grenouille_rousse
mitochondrion

Repository


seq_tot=0
n=0
for file in Data/Miseq329/fastq/*_R1_*.fastq.gz
do
sample=$(echo $file|awk -F "/" '{print $NF}'| sed -e 's/_.*.fastq.*//g' | sort | uniq)
line=$(zcat $file|wc -l)
seq=$(echo $line/4|bc)
n=$((n+1))
seq_tot=$((seq_tot+seq))
echo -e "|"$sample"|"$seq"|"
done
moy=$((seq_tot/n))
echo "Il y a "$seq_tot" séquences en données brutes au total, soit "$moy" séquences par échantillon en moyenne"


seq_tot=0
n=0
for file in Data/Miseq330/fastq/*_R1_*.fastq.gz
do
sample=$(echo $file|awk -F "/" '{print $NF}'| sed -e 's/_.*.fastq.*//g' | sort | uniq)
line=$(zcat $file|wc -l)
seq=$(echo $line/4|bc)
n=$((n+1))
seq_tot=$((seq_tot+seq))
echo -e "|"$sample"|"$seq"|"
done
moy=$((seq_tot/n))
echo "Il y a "$seq_tot" séquences en données brutes au total, soit "$moy" séquences par échantillon en moyenne"


for file in Data/Miseq329/fastq/*_R1_*.fastq.gz
do
fastqc --outdir Analysis/Miseq329/Quality/R1/ $file
done

multiqc -m fastqc Analysis/Miseq329/Quality/R1/ -o Analysis/Miseq329/Report/ -n QC_329_R1_Report

for file in Data/Miseq329/fastq/*_R2_*.fastq.gz
do
fastqc --outdir Analysis/Miseq329/Quality/R2/ $file
done

multiqc -m fastqc Analysis/Miseq329/Quality/R2/ -o Analysis/Miseq329/Report/ -n QC_329_R2_Report


for file in Data/Miseq330/fastq/*_R1_*.fastq.gz
do
fastqc --outdir Analysis/Miseq330/Quality/R1/ $file
done

multiqc -m fastqc Analysis/Miseq330/Quality/R1/ -o Analysis/Miseq330/Report/ -n QC_330_R1_Report

for file in Data/Miseq330/fastq/*_R2_*.fastq.gz
do
fastqc --outdir Analysis/Miseq330/Quality/R2/ $file
done

multiqc -m fastqc Analysis/Miseq330/Quality/R2/ -o Analysis/Miseq330/Report/ -n QC_330_R2_Report


conda activate cutadapt


mkdir Analysis/Miseq329/Demultiplex
awk '{print $3}' Data/Rana_barcodes_libs_329.csv |sort|uniq > Data/list_lib_329.txt

while read a
    do
    echo $a
    grep "$a" Data/Rana_barcodes_libs_329.csv |awk '{print ">"$1"\n"$2}' > Data/Rana_barcodes_libs_329.fasta
    cutadapt -e 0.17 --minimum-length 30 -q 10 --no-indels -g file:Data/Rana_barcodes_libs_329.fasta -o Analysis/Miseq329/Demultiplex/demux-{name}_R1.fastq.gz -p Analysis/Miseq329/Demultiplex/demux-{name}_R2.fastq.gz Data/Miseq329/fastq/"$a"_*_R1_001.fastq.gz Data/Miseq329/fastq/"$a"_*_R2_001.fastq.gz
    done < Data/list_lib_329.txt


seq_tot=0
n=0
for file in Analysis/Miseq329/Demultiplex/*_R1.fastq.gz
do
sample=$(echo $file|awk -F "/" '{print $NF}'| sed -e 's/_R1.fastq.*//g' | sort | uniq)
line=$(zcat $file|wc -l)
seq=$(echo $line/4|bc)
n=$((n+1))
seq_tot=$((seq_tot+seq))
echo -e "|"$sample"|"$seq"|"
done
moy=$((seq_tot/n))
echo "Il y a "$seq_tot" séquences en sortie de démultiplexage, soit "$moy" séquences par échantillon en moyenne"


