#!/bin/bash

## Modify this job script accordingly and submit with the command:
##    sbatch HPC.sbatch
#SBATCH --nodes=1   # number of nodes
#BATCH --ntasks-per-node=16   # 16 processor core(s) per node
#SBATCH --job-name='MapMiwiKO'
#SBATCH --mem=100000
#SBATCH --partition="all"
#SBATCH --mail-user=kara.stark@duke.edu   # email address
#SBATCH --mail-type=BEGIN
#SBATCH --mail-type=END
#SBATCH --mail-type=FAIL
#SBATCH --output="1-%j.out"
#SBATCH --error="1-%j.err"
## LOAD MODULES, INSERT CODE, AND RUN YOUR PROGRAMS HERE

module load samtools 

genome="/data/zhanglab/Kara_Stark/Kara_data/20230523_Koala_KoRV_liver_testis_eccDNA/mapping/phaCin.fa" 

for file in /data/zhanglab/Kara_Stark/Kara_data/20230523_Koala_KoRV_liver_testis_eccDNA/mapping/*.fastq; 
do 
name=$(basename $file)
#/data/zhanglab/oliver_chung/software/minimap2/minimap2 -ax map-ont $genome $file > $name"phaCin.sam"; 
samtools view -S -b $name".phaCin.sam" > $name".phaCin.bam";
samtools sort $name".phaCin.bam" -o $name".phaCin.sorted.bam";
samtools index $name".phaCin.sorted.bam";
samtools stats $name".phaCin.sorted.bam" | head -n 30 > $name".phaCin.sorted.bam.stats";
/data/zhanglab/oliver_chung/software/anaconda3/bin/bamCoverage -b $name".phaCin.sorted.bam" -o $name".phaCin.sorted.bw";
done