I am working with the Growthrates package to generate parameter estimates of growth rate curves for my data. I have made the regressions and looked at the produced plots and I am happy with the data, but I would like to reproduce the following plots in ggplot2.
Figure 1: Multiplot of a regression for each group:treatment combo
I would like a multiplot of the regression lines for each group:Treatment combination, but with all the regressions I performed on it in ((i.e. logistic, gompertz, gompertz2, etc..). So far I have:
library(growthrates)
####Using logistic regression to fit the data across mutliple groups
p <- c(y0 = 1, mumax = 0.5, K = 200)
lower <- c(y0 = 0, mumax = 0, K = 20)
upper <- c(y0 = 100, mumax = 5, K = 400)
many_logistics <- all_growthmodels(y_data ~
grow_logistic(total_time_days, parms) | sample + treatment,
data = Alldata,
p = p,
lower = lower,
upper = upper,
log = "y")
pp <- coef(many_logistics)
par(mfrow = c(5, 3))
par(mar = c(2.5, 4, 2, 1))
plot(many_logistics)
many_logistics_results <- results(many_logistics)
xyplot(mumax ~ treatment | sample, data = many_logistics_results, layout = c(3, 1))
xyplot(r2 ~ treatment | sample, data = many_logistics_results, layout = c(3, 1))
xyplot(K ~ treatment | sample, data = many_logistics_results, layout = c(3, 1))
curve_logistics <- predict(many_logistics) #Prediction for given data (data for curve)
est_logistics <- predict(many_logistics, newdata=data.frame(time=seq(0, 1, 0.1))) #Extrapolation/Interpolation from curve
####Using Gompertz regression to fit the data across mutliple groups
p <- c(y0 = 1, mumax = 0.5, K = 200)
lower <- c(y0 = 0, mumax = 0, K = 20)
upper <- c(y0 = 100, mumax = 5, K = 400)
many_gompertz <- all_growthmodels(y_datay_data ~
grow_gompertz(total_time_days, parms) | sample + treatment,
data = Alldata,
p = p,
lower = lower,
upper = upper)
pp <- coef(many_gompertz)
par(mfrow = c(5, 3))
par(mar = c(2.5, 4, 2, 1))
plot(many_gompertz)
many_gompertz_results <- results(many_gompertz)
xyplot(mumax ~ treatment | sample, data = many_gompertz_results, layout = c(3, 1))
xyplot(r2 ~ treatment | sample, data = many_gompertz_results, layout = c(3, 1))
xyplot(K ~ treatment | sample, data = many_gompertz_results, layout = c(3, 1))
curve_gompertz <- predict(many_gompertz) #Prediction for given data (data for curve)
est_gompertz <- predict(many_gompertz, newdata=data.frame(time=seq(0, 1, 0.1))) #Extrapolation/Interpolation from curve
#Prepare the data frames
curve_logistics2 <- curve_logistics %>%
map_df(as_tibble, .id = "src") %>%
separate(src, c("sample", "treatment"), ":") %>%
mutate(regression = "logistic")
curve_gompertz2 <- curve_gompertz %>%
map_df(as_tibble, .id = "src") %>%
separate(src, c("sample", "treatment"), ":") %>%
mutate(regression = "gompertz")
alldata2<- Alldata %>%
select("sample", "treatment","total_time_days", "y_data") %>%
rename(time = "total_time_days") %>%
rename(y = "y_data") %>%
mutate(regression = "none")
comp_reg <- bind_rows(curve_logistics2, curve_gompertz2, alldata2)
#define the function to automatically generate plots#define the function to automatically generate plots
REGRESSION_LINE_PLOT <-function(x) {ggplot(data = x, aes(x=time, y=y, colour = regression, linetype = regression)) +
geom_point(size = 2.5, data = subset(x, regression %in% c("none"))) +
stat_smooth(data = subset(x, regression %in% c("gompertz", "logistic"))) +
theme_bw() +
theme(panel.grid.major=element_blank(),
panel.grid.minor=element_blank(),
panel.spacing = unit(0,"cm"),
