DIR=$(zenity --file-selection --directory --title="Select a DIRECTORY CONTAINING DATA")
cd $DIR

THRESHOLD=$(zenity --forms --title="INDICATE THRESHOLD min COVERAGE" --text="INDICATE THRESHOLD" \
   --add-entry="THRESHOLD")

GQ=$(zenity --forms --title="INDICATE THRESHOLD Genotyping Quality" --text="INDICATE THRESHOLD" \
   --add-entry="THRESHOLD")



echo "COVERAGE Analysis step starting"


zenity progress bar dialog
(
echo "20" ; sleep 1
echo "#  COVERAGE and depth calculation" ; sleep 1

cd $DIR
depth=$(ls | grep .deep.txt)
if [ -z "${depth}" ];
then
for file in *.bam; 
do
samtools depth "$file" > "$(basename "$file" .bam).deep.txt" ;done
	
else
echo "$depth found."
fi

echo "40" ; sleep 1
echo "#under threshold--calculation " ; sleep 1



TOTBED=$(ls | grep .TOT.bed)
if [ -z "${TOTBED}" ];
then
for file in *.bam; 
do
bamToBed -i "$file" > "$(basename "$file" .bam).TOT.bed" ;done
	
else
echo "$TOTBED found."
fi

cat *.TOT.bed | awk -F'\t' '{print $1"\t"$2"\t"$3}' > TOTALI.bed

sortBed -i TOTALI.bed > PTOTALI.bed
mergeBed -i PTOTALI.bed > TOTALI.bed




for file in *.deep.txt; 
do

awk -F"\t" '$3 < '$THRESHOLD' { print $1"\t"$2"\t"$2 }' "$file" > "$(basename "$file" .deep.txt).underT.bed" ;done

echo "50" ; sleep 1
echo "#not covered regions " ; sleep 1

echo "80" ; sleep 1
echo "# region in target calculation" ; sleep 1
for file in *.TOT.bed
do
subtractBed -a TOTALI.bed -b $file > "$(basename "$file" .TOT.bed).zero.bed" ;done

for file in *.underT.bed;
do
intersectBed -a TOTALI.bed -b "$file" > "$(basename "$file" .underT.bed).underTHRESHOLD.bed" ;done
for file in *.underTHRESHOLD.bed; 
do
cat "$file" "$(basename "$file" .underTHRESHOLD.bed).zero.bed" > "$(basename "$file" .underTHRESHOLD.bed).RECOVER.bed" ;done
echo "100" ; sleep 1
) |
zenity --progress --auto-close "press OK and go on" 
--text "upload" --percentage=0


for file in *.deep.txt; do                                                                                                                                                                                                                                                                      awk -F'\t' '{print $1"-"$2"\t"$1"\t"$2"\t"$3}' $file > "$(basename "$file" .deep.txt).tempD";
done

cat *tempD > COVERAGE


awk -F"\t" '!_[$1,$2]++' COVERAGE > BASES

sort -k1 BASES > tempBASES

for file in *.tempD
do
sort -k1 $file > "$(basename "$file" .tempD).tempD2";
done


for file in *.tempD
do
join -a 1 -a 2 -e "0" tempBASES "$(basename "$file" .tempD).tempD2" -o 2.4  > "$(basename "$file" .tempD).tempDID";
done


for file in *.tempDID
do
find $file -type f -print -exec cat {} \; > "$(basename "$file" .tempDID).tempDID2";
done

rm -f, yes | rm *.tempDID

paste *.tempDID2 | sed "s/.tempDID//g" > MATRIX

echo "COORDINATE" > tempCO 
awk -F'\t' '{print $1}' tempBASES >> tempCO 

paste tempCO MATRIX | sed "s/\t/,/g" > CoverageMatrix.csv

rm -f, yes | rm *.temp

rm -f, yes | rm *.deep*
rm -f, yes | rm *.underTHRESHOLD.bed
rm -f, yes | rm *.TOT.bed
rm -f, yes | rm *.zero.bed
rm -f, yes | rm *.underT.bed

zenity progress bar dialog
(
echo "20" ; sleep 1
echo "#  vcf files processing" ; sleep 1

mkdir VCF_Original

cp *.vcf VCF_