mkdir Analysis/Miseq330/Demultiplex
awk '{print $3}' Data/Rana_barcodes_libs_330.csv |sort|uniq > Data/list_lib_330.txt

while read a
    do
    echo $a
    grep "$a" Data/Rana_barcodes_libs_330.csv |awk '{print ">"$1"\n"$2}' > Data/Rana_barcodes_libs_330.fasta
    cutadapt -e 0.17 --minimum-length 30 -q 10 --no-indels -g file:Data/Rana_barcodes_libs_330.fasta -o Analysis/Miseq330/Demultiplex/demux-{name}_R1.fastq.gz -p Analysis/Miseq330/Demultiplex/demux-{name}_R2.fastq.gz Data/Miseq330/fastq/"$a"_*_R1_001.fastq.gz Data/Miseq330/fastq/"$a"_*_R2_001.fastq.gz
    done < Data/list_lib_330.txt


seq_tot=0
n=0
for file in Analysis/Miseq330/Demultiplex/*_R1.fastq.gz
do
sample=$(echo $file|awk -F "/" '{print $NF}'| sed -e 's/_R1.fastq.*//g' | sort | uniq)
line=$(zcat $file|wc -l)
seq=$(echo $line/4|bc)
n=$((n+1))
seq_tot=$((seq_tot+seq))
echo -e "|"$sample"|"$seq"|"
done
moy=$((seq_tot/n))
echo "Il y a "$seq_tot" séquences en sortie de démultiplexage, soit "$moy" séquences par échantillon en moyenne"


conda activate cutadapt

mkdir Analysis/Miseq329/Trimming
for i in Analysis/Miseq329/Demultiplex/*_R1.fastq.gz
do
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/.fastq.gz/.fastq/')
cutadapt -q 10 -m 30 -a AGATCGGAAGAGC -o Analysis/Miseq329/Trimming/clean_"$sample" "$i"
done

for i in Analysis/Miseq329/Demultiplex/*_R2.fastq.gz
do
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/.fastq.gz/.fastq/')
cutadapt -u 5 -q 10 -m 30 -a AGATCGGAAGAGC -o Analysis/Miseq329/Trimming/clean_"$sample" "$i"
done


conda activate fastqpair

for i in Analysis/Miseq329/Trimming/clean_demux-*_R1.fastq
do
sample=$(echo $i | sed -e 's/_R1.fastq//g')
fastq_pair "$sample"_R1.fastq "$sample"_R2.fastq
done


seq_tot=0
n=0
for file in Analysis/Miseq329/Trimming/*_R1.fastq.paired.fq
do
sample=$(echo $file|awk -F "/" '{print $NF}'| sed -e 's/_R1.fastq.*//g' | sort | uniq)
line=$(cat $file|wc -l)
seq=$(echo $line/4|bc)
n=$((n+1))
seq_tot=$((seq_tot+seq))
echo -e "|"$sample"|"$seq"|"
done
moy=$((seq_tot/n))
echo "Il y a "$seq_tot" séquences en sortie de trimming, soit "$moy" séquences par échantillon en moyenne"


conda activate cutadapt

mkdir Analysis/Miseq330/Trimming
for i in Analysis/Miseq330/Demultiplex/*_R1.fastq.gz
do
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/.fastq.gz/.fastq/')
cutadapt -q 10 -m 30 -a AGATCGGAAGAGC -o Analysis/Miseq330/Trimming/clean_"$sample" "$i"
done

for i in Analysis/Miseq330/Demultiplex/*_R2.fastq.gz
do
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/.fastq.gz/.fastq/')
cutadapt -u 5 -q 10 -m 30 -a AGATCGGAAGAGC -o Analysis/Miseq330/Trimming/clean_"$sample" "$i"
done


conda activate fastqpair

for i in Analysis/Miseq330/Trimming/clean_demux-*_R1.fastq
do
sample=$(echo $i | sed -e 's/_R1.fastq//g')
fastq_pair "$sample"_R1.fastq "$sample"_R2.fastq
done


