---
title: "HiSat_GL"
output: html_document
date: "2024-06-03"
---


```{r setup, include=FALSE}
library(knitr)
library(tidyverse)
library(kableExtra)
library(DT)
library(Biostrings)
library(tm)
library(pheatmap)
library(DESeq2)
```

# Differentially Expressed Genes
 
# Reads

```{r, engine='bash', eval=TRUE}
ls /home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/data/raw-trimmed/
```


# Genome


```{bash}
cd /home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/data

/home/shared/datasets download genome accession GCF_036588685.1 --include gff3,gtf,rna,cds,protein,genome,seq-report
```

```{bash}
cd /home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/data
unzip ncbi_dataset.zip
```

```{r, engine='bash', eval=TRUE}
ls ../data/ncbi_dataset/data/GCF_036588685.1

```


# Hisat

```{bash}
/home/shared/hisat2-2.2.1/hisat2_extract_exons.py \
/home/shared/analyses/12-fix-gff/mod_augustus.gtf \
> /home/shared/analyses/13-hisat-deseq2/m_exon.tab
```

```{r, engine='bash'}
/home/shared/hisat2-2.2.1/hisat2_extract_splice_sites.py \
../analyses/12-fix-gff/mod_augustus.gtf \
> ../analyses/13-hisat-deseq2/m_spice_sites.tab
```

```{r, engine='bash'}
echo "13-hisat-deseq2/GCF*" >> ../analyses/.gitignore
echo "13-hisat-deseq2/GCF**fastq" >> ../analyses/.gitignore
```

```{r, engine='bash'}
/home/shared/hisat2-2.2.1/hisat2-build \
../data/ncbi_dataset/data/GCA_032158295.1/GCA_032158295.1_ASM3215829v1_genomic.fna \
../analyses/13-hisat-deseq2/GCA_032158295.index \
--exon ../analyses/13-hisat-deseq2/m_exon.tab \
--ss ../analyses/13-hisat-deseq2/m_spice_sites.tab \
-p 20 \
../analyses/12-fix-gff/mod_augustus.gtf \
2> ../analyses/13-hisat-deseq2/hisat2-build_stats.txt
```

```{r, engine='bash'}
echo "13-hisat-deseq2/*sam" >> ../analyses/.gitignore
```



```{r, engine='bash', eval=TRUE}
find /home/shared/8TB_HDD_02/graceac9/data/pycno2021/*_R1_001.fastq.gz.fastp-trim.20220810.fq.gz | xargs basename -s _R1_001.fastq.gz.fastp-trim.20220810.fq.gz | xargs -I{} echo {}
```





keeping unmapped reads 
```{r, engine='bash'}
find /home/shared/8TB_HDD_02/graceac9/data/pycno2021/*_R1_001.fastq.gz.fastp-trim.20220810.fq.gz \
| xargs -I{} basename -s _R1_001.fastq.gz.fastp-trim.20220810.fq.gz {} \
| xargs -I{} sh -c '/home/shared/hisat2-2.2.1/hisat2 \
-x ../analyses/13-hisat-deseq2/GCA_032158295.index \
--dta \
-p 32 \
-1 /home/shared/8TB_HDD_02/graceac9/data/pycno2021/{}_R1_001.fastq.gz.fastp-trim.20220810.fq.gz \
-2 /home/shared/8TB_HDD_02/graceac9/data/pycno2021/{}_R2_001.fastq.gz.fastp-trim.20220810.fq.gz \
-S ../analyses/13-hisat-deseq2/{}_03.sam \
--un-conc ../analyses/13-hisat-deseq2/{}_unmapped_reads.fastq \
> ../analyses/13-hisat-deseq2/{}_hisat03.stdout 2> ../analyses/13-hisat-deseq2/{}_hisat03.stderr'
```







Explanation
xargs -I{}: This option allows you to replace {} in the command with the output from the previous command (i.e., basename). It's used twice: first, to strip the suffix from the filenames, and second, to construct and execute the hisat2 command.

sh -c: This is used to execute a complex command within xargs. It's necessary because the output redirection (>, 2>) is shell functionality, and without sh -c, xargs wouldn't handle it correctly.

