---
title: "14-BWA"
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
editor_options: 
  markdown: 
    wrap: sentence
---

```{r setup, include=FALSE}
library(knitr)
library(tidyverse)
library(kableExtra)
library(DT)
library(Biostrings)
library(tm)
library(pheatmap)
library(DESeq2)
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
  comment = ""         # Prevents appending '##' to beginning of lines in code output
)
```


# Genome

```{bash}
cd ../data

curl -O https://owl.fish.washington.edu/halfshell/genomic-databank/GCF_031168955.1_ASM3116895v1_genomic.fna
```


```{bash}
bwa index ../data/GCF_031168955.1_ASM3116895v1_genomic.fna
```
# Reads - getting on raven

ecotype

```{bash}
mkdir -p ../data/fastq-ecotype
cd ../data/fastq-ecotype
wget -r -np -nd -A "*.gz" https://owl.fish.washington.edu/nightingales/G_macrocephalus/30-1149634506/00_fastq/
```


# ALign



```{bash}
# Path to reference genome (must be indexed with bwa index)
REFERENCE="../data/GCF_031168955.1_ASM3116895v1_genomic.fna"

# Number of threads per BWA job
THREADS=42


# Directory containing fastq files
FASTQ_DIR="../data/fastq-ecotype"

# Output directory (you can change this)
OUT_DIR="../output/14-BWA"

# File suffixes
R1_SUFFIX="_R1_001.fastq.gz"
R2_SUFFIX="_R2_001.fastq.gz"
OUT_SUFFIX=".sam"

# -------------------------------
# RUN BWA IN PARALLEL
# -------------------------------
# Run loop
for sample in $(ls "${FASTQ_DIR}"/*"${R1_SUFFIX}" | xargs -n 1 basename | sed "s/${R1_SUFFIX}//" | sort -u); do
  R1_FILE="${FASTQ_DIR}/${sample}${R1_SUFFIX}"
  R2_FILE="${FASTQ_DIR}/${sample}${R2_SUFFIX}"
  OUT_FILE="${OUT_DIR}/${sample}${OUT_SUFFIX}"

  echo "Running BWA on ${sample}..."
  bwa mem -t "${THREADS}" "${REFERENCE}" "${R1_FILE}" "${R2_FILE}" > "${OUT_FILE}"
done
```