---
title: "Long non-coding RNA discovery pipeline"
author: "Steven Roberts"
date: "`r format(Sys.time(), '%d %B, %Y')`"  
format:
  html:
    toc: true
    toc-depth: 2
    html-math-method: katex
    css: styles.css
    theme: sandstone
editor: 
  markdown: 
    wrap: 72
---

Steven's attempt


```{r setup, include=FALSE}
library(knitr)
library(tidyverse)
library(kableExtra)
library(DT)
library(Biostrings)
library(tm)
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
)
```



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

# Define key paths and tool directories
 
DATA_DIR <- "../data/01-lncRNA"
OUTPUT_DIR <- "../output/01-lncRNA"
THREADS <- "32"
  
FASTQ_SOURCE <- "https://gannet.fish.washington.edu/Atumefaciens/20230519-E5_coral-fastqc-fastp-multiqc-RNAseq/P_meandrina/trimmed/"
FASTQ_SUFFIX <- "fastq.gz"
GENOME_SOURCE <- "https://owl.fish.washington.edu/halfshell/genomic-databank/Pocillopora_meandrina_HIv1.assembly.fasta"

GTF_SOURCE <- "https://github.com/urol-e5/timeseries_molecular/raw/e4361d794b8a6887bc80a979491cb931e93f3e2a/F-Ptua/data/Pocillopora_meandrina_HIv1.genes-validated.gtf"
GFF_SOURCE <- "https://github.com/urol-e5/timeseries_molecular/raw/e4361d794b8a6887bc80a979491cb931e93f3e2a/F-Ptua/data/Pocillopora_meandrina_HIv1.genes-validated.gff3"

HISAT2_DIR <- "/home/shared/hisat2-2.2.1"
SAMTOOLS_DIR <- "/home/shared/samtools-1.12"
STRINGTIE_DIR <- "/home/shared/stringtie-2.2.1.Linux_x86_64"
GFFCOMPARE_DIR <- "/home/shared/gffcompare-0.12.6.Linux_x86_64"
BEDTOOLS_DIR <- "/home/shared/bedtools2/bin"
CPC2_DIR <- "/home/shared/CPC2_standalone-1.0.1"
CONDA_PATH <- "/opt/anaconda/anaconda3/bin/conda"

GENOME_FASTA <- file.path(DATA_DIR, "genome.fasta")
GENOME_GTF <- file.path(DATA_DIR, "genome.gtf")
GENOME_GFF <- file.path(DATA_DIR, "genome.gff")
FASTQ_DIR <- file.path(DATA_DIR, "fastq")
GENOME_INDEX <- file.path(OUTPUT_DIR, "genome.index")

# Export these as environment variables for bash chunks.
Sys.setenv(
  THREADS = THREADS,
  DATA_DIR = DATA_DIR,
  FASTQ_SOURCE = FASTQ_SOURCE,
  FASTQ_SUFFIX = FASTQ_SUFFIX,
  OUTPUT_DIR = OUTPUT_DIR,
  GENOME_SOURCE = GENOME_SOURCE,
  GTF_SOURCE = GTF_SOURCE,
  GFF_SOURCE = GFF_SOURCE,
  HISAT2_DIR = HISAT2_DIR,
  SAMTOOLS_DIR = SAMTOOLS_DIR,
  STRINGTIE_DIR = STRINGTIE_DIR,
  GFFCOMPARE_DIR = GFFCOMPARE_DIR,
  BEDTOOLS_DIR = BEDTOOLS_DIR,
  CPC2_DIR = CPC2_DIR,
  CONDA_PATH = CONDA_PATH,
  GENOME_FASTA = GENOME_FASTA,
  GENOME_GTF = GENOME_GTF,
  GENOME_GFF = GENOME_GFF,
  FASTQ_DIR = FASTQ_DIR,
  GENOME_INDEX = GENOME_INDEX
)
```




# Download Genome and Reads for Hisat

```{r, engine='bash'}

wget -nv -r \
--no-directories --no-parent \
-P ${FASTQ_DIR} \
-A "*${FASTQ_SUFFIX}" ${FASTQ_SOURCE}
```

```{r, engine='bash'}
ls ${FASTQ_DIR}
```


```{r, engine='bash'}

curl -o "${GENOME_FASTA}" "${GENOME_SOURCE}"
```

```{r, engine='bash'}


curl -o "${GENOME_GTF}" "${GTF_SOURCE}"
```


```{r, engine='bash'}


curl -o "${GENOME_GFF}" "${GFF_SOURCE}"
```

```{bash}
head "${GENOME_FASTA}"
head "${GENOME_GFF}"
head "${GENOME_GTF}"
```


# HISAT

```{r, engine='bash'}
python
"${HISAT2_DIR}/hisat2_extract_exons.py" "${GENOME_GTF}" > "${OUTPUT_DIR}/exon.txt"

"${HISAT2_DIR}/hisat2_extract_splice_sites.py" "${GENOME_GTF}" > "${OUTPUT_DIR}/splice_sites.txt"

```





```{r, engine='bash'}

"${HISAT2_DIR}/hisat2-build" \
  -p "${THREADS}" \
  "${GENOME_FASTA}" \
  "${GENOME_INDEX}" \
  2> "${OUTPUT_DIR}/hisat2-build_stats.txt"

```