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

set -e

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 PAN010 PAN011 PAN027 PAN028; do
    sleep 3
    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

    # Only run for PAN027
    if [ "$individual" = "PAN027" ]; then
        #FORMAT HORHAP
        for a in /public/groups/migalab/mcechova/pedigree/annotations/v1.1/${individual}/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
    fi

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

    #FORMAT CENSAT
    for a in /public/groups/migalab/mcechova/pedigree/annotations/v1.1/${individual}/*.cenSat.bed; do
        filename=$(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

echo "Converting to big bed now"
for individual in PAN010 PAN011 PAN027 PAN028; do
    sleep 3
    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;