Creating a stacked barchart in R with ggplot2 with microbiome data (CC102)

May 10, 2021 • PD Schloss • 2 min read

Code

This is where we started before the episode

library(tidyverse)
library(readxl)

metadata <- read_excel("raw_data/schubert.metadata.xlsx", na="NA") %>%
  select(sample_id, disease_stat) %>%
  drop_na(disease_stat)

otu_counts <- read_tsv("raw_data/schubert.subsample.shared") %>%
  select(Group, starts_with("Otu")) %>%
  rename(sample_id = Group) %>%
  pivot_longer(-sample_id, names_to="otu", values_to = "count")

taxonomy <- read_tsv("raw_data/schubert.cons.taxonomy") %>%
  select("OTU", "Taxonomy") %>%
  rename_all(tolower) %>%
  mutate(taxonomy = str_replace_all(taxonomy, "\\(\\d+\\)", ""),
         taxonomy = str_replace(taxonomy, ";$", "")) %>%
  separate(taxonomy,
           into=c("kingdom", "phylum", "class", "order", "family", "genus"),
           sep=";")

otu_rel_abund <- inner_join(metadata, otu_counts, by="sample_id") %>%
  inner_join(., taxonomy, by="otu") %>%
  group_by(sample_id) %>%
  mutate(rel_abund = count / sum(count)) %>%
  ungroup() %>%
  select(-count) %>%
  pivot_longer(c("kingdom", "phylum", "class", "order", "family", "genus", "otu"),
               names_to="level",
               values_to="taxon")

Installations

comments powered by Disqus