axis.line=element_line(colour="black"),
# axis.title.x = element_text(size=14, colour = "black"),
axis.title.x = element_blank(),
# axis.title.y = element_text(size=14, colour = "black"),
axis.title.y = element_blank(),
# axis.text.y = element_text(size=14, colour = "black"),
# axis.text.x = element_text(size=14, colour = "black"),
strip.background = element_blank(),
strip.text = element_text(size = 12, colour="black", face = "bold"),
legend.text= element_text(size = 12, colour = "black"),
legend.title=element_blank(),
text = element_text(size=12, family="Arial")) +
# plot.margin=unit(c(0.1,0.1,0.1,0.1),"cm")) +
#scale_colour_manual(values = cbbPalette) + ### here I tell R to use my custom colour palette
#scale_x_continuous(limits = c(-1,14)) + # set time range from -1 to 70 since we started sampling on day -1
#scale_y_continuous(limits = c(-1,350), breaks = seq(0, 360, 90)) + # For comparison purposes, i want all my panels to have the same y axis scale
ylab("") +
xlab("")
}
comp_reg_nested<- comp_reg %>%
group_by(sample, treatment) %>%
nest() %>%
mutate(plots=map(.x=data, ~REGRESSION_LINE_PLOT(.x)))
fo_ad_line <- comp_reg_nested[[1,"plots"]]
However, I do not think the regression lines are properly represented in ggplot22. Is there a better way to do this?
I created a data example more or less similar to your data structure from the builtin data of the package and simplified the code a little bit, omitting the default plot functions. I very much enjoyed your data frame construction method with map_df, thank you. Then I added a simple ggplot, that can of course be extended and adapted to your needs.
library(growthrates)
library(dplyr)
library(purrr)
library(tidyr)
library(ggplot2)
## use subset of built-in example data of the package
## and adapt it to the existing part of the script
data(bactgrowth)
Alldata <- bactgrowth[(bactgrowth$conc < 1) & bactgrowth$replicate == 1, ]
names(Alldata) <- c("sample", "replicate", "treatment", "total_time_days", "y_data")
Alldata$y_data <- Alldata$y_data * 1000
Alldata$treatment <- as.character(Alldata$treatment)
####Using logistic regression to fit the data across mutliple groups
p <- c(y0 = 1, mumax = 0.5, K = 200)
lower <- c(y0 = 0, mumax = 0, K = 20)
upper <- c(y0 = 100, mumax = 5, K = 400)
many_logistics <- all_growthmodels(y_data ~
grow_logistic(total_time_days, parms) | sample + treatment,
data = Alldata,
p = p,
lower = lower,
upper = upper)
many_logistics_results <- results(many_logistics)
curve_logistics <- predict(many_logistics)
####Using Gompertz regression to fit the data across mutliple groups
many_gompertz <- all_growthmodels(y_data ~
grow_gompertz(total_time_days, parms) | sample + treatment,
data = Alldata,
p = p,
lower = lower,
upper = upper)
many_gompertz_results <- results(many_gompertz)
curve_gompertz <- predict(many_gompertz)
#Prepare the data frames
curve_logistics2 <- curve_logistics %>%
map_df(as_tibble, .id = "src") %>%
separate(src, c("sample", "treatment"), ":") %>%
mutate(regression = "logistic")
curve_gompertz2 <- curve_gompertz %>%
map_df(as_tibble, .id = "src") %>%
separate(src, c("sample", "treatment"), ":") %>%
mutate(regression = "gompertz")
alldata2<- Alldata %>%
rename(time = "total_time_days", y = "y_data")
## combine the two curves to a joint data frame
comp_reg <- bind_rows(curve_logistics2, curve_gompertz2)
## plot it
ggplot(comp_reg, aes(time, y)) +
geom_point(data = alldata2) +
geom_line(aes(color = regression)) +
facet_grid(treatment ~ sample)