#9DBEBB"), guide = "none") +
# remove all axis stuff
theme_classic() +
theme(axis.line = element_blank(),
axis.text = element_blank(),
axis.title = element_blank(),
axis.ticks = element_blank()) +
geom_text(aes(x = x, y = y, label = label),
data = data.frame(x = 1:2,
y = 10 + max(df$sale_2021),
label = c("2020", "2021")),
col = "grey30",
size = 6) +
# add vertical lines that act as axis for 2020
geom_segment(x = 1, xend = 1,
y = min(df$sale_2020) -10,
yend = max(df$sale_2020) + 81,
col = "grey70", size = 1.5) +
# add vertical lines that act as axis for 2021
geom_segment(x = 2, xend = 2,
y = min(df$sale_2021) - 80,
yend = max(df$sale_2021) + 1,
col = "grey70", size = 1.5) +
# add the success rate next to each point on 2021 axis
geom_text(aes(x = 2 + 0.08,
y = sale_2021,
label = paste0(round(sale_2021, 1))),
col = "grey30") +
# add the success rate next to each point on 2021 axis
geom_text(aes(x = 1 - 0.08,
y = sale_2020,
label = paste0(round(sale_2020, 1))),
col = "grey30") +
# add the success rate next to each point on 2020 axis
geom_text(aes(x = 2 - 0.5,
y = c(156, 135),
label = paste0(round(chng.percent, 1), "%")),
col = "grey30")
I am trying to plot the differences in pairs. I found an example on this forum, but to this graph I would like to add the significance level information using the geom_signif function.
Unfortunately, I get the message back:
"Error in f (...):
Can only handle data with groups that are plotted on the x-axis "
Can someone help me fix this problem?
d <- data.frame(y = rnorm(20, 9, 2),
group = as.factor(rep(c('Post-FAP', 'Post-DEP'), each = 10)),
id = rep(1:10, 2))
ggplot(d, aes(y = y)) +
geom_boxplot(aes(x = rep(c(-2.5, 2.5), each = 10), group = group), fill = '#47E3FF') +
geom_point(aes(x = rep(c(-1, 1), each = 10)), shape = 21, size = 1.5, col = "black", fill = "grey") +
geom_line(aes(x = rep(c(-1, 1), each = 10), group = id)) +
#geom_signif(annotation = "p=0.05", y_position = 13, xmin = -2.5, xmax = 2.5, tip_length = .02) +
scale_x_continuous(breaks = c(-2.5, 2.5), labels = c("Post-FAP", "Post-DEP")) +
scale_y_continuous(minor_breaks = seq(5, 14, by =1),
breaks = seq(6, 14, by = 2), limits = c(5, 14),
guide = "axis_minor") +
theme_bw() +
theme(legend.position = "none", panel.grid = element_blank())
I think what you need to do is install ggh4x. It is an addon to ggplot2 that has some helpful tools, like properly adding ticks and minor ticks in your case. Once you load the R package then you should be good to go.
Edit:
The reason that you were getting that error was that you were not specifying group() for ggsignif
library(ggh4x)
library(ggplot2)
library(ggsignif)
ggplot(d, aes(y = y)) +
geom_boxplot(aes(x = rep(c(-2.5, 2.5), each = 10), group = group), fill = '#47E3FF') +
geom_point(aes(x = rep(c(-1, 1), each = 10)), shape = 21, size = 1.5, col = "black", fill = "grey") +
geom_line(aes(x = rep(c(-1, 1), each = 10), group = id)) +
geom_signif(d, mapping = aes(x=id, y=y,group=group),annotation = "p=0.05", y_position = 13, xmin = -2.5, xmax = 2.5, tip_length = .02) +
scale_x_continuous(breaks = c(-2.5, 2.5), labels = c("Post-FAP", "Post-DEP")) +
scale_y_continuous(minor_breaks = seq(5, 14, by =1),
breaks = seq(5, 14, by = 2), limits = c(5, 14),
guide = "axis_minor") +
theme_bw() +
theme(legend.position = "none", panel.grid = element_blank())
There is a thread here on the error message you posted, saying that all the information on aes (x and y) need to be accessible by the subfunction, i.e. geom_signif.
Using ggplot(d, x=aes(as.numeric(group), y=y, group = group)) worked for me.
Interestingly, ggplot(d, x=aes(rep(c(-2.5, 2.5), each = 10), y=y, group = group)) , did not return an error, but also did not show the geom_signif annotation.
