#write down chromosome sizes
cat /public/groups/migalab/mcechova/pedigree/assemblies/v1.1/PAN010*.fai | cut -f1,2 | sort -V >PAN010/genome.chrom.sizes
cat /public/groups/migalab/mcechova/pedigree/assemblies/v1.1/PAN011*.fai | cut -f1,2 | sort -V >PAN011/genome.chrom.sizes
cat /public/groups/migalab/mcechova/pedigree/assemblies/v1.1/PAN027*.fai | cut -f1,2 | sort -V >PAN027/genome.chrom.sizes
cat /public/groups/migalab/mcechova/pedigree/assemblies/v1.1/PAN028*.fai | cut -f1,2 | sort -V >PAN028/genome.chrom.sizes

#convert the assemblies to the 2bit format
wget http://hgdownload.soe.ucsc.edu/admin/exe/linux.x86_64/faToTwoBit
chmod +x faToTwoBit

./faToTwoBit ../../assemblies/v1.1/assembly.v1.1.PAN010.diploid.fa assembly.v1.1.PAN010.diploid.2bit
./faToTwoBit ../../assemblies/v1.1/assembly.v1.1.PAN011.diploid.fa assembly.v1.1.PAN011.diploid.2bit
./faToTwoBit ../../assemblies/v1.1/assembly.v1.1.PAN027.diploid.fa assembly.v1.1.PAN027.diploid.2bit
./faToTwoBit ../../assemblies/v1.1/assembly.v1.1.PAN028.diploid.fa assembly.v1.1.PAN028.diploid.2bit

##############################################
#convert all annotation bed files to bb format
##############################################

cd /public/groups/migalab/mcechova/pedigree/browser/v1.1

source /opt/miniconda/etc/profile.d/conda.sh
conda activate /public/home/mcechova/conda/samtools 

for individual in PAN027; do
    echo "Processing $individual"

    #FORMAT FLAGGER
    for a in /public/groups/migalab/mcechova/pedigree/annotations/v1.1/${individual}/flagger*.bed; do
        filename=$(basename "$a" .bed)
        echo "  $filename"

        # Sort BED (remove track + comments)
        grep -v "track name" "$a" | \
        grep -v "^#" | \
        awk 'BEGIN{OFS="\t"} { $7=$2; $8=$3; print }' | \
        bedtools sort -g ${individual}/genome.chrom.sizes \
        > ${individual}/${filename}.sorted.bed
    done

    #FORMAT CENTRODIP
    for a in /public/groups/migalab/mcechova/pedigree/annotations/v1.1/${individual}/centrodip*.bed; do
        filename=$(basename "$a" .bed)
        echo "  $filename"

        # Sort BED (remove track + comments)
        grep -v "track name" "$a" | \
        grep -v "^#" | \
        awk 'BEGIN{OFS="\t"} { $5=1; print }' | \
        bedtools sort -g ${individual}/genome.chrom.sizes \
        > ${individual}/${filename}.sorted.bed
    done

    #FORMAT HORHAP, NUCFLAG
    for a in /public/groups/migalab/mcechova/pedigree/annotations/v1.1/${individual}/{nucflag,horhap}*.bed; do
        filename=$(basename "$a" .bed)
        echo "  $filename"

        # Sort BED (remove track + comments)
        grep -v "track name" "$a" | \
        grep -v "^#" | \
        bedtools sort -g ${individual}/genome.chrom.sizes \
        > ${individual}/${filename}.sorted.bed
    done

done

for individual in PAN027; do
    echo "Processing $individual"
    cd ${individual}

    for a in *.sorted.bed; do 
    	echo $a; 
    	filename=$(basename "$a" .sorted.bed)
        echo "  $filename"
        # Convert to BigBed (use sorted file)
        ../bedToBigBed \
            $a \
            genome.chrom.sizes \
            ${filename}.bb
    done;
    cd ..
done;