seq_tot=0
n=0
for file in Analysis/Miseq330/Trimming/*_R1.fastq.paired.fq
do
sample=$(echo $file|awk -F "/" '{print $NF}'| sed -e 's/_R1.fastq.*//g' | sort | uniq)
line=$(cat $file|wc -l)
seq=$(echo $line/4|bc)
n=$((n+1))
seq_tot=$((seq_tot+seq))
echo -e "|"$sample"|"$seq"|"
done
moy=$((seq_tot/n))
echo "Il y a "$seq_tot" séquences en sortie de trimming, soit "$moy" séquences par échantillon en moyenne"


mkdir Analysis/Miseq329/Mapping/
conda activate mapping


bwa index Data/Reference/LR991693_Rana_temporia_mt.fasta

samtools faidx Data/Reference/LR991693_Rana_temporia_mt.fasta

samtools dict Data/Reference/LR991693_Rana_temporia_mt.fasta > Data/Reference/LR991693_Rana_temporia_mt.fasta.dict


mkdir Analysis/Miseq329/Mapping/LR991693


for i in Analysis/Miseq329/Trimming/*_R1.fastq.paired.fq
do
file=$(echo $i |sed 's/_R1.fastq.paired.fq//')
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/_R1.fastq.paired.fq//')
bwa mem -t 20 -R '@RG\tID:'${sample}'\tSM:'${sample}'\tPL:illunmina' Data/Reference/LR991693_Rana_temporia_mt.fasta $i ${file}_R2.fastq.paired.fq |samtools sort -@ 10 -o Analysis/Miseq329/Mapping/LR991693/mapped_${sample}.bam -
done


for i in Analysis/Miseq329/Mapping/LR991693/*.bam
do
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/.bam//')
samtools flagstat $i | awk -F " " -v var1="$sample" '{if($0~/paired in sequencing/){total=$1};if($0~/with itself and mate mapped/){paired=$1};if($0~/singletons/){sing=$1}}END{sum=sing+paired;perc=sum/total*100;print "|"var1"|"sum"|"perc"|"}'
done


bwa index Data/Reference/MT483700_Rana_temporia_mt.fasta

samtools faidx Data/Reference/MT483700_Rana_temporia_mt.fasta

samtools dict Data/Reference/MT483700_Rana_temporia_mt.fasta > Data/Reference/MT483700_Rana_temporia_mt.fasta.dict


mkdir Analysis/Miseq329/Mapping/MT483700


for i in Analysis/Miseq329/Trimming/*_R1.fastq.paired.fq
do
file=$(echo $i |sed 's/_R1.fastq.paired.fq//')
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/_R1.fastq.paired.fq//')
bwa mem -t 20 -R '@RG\tID:'${sample}'\tSM:'${sample}'\tPL:illunmina' Data/Reference/MT483700_Rana_temporia_mt.fasta $i ${file}_R2.fastq.paired.fq |samtools sort -@ 10 -o Analysis/Miseq329/Mapping/MT483700/mapped_${sample}.bam -
done


for i in Analysis/Miseq329/Mapping/MT483700/*.bam
do
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/.bam//')
samtools flagstat $i | awk -F " " -v var1="$sample" '{if($0~/paired in sequencing/){total=$1};if($0~/with itself and mate mapped/){paired=$1};if($0~/singletons/){sing=$1}}END{sum=sing+paired;perc=sum/total*100;print "|"var1"|"sum"|"perc"|"}'
done


bwa index Data/Reference/NC_042226_Rana_temporia_mt.fasta

samtools faidx Data/Reference/NC_042226_Rana_temporia_mt.fasta

samtools dict Data/Reference/NC_042226_Rana_temporia_mt.fasta > Data/Reference/NC_042226_Rana_temporia_mt.fasta.dict


mkdir Analysis/Miseq329/Mapping/NC_042226


for i in Analysis/Miseq329/Trimming/*_R1.fastq.paired.fq
do
file=$(echo $i |sed 's/_R1.fastq.paired.fq//')
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/_R1.fastq.paired.fq//')
bwa mem -t 20 -R '@RG\tID:'${sample}'\tSM:'${sample}'\tPL:illunmina' Data/Reference/NC_042226_Rana_temporia_mt.fasta $i ${file}_R2.fastq.paired.fq |samtools sort -@ 10 -o Analysis/Miseq329/Mapping/NC_042226/mapped_${sample}.bam -
done


