# masterbashscript.sh - stacks pipeline for Ny. darlingi nextRAD data

#!/bin/bash

# run all samples through ustacks
# includes 19 individuals from Peru and Brazil not in current study for catalog building

src=$HOME/projects/Adarlingi/combined_analysis_2018
seqdir=/illumina/darlingi_nextrad_samples       
logdir=$src/denovo_log       
stacksdir=$src/denovo_stacks
dbdir=/genomes/Adarlingi/
dbname="Adarlingi_bwa"
mapdir=$src/population_maps
outdir=$stacksdir/populations_corrected_10kloci_p4r0.5_maf0.02het

id=1
while read sample
do
         echo "ustacks -f $seqdir/${sample}.fastq.gz -o $stacksdir -i $id --name $sample -M 4 -d -p 1 2> $logdir/${sample}_ustacks.log" >>$$src/scripts/run_ustacks_kate_new_samples.sh
         let "id+=1"     
done < kate_new_samples
parallel -j 20 --noswap --progress --nice 19 < $src/scripts/run_ustacks_kate_new_samples.sh

# build master darlingi catalog using catalog_map of 24 samples

echo 'starting cstacks'
cstacks -n 4 -P $stacksdir -M $mapdir/catalog_map -p 60 2> $logdir/catalog.log

# align catalog to darlingi genome (AdarC3)

bwa mem -t 60 $dbdir/$dbname $stacksdir/catalog.fa.gz > $stacksdir/catalog.sam
cd $stacksdir
cat catalog.sam | parallel "samtools view -b -S {} | samtools sort - {.}; samtools index {.}.bam"
rm *.sam

# after catalog building and ustacks - match 190 deforestation samples in brazil_deforestation_popmap to catalog

echo 'starting sstacks'
sstacks -P $stacksdir -M $mapdir/brazil_deforestation_popmap -p 60 2> $logdir/sstacks.log
echo 'starting tsv2bam'
tsv2bam -P $stacksdir -M $mapdir/brazil_deforestation_popmap -t 60 2> $logdir/tsv2bam.log
echo 'starting gstacks'
gstacks -P $stacksdir -M $mapdir/brazil_deforestation_popmap -t 60 2> $logdir/gstacks.log
stacks-integrate-alignments -P $stacksdir -B $stacksdir/catalog.bam -O $stacksdir

# run populations - population map includes only 164 individuals matching to >=100,000 catalog loci, locality is population

mkdir $outdir
populations -P $stacksdir -M $mapdir/brazil_deforestation_popmap_locality_10kloci -O $outdir \
        -r 0.5 -p 4 --vcf --genepop --structure --fstats --hwe --write_single_snp \
        --no_hap_exports --min_maf 0.02 --max_obs_het 0.7 -t 20