I am trying to add labels to a ggplot object. The labels do not look neat and tidy due to their positioning. I have tried using various geom_label_repel and geom_text_repel options but am not having much luck.
I cannot share the data unfortunately, but I have inserted one of my codes below and a screenshot of one section of the redacted graph. The graph has multiple peaks that need labelling. Each label has 2 lines.
I would like the lines connecting the labels to be directly above each peak on the x axis, then turn at a right angle and the line continue horizontally slightly. I would then like the label to sit on top of this horizontal section of the line.
Some peaks are very close together, so the labels will end up being pushed up the y axis so they are able to stack up neatly.
I hope that description makes sense. I would appreciate it if anyone is able to help.
Thank you!
library(ggplot2)
library(ggrepel)
library(dplyr)
upper_plot <- ggplot() +
geom_point(data = plot_data[which(analysis == "Analysis1"),],
aes(x = rel_pos, y = logged_p, color = as.factor(chr)),
size = 0.25) +
scale_color_manual(values = rep(my_upper_colors, nrow(axis_df))) +
geom_point(data=upper_highlight_pos2_old,
aes(x = rel_pos, y = logged_p),
color= c('grey'),
size=0.75,
pch = 16) +
geom_point(data=upper_labels_old,
aes(x = rel_pos, y = logged_p),
color='dark grey',
size=2,
pch = 18) +
geom_point(data=upper_highlight_pos2_novel,
aes(x = rel_pos, y = logged_p),
color= c('black'),
size=0.75,
pch = 16) +
geom_point(data=upper_labels_novel,
aes(x = rel_pos, y = logged_p),
color='black',
size=2,
pch = 18) +
scale_x_continuous(labels = axis_df$chr,
breaks = axis_df$chr_center,
expand = expansion(mult = 0.01)) +
scale_y_continuous(limits = c(0, maxp),
expand = expansion(mult = c(0.02, 0.06))) +
# geom_hline(yintercept = -log10(1e-5), color = "red", linetype = "dashed",
# size = 0.3) +
geom_hline(yintercept = -log10(5e-8), color = "black", linetype = "dashed",
size = 0.3) +
labs(x = "", y = bquote(atop('GWAS', '-log'[10]*'(p)'))) +
theme_classic() +
theme(legend.position = "none",
axis.title.x = element_blank(),
plot.margin = margin(t=5, b = 5, r=5, l = 10)) +
geom_label_repel(data = upper_labels,
aes(x = rel_pos, y = logged_p, label = label),
ylim = c(maxp / 3, NA),
size = 2,
force_pull = 0,
nudge_x = 0.5,
box.padding = 0.5,
nudge_y = 0.5,
min.segment.length = 0, # draw all lines no matter how short
segment.size = 0.2,
segment.curvature = -0.1,
segment.ncp = 3,
segment.angle = 45,
label.size=NA, #no border/box
fill = NA, #no background
)
This is my current untidy layout...
EDIT:
This is the sort of layout I am after. The lines will need to be flexible and either be right-handed or left-handed depending on space (source: https://www.nature.com/articles/s41588-020-00725-7)
Here is the data set:
d <- tribble(
~priceseg, ~price_n, ~zet_n, ~zet_n2,
"(0,1]", 16, 2, 24,
"(1,3]", 33, 3, 38,
"(3,5]", 33, 2, 25,
"(5,6]", 17, 1, 13,
)
And here is the visualisation thanks to #d.b
ggplot(d) +
geom_col(aes(x = priceseg, y = price_n), fill = ("#F1948A"), colour="black", size = 0.6) +
geom_line(data = d, mapping = aes(x = priceseg, y = zet_n2, group = 1), colour = "#154360", size = 1) +
geom_label(data = d, mapping = aes(x = priceseg, y = price_n, label = price_n), nudge_y = -0.6)
Now, I want to add the legend for bar plot and line in the visualisation something like this: Combined line & bar geoms: How to generate proper legend?
Also, I would like to add % in geom_label.
But somehow, I could not manage to implement it. Any help?
Here is an option
# Calculate percentage and add as column to `d`
d <- transform(d, perc = sprintf("%2.1f%%", price_n / sum(price_n) * 100))
# Plot
ggplot(d, aes(x = priceseg)) +
geom_col(aes(y = price_n, fill = "bar_data"), colour = "black", size = 0.6) +
geom_line(aes(y = zet_n2, group = 1, colour = "line_data"), size = 1) +
scale_fill_manual("", values = "#F1948A") +
scale_colour_manual("", values = "#154360") +
geom_label(aes(y = price_n, label = perc), nudge_y = -0.6) +
theme(
legend.key = element_blank(),
legend.title = element_blank(),
legend.box = "horizontal")
You can adjust the fill and colour "labels" by changing the strings "bar_data" and "line_data".