for i in Analysis/Miseq329/Mapping/NC_042226/*.bam
do
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/.bam//')
samtools flagstat $i | awk -F " " -v var1="$sample" '{if($0~/paired in sequencing/){total=$1};if($0~/with itself and mate mapped/){paired=$1};if($0~/singletons/){sing=$1}}END{sum=sing+paired;perc=sum/total*100;print "|"var1"|"sum"|"perc"|"}'
done


mkdir Analysis/Miseq330/Mapping/
conda activate mapping


mkdir Analysis/Miseq330/Mapping/LR991693


for i in Analysis/Miseq330/Trimming/*_R1.fastq.paired.fq
do
file=$(echo $i |sed 's/_R1.fastq.paired.fq//')
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/_R1.fastq.paired.fq//')
bwa mem -t 20 -R '@RG\tID:'${sample}'\tSM:'${sample}'\tPL:illunmina' Data/Reference/LR991693_Rana_temporia_mt.fasta $i ${file}_R2.fastq.paired.fq |samtools sort -@ 10 -o Analysis/Miseq330/Mapping/LR991693/mapped_${sample}.bam -
done


for i in Analysis/Miseq330/Mapping/LR991693/*.bam
do
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/.bam//')
samtools flagstat $i | awk -F " " -v var1="$sample" '{if($0~/paired in sequencing/){total=$1};if($0~/with itself and mate mapped/){paired=$1};if($0~/singletons/){sing=$1}}END{sum=sing+paired;perc=sum/total*100;print "|"var1"|"sum"|"perc"|"}'
done


mkdir Analysis/Miseq330/Mapping/MT483700


for i in Analysis/Miseq330/Trimming/*_R1.fastq.paired.fq
do
file=$(echo $i |sed 's/_R1.fastq.paired.fq//')
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/_R1.fastq.paired.fq//')
bwa mem -t 20 -R '@RG\tID:'${sample}'\tSM:'${sample}'\tPL:illunmina' Data/Reference/MT483700_Rana_temporia_mt.fasta $i ${file}_R2.fastq.paired.fq |samtools sort -@ 10 -o Analysis/Miseq330/Mapping/MT483700/mapped_${sample}.bam -
done


for i in Analysis/Miseq330/Mapping/MT483700/*.bam
do
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/.bam//')
samtools flagstat $i | awk -F " " -v var1="$sample" '{if($0~/paired in sequencing/){total=$1};if($0~/with itself and mate mapped/){paired=$1};if($0~/singletons/){sing=$1}}END{sum=sing+paired;perc=sum/total*100;print "|"var1"|"sum"|"perc"|"}'
done


mkdir Analysis/Miseq330/Mapping/NC_042226


for i in Analysis/Miseq330/Trimming/*_R1.fastq.paired.fq
do
file=$(echo $i |sed 's/_R1.fastq.paired.fq//')
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/_R1.fastq.paired.fq//')
bwa mem -t 20 -R '@RG\tID:'${sample}'\tSM:'${sample}'\tPL:illunmina' Data/Reference/NC_042226_Rana_temporia_mt.fasta $i ${file}_R2.fastq.paired.fq |samtools sort -@ 10 -o Analysis/Miseq330/Mapping/NC_042226/mapped_${sample}.bam -
done


for i in Analysis/Miseq330/Mapping/NC_042226/*.bam
do
sample=$(echo $i|awk -F "/" '{print $NF}' |sed 's/.bam//')
samtools flagstat $i | awk -F " " -v var1="$sample" '{if($0~/paired in sequencing/){total=$1};if($0~/with itself and mate mapped/){paired=$1};if($0~/singletons/){sing=$1}}END{sum=sing+paired;perc=sum/total*100;print "|"var1"|"sum"|"perc"|"}'
done