---
title: "Non-target taxa"
author: Steven Roberts
date: "`r format(Sys.time(), '%d %B, %Y')`" 
output: 
  # github_document:
  #   toc: true
  #   toc_depth: 3
  #   number_sections: true
  #   html_preview: true
  html_document:
    theme: readable
    highlight: zenburn
    toc: true
    toc_float: true
    number_sections: true
    code_folding: show
    code_download: true
---

```{r setup, include=FALSE}
library(knitr)
library(tidyverse)
library(kableExtra)
library(DESeq2)
library(pheatmap)
library(RColorBrewer)
library(data.table)
library(DT)
library(formattable)
library(Biostrings)
library(spaa)
knitr::opts_chunk$set(
  echo = TRUE,         # Display code chunks
  eval = FALSE,         # Evaluate code chunks
  warning = FALSE,     # Hide warnings
  message = FALSE,     # Hide messages
  fig.width = 6,       # Set plot width in inches
  fig.height = 4,      # Set plot height in inches
  fig.align = "center" # Align plots to the center
)
```


```{r, eval=TRUE}

# specify the path to your files
path <- "../results/MEGAN"

# get all files in the directory
files <- list.files(path, pattern = "*.tab", full.names = TRUE) 


```


# Fraction of reads Arthropoda


```{r, eval=TRUE}
df <- files %>%
  map_df(~{
    read_tsv(.x, col_names = FALSE) %>%
    set_names(c("phylum", "count")) %>%
    mutate(sample = str_remove(basename(.x), ".MEGAN.taxonName_to_count_summarized-phylum.tab"))  # remove the extension from the filename
  })


```
```{r, eval=TRUE}
datatable(df)

```

```{r, eval=TRUE}
datatable(
  df %>%
 pivot_wider(names_from = phylum, values_from = count, values_fill = 0) %>%
 mutate(total = rowSums(select(., 2:35), na.rm = TRUE)) %>%
 mutate(fraction = Arthropoda/total) %>%
 select("sample", "fraction", "Arthropoda", "Chordata", "Microsporidia", "Proteobacteria", "Bacteroidetes")
)
```
```{r, eval=TRUE}
df %>%
 pivot_wider(names_from = phylum, values_from = count, values_fill = 0) %>%
 mutate(total = rowSums(select(., 2:35), na.rm = TRUE)) %>%
 mutate(fraction = Arthropoda/total) %>%
 select("sample", "fraction", "Arthropoda", "Chordata", "Microsporidia", "Proteobacteria", "Bacteroidetes") %>%
  ggplot(aes(x=fraction)) +
  geom_histogram(bins = 50, fill="blue", color="black") +
  labs(x="Percent", y="Frequency", title="Histogram of Arthr0poda Fraction of reads") +
  theme_minimal()
```




```{r, eval=TRUE}
df %>%
  filter(phylum == c("Arthropoda", "Chordata", "Microsporidia", "Proteobacteria", "Bacteroidetes")) %>%
  group_by(phylum, sample) %>%
  summarise(total = mean(count, na.rm = TRUE)) %>%
  ggplot(aes(x = phylum, y = total)) +
  geom_col(position = "dodge") +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
  labs(x = "Category", y = "Total Count")

```

```{r, eval=TRUE}
df_wider <- df %>%
 pivot_wider(names_from = phylum, values_from = count, values_fill = 0) %>%
 select("sample", "Arthropoda", "Chordata", "Microsporidia", "Proteobacteria", "Bacteroidetes")

```

```{r, eval=TRUE}
datatable(df_wider)
```