I'm struggling to find a straightforward solution to fix my plot. The problem stems down to the discrete nature of the x-axis. I want to annotate the plot with text and segments in order to show statistical results.
1) I want to print the p-value between "Baby" and "Queen" as well as between "Queen" and "Worker", but ggplot only allows to annotate above each label, not between them.
2) Similarly, I want the first two geom_segments to be separated, but ggplot won't let me end the first one at something like "Queen"-0.1 and start the second one at "Queen"+0.1 as it is mixing factors and numbers.
Fully reproducible example below, with issues on line 12, 13 and 18:
data <- data.frame(Group.1 = rep(c("A","B"),3),Group.2 = c("Baby","Baby","Worker","Worker","Queen","Queen"),
value = c(0.18,0.30,0.09,0.25,-0.26,-0.55))
boxplot_candidates <- ggplot(aes(y=value,x=Group.2,fill=Group.2),data= data) + theme_bw() +
scale_fill_manual(values=c("lightgreen","darkgreen","goldenrod1"),name="") +
theme(plot.title = element_text(face="bold", size=18, hjust=0)) +
labs(x="",y="Transcript expression\n(log2-centered TMM-nornalised TPMs)") +
theme(plot.title=element_text(size=18, vjust=2),legend.position="", legend.text=element_text(size=14),
axis.text.x = element_text(size = 14, colour = "black"),
axis.text.y = element_text(size = 14, colour = "black"),
axis.title.y=element_text(size = 14, colour = "black",vjust=1),
axis.title.x=element_text(size = 14, colour = "black")) +
geom_segment(aes(x="Baby",xend="Queen",y=0.7,yend=0.7)) + ##### MAKE XEND SMALLER
geom_segment(aes(x="Queen",xend="Worker",y=0.7,yend=0.7)) + ##### MAKE XEND LARGER
geom_segment(aes(x="Baby",xend="Worker",y=1.2,yend=1.2)) +
ylim(-1.5,1.5) + stat_boxplot(geom ='errorbar') +
geom_boxplot(notch=F,outlier.shape=NA) +
geom_point(size=2,position = position_jitter(width = 0.2)) + stat_summary(fun.y=mean, colour = "white",geom="point", size=4) +
annotate("text", x = as.factor(unique(data$Group.2)),y=c(0.8,0.8,1.3),
label = c("p < 0.001","p < 0.001","p = 0.89"),family="",fontface = 3,size=4) ##### PRINT "p < 0.001" BETWEEN LABELS
print(boxplot_candidates)
Categorical variables are simply placed at locations 1, 2, 3, etc. If you want to reach locations between two categorical variables, you can use coordinates such as 1.2 or 1.5 etc.
Here is a reproducible example with all the irrelevant theme code stripped out:
data <- data.frame(Group.1 = rep(c("A", "B"), 3),
Group.2 = c("Baby", "Baby", "Worker", "Worker", "Queen", "Queen"),
value = c(0.18, 0.30, 0.09, 0.25, -0.26, -0.55))
ggplot(data, aes(y = value, x = Group.2, fill = Group.2)) +
stat_boxplot(geom = 'errorbar') +
geom_boxplot(notch = F, outlier.shape = NA) +
geom_segment(aes(x=1.1, xend=1.9, y=0.7, yend=0.7)) +
geom_segment(aes(x=2.1, xend=2.9, y=0.7, yend=0.7)) +
geom_segment(aes(x=1.1, xend=2.9, y=1.2, yend=1.2)) +
geom_point(size = 2, position = position_jitter(width = 0.2)) +
stat_summary(fun.y = mean, colour = "white", geom = "point", size = 4) +
annotate("text",
x = c(1.5, 2.5, 2),
y = c(0.8, 0.8, 1.3),
label = c("p < 0.001", "p < 0.001", "p = 0.89"),
family = "", fontface = 3, size=4) +
scale_fill_manual(values=c("lightgreen", "darkgreen", "goldenrod1"),
guide = "none") +
ylim(-1.5, 1.5) +
labs(x="", y="Transcript expression\n(log2-centered TMM-nornalised TPMs)") +
theme_bw()