Using the R system function to run another program and create lefse LDA plots (CC114)

June 10, 2021 • PD Schloss • 1 min read • •

Code

This is where we started before the episode

library(tidyverse)
library(readxl)
library(glue)
library(ggtext)

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=";") %>%
  mutate(pretty_otu = str_replace(string=otu,
                                  pattern="tu0*",
                                  replacement = "TU "),
         genus = str_replace(string=genus,
                             pattern="(.*)",
                             replacement="*\\1*"),
         genus = str_replace(string=genus,
                             pattern="\\*(.*)_unclassified\\*",
                             replacement="Unclassified<br>*\\1*"),
         taxon = glue("{genus}<br>({pretty_otu})")) %>%
  select(otu, taxon)

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

shared_file <- read_tsv("raw_data/schubert.subsample.shared")

Installations