Output Redirection:

> ../analyses/13-hisat-deseq2/{}_hisat.stdout: Redirects the standard output to a unique file for each sample.
2> ../analyses/13-hisat-deseq2/{}_hisat.stderr: Redirects the standard error to a different unique file for each sample.
This setup ensures that the output from each sample's alignment process is neatly organized into separate files, making it easier to manage and debug individual runs.




```{r, engine='bash'}
echo "13-hisat-deseq2/*bam" >> ../analyses/.gitignore
echo "13-hisat-deseq2/*bam*" >> ../analyses/.gitignore
```

```{r, engine='bash'}
for samfile in ../analyses/13-hisat-deseq2/*.sam; do
  bamfile="${samfile%.sam}.bam"
  sorted_bamfile="${samfile%.sam}.sorted.bam"
  /home/shared/samtools-1.12/samtools view -bS -@ 20 "$samfile" > "$bamfile"
  /home/shared/samtools-1.12/samtools sort -@ 20 "$bamfile" -o "$sorted_bamfile"
  /home/shared/samtools-1.12/samtools index -@ 20 "$sorted_bamfile"
done
```

,
```{r, engine='bash'}
rm ../analyses/13-hisat-deseq2/*sam
```


```{r, engine='bash'}
ls ../analyses/13-hisat-deseq2/*sorted.bam | wc -l
```




# Stringtie

```{r, engine='bash'}
echo "13-hisat-deseq2/*gtf" >> ../analyses/.gitignore
```


```{bash}
/home/shared/gffread-0.12.7.Linux_x86_64/gffread \
../analyses/12-fix-gff/mod_augustus.gtf \
-T \
-o ../analyses/13-hisat-deseq2/mod_augustus.gff

```



```{r, engine='bash'}
find ../analyses/13-hisat-deseq2/*sorted.bam \
| xargs basename -s .sorted.bam | xargs -I{} \
sh -c '/home/shared/stringtie-2.2.1.Linux_x86_64/stringtie \
-p 36 \
-eB \
-G ../analyses/13-hisat-deseq2/mod_augustus.gff \
-o ../analyses/13-hisat-deseq2/{}.gtf \
../analyses/13-hisat-deseq2/{}.sorted.bam'
```


```{bash}
#!/bin/bash

# Directory to search
directory="/home/shared/8TB_HDD_03/sr320/github/grace-L-byssus/output/13-Hisat"

# File extension to look for (e.g., .gtf)
extension="gtf"

# Output file
output_file="/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/13-Hisat/output.txt"

# Ensure the directory exists
if [ ! -d "$directory" ]; then
    echo "The directory $directory does not exist."
    exit 1
fi

# Find files with the specified extension and store them in an array
shopt -s nullglob
files=("$directory"/*."$extension")
shopt -u nullglob

# Check if array is empty
if [ ${#files[@]} -eq 0 ]; then
    echo "No files found with the extension .$extension in the directory $directory."
    exit 1
fi

# Create a new array with filenames without extensions
output=()
for file in "${files[@]}"; do
    # Extract filename without the extension
    filename=$(basename "$file" ."$extension")
    # Append the filename without extension and the full path to the output array
    output+=("$filename $file")
done

# Write only the array contents to the text file
for item in "${output[@]}"; do
    echo "$item"
done > "$output_file"

echo "Output written to $output_file"


```

```{bash}
head /home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/13-Hisat/output.txt
```



```{bash}
python /home/shared/stringtie-2.2.1.Linux_x86_64/prepDE.py \
-i /home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/13-Hisat/output.txt \
-g /home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/13-Hisat/gene_count_matrix.csv 
```

```{bash}
head  /home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/13-Hisat/gene_count_matrix.csv 

```