mag_cts_per_trait.Rmd

---
title: "Counts of MAGs per trait"
author: "Seojin Jung"
date: "`r Sys.Date()`"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

```{r load_libs, warning=FALSE, message=FALSE}
packages <- c("R.utils", "RColorBrewer", "ape", "assertthat", "checkmate",
              "coRdon", "corrplot", "dendextend", "devtools", "doParallel",
              "dplyr", "DT", "factoextra", "formatR", "futile.logger", "ggplot2", 
              "grid", "gtools", "kmed", "lazyeval", "magrittr", "parallel", 
              "pheatmap", "readr", "stringr", "tibble", "tictoc", "tidyr", "vegan")
for (pkg in packages) {
  library(pkg, character.only=TRUE)
}

# bioconductor packages
library(BiocManager)
library(Biostrings)
library(ComplexHeatmap)
library(coRdon)

# everything else
library(gRodon)
library(pairwiseAdonis)
library(EcolUtils)
library(ggtree)
library(microtrait)
```

```{r load_data}
load("data/traits.RData")
```

For each trait, the number of MAGs in which that trait was detected is listed in a data frame. Trait levels (except for GH genes) are separated out into distinct columns for ease of comprehension. 

```{r counts_all}
# all traits
bw_all_counts <- sapply(bw_all_traits, function(column) sum(column > 0)) %>% as.data.frame()
bw_all_counts <- bw_all_counts[-1, , drop = FALSE]
colnames(bw_all_counts)[1] <- "Number of MAGs"
bw_all_counts <- bw_all_counts %>% rownames_to_column(var = "Trait name")
bw_all_counts <- bw_all_counts %>%
  separate('Trait name', 
           into = c("Trait level 1", "Trait level 2", "Trait level 3", "Trait level 4",
                    "Trait level 5", "Trait level 6", "Trait level 7"), 
           sep = ":", extra = "merge")

datatable(bw_all_counts)
```

```{r counts_transport}
# transport
bw_transport_counts <- sapply(bw_transport, function(column) sum(column > 0)) %>% as.data.frame()
bw_transport_counts <- bw_transport_counts[-1, , drop = FALSE]
colnames(bw_transport_counts)[1] <- "Number of MAGs"
bw_transport_counts <- bw_transport_counts %>% rownames_to_column(var = "Trait name")
bw_transport_counts <- bw_transport_counts %>%
  separate('Trait name', 
           into = c("Trait level 1", "Trait level 2", "Trait level 3", "Trait level 4",
                    "Trait level 5"), 
           sep = ":", extra = "merge")

datatable(bw_transport_counts)
```

```{r counts_gh}
# GH
bw_gh_counts <- sapply(bw_gh, function(column) sum(column > 0)) %>% as.data.frame()
bw_gh_counts <- bw_gh_counts[-1, , drop = FALSE]
colnames(bw_gh_counts)[1] <- "Number of MAGs"
bw_gh_counts <- bw_gh_counts %>% rownames_to_column(var = "GH family")

datatable(bw_gh_counts)
```