Data filtering and genome assembly

Shell script for data filtering:

#!/bin/bash

 

echo 'Finding fastqs in '$1

echo 'Using '$2' CPUs and '${3}'G mem'

 

base=`basename $1`

outdir=${base}_bbduk

mkdir $outdir

 

zcat ${1}/*_1.fastq.gz > $outdir/${base}_1.raw.fq

zcat ${1}/*_2.fastq.gz > $outdir/${base}_2.raw.fq

 

pigz -p $2 $outdir/${base}_*.raw.fq

 

echo ''

ls -al $outdir/${base}_1.raw.fq.gz

ls -al $outdir/${base}_2.raw.fq.gz

echo ''

 

bbduk.sh \

-Xmx${3}g \

threads=$2 \

in1=$outdir/${base}_1.raw.fq.gz \

in2=$outdir/${base}_2.raw.fq.gz \

out1=$outdir/${base}_1.bbduk.fq.gz \

out2=$outdir/${base}_2.bbduk.fq.gz \

ref=~/anaconda3/envs/main_env/opt/bbmap-38.22-0/resources/adapters.fa \

ktrim=r k=23 mink=11 hdist=2 maq=10 minlen=100 tpe tbo stats=${outdir}/bbduk.contaminants &> ${outdir}/bbduk.stats

 

echo ''

kmercountexact.sh -Xmx${3}g threads=8 in1=$outdir/${base}_1.raw.fq.gz in2=$outdir/${base}_2.raw.fq.gz khist=$outdir/${base}.raw.khist

 

echo ''

kmercountexact.sh -Xmx${3}g threads=8 in1=$outdir/${base}_1.bbduk.fq.gz in2=$outdir/${base}_2.bbduk.fq.gz khist=$outdir/${base}.bbduk.khist

 

echo ''

perl -lane 'if(/#/){next}else{print join(" ",$F[0],$F[1])}' $outdir/${base}.raw.khist > $outdir/${base}.raw.khist_jf.hist

perl -lane 'if(/#/){next}else{print join(" ",$F[0],$F[1])}' $outdir/${base}.bbduk.khist > $outdir/${base}.bbduk.khist_jf.hist