barplot_line_ggplot2.R

library(tidyverse)

## -- Attaching packages ----------------------------------------------------------------- tidyverse 1.3.0 --

## √ ggplot2 3.3.2     √ purrr   0.3.4
## √ tibble  3.0.3     √ dplyr   1.0.1
## √ tidyr   1.1.2     √ stringr 1.4.0
## √ readr   1.4.0     √ forcats 0.5.0

## Warning: package 'readr' was built under R version 4.0.3

## -- Conflicts -------------------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

df <- data.frame(
  Phylum=c("Ruminococcaceae","Bacteroidaceae","Eubacteriaceae","Lachnospiraceae","Porphyromonadaceae"),
  GroupA=c(37.7397,31.34317,222.08827,5.08956,3.7393),
  GroupB=c(113.2191,94.02951,66.26481,15.26868,11.2179),
  GroupC=c(123.2191,94.02951,46.26481,35.26868,1.2179),
  GroupD=c(37.7397,31.34317,222.08827,5.08956,3.7393)
)

df.long <- df %>% gather(group, abundance, -Phylum)

## 
link_dat <- df %>%
  arrange(by=desc(Phylum)) %>%
  mutate_if(is.numeric, cumsum)
bar.width <- 0.7
link_dat <- link_dat[, c(1,2,rep(3:(ncol(link_dat)-1),each=2), ncol(link_dat))]
link_dat <- data.frame(y=t(matrix(t(link_dat[,-1]), nrow=2)))
link_dat$x.1 <- 1:(ncol(df)-2)+bar.width/2
link_dat$x.2 <- 1:(ncol(df)-2)+(1-bar.width/2)
df.long

##                Phylum  group abundance
## 1     Ruminococcaceae GroupA  37.73970
## 2      Bacteroidaceae GroupA  31.34317
## 3      Eubacteriaceae GroupA 222.08827
## 4     Lachnospiraceae GroupA   5.08956
## 5  Porphyromonadaceae GroupA   3.73930
## 6     Ruminococcaceae GroupB 113.21910
## 7      Bacteroidaceae GroupB  94.02951
## 8      Eubacteriaceae GroupB  66.26481
## 9     Lachnospiraceae GroupB  15.26868
## 10 Porphyromonadaceae GroupB  11.21790
## 11    Ruminococcaceae GroupC 123.21910
## 12     Bacteroidaceae GroupC  94.02951
## 13     Eubacteriaceae GroupC  46.26481
## 14    Lachnospiraceae GroupC  35.26868
## 15 Porphyromonadaceae GroupC   1.21790
## 16    Ruminococcaceae GroupD  37.73970
## 17     Bacteroidaceae GroupD  31.34317
## 18     Eubacteriaceae GroupD 222.08827
## 19    Lachnospiraceae GroupD   5.08956
## 20 Porphyromonadaceae GroupD   3.73930

link_dat

##          y.1       y.2  x.1  x.2
## 1   37.73970 113.21910 1.35 1.65
## 2  113.21910 123.21910 2.35 2.65
## 3  123.21910  37.73970 3.35 3.65
## 4   41.47900 124.43700 1.35 1.65
## 5  124.43700 124.43700 2.35 2.65
## 6  124.43700  41.47900 3.35 3.65
## 7   46.56856 139.70568 1.35 1.65
## 8  139.70568 159.70568 2.35 2.65
## 9  159.70568  46.56856 3.35 3.65
## 10 268.65683 205.97049 1.35 1.65
## 11 205.97049 205.97049 2.35 2.65
## 12 205.97049 268.65683 3.35 3.65
## 13 300.00000 300.00000 1.35 1.65
## 14 300.00000 300.00000 2.35 2.65
## 15 300.00000 300.00000 3.35 3.65

ggplot(df.long, aes(x=group, y=abundance, fill=Phylum)) +
  geom_bar(stat = "identity", width=bar.width, col='black')  +
  geom_segment(data=link_dat,
               aes(x=x.1, xend=x.2, y=y.1, yend=y.2), inherit.aes = F)

#######ref https://mp.weixin.qq.com/s/eaVdaj3ubDdhKsKyfzK1Sg