nzimmer_metageno2/wgs.sh

#!/bin/bash

mkdir results

# Question 1
soft/bowtie2 --end-to-end --fast -x databases/all_genome.fasta -1 EchE_R1.fastq.gz -2 EchE_R2.fastq.gz -S results/alignment.sam

# Question 2

# a
samtools view -b results/alignment.sam

# b
samtools sort -@ 4 results/alignment.bam -o results/alignment.sorted.bam

# c
samtools index results/alignment.sorted.bam

# d
samtools idxstats -@ 4 results/alignment.sorted.bam > results/alignment.idx

# f
grep ">" databases/all_genome.fasta|cut -f 2 -d ">" > results/association.tsv

# Question 3

soft/megahit --k-list 21 --mem-flag 0 -1 EchE_R1.fastq.gz -2 EchE_R2.fastq.gz -o contigs

# Question 4

soft/prodigal -i contigs/final.contigs.fa -d genes.fna

# Question 5

sed "s:>:*\n>:g" genes.fna | sed -n "/partial=00/,/*/p"|grep -v "*" > genes_full.fna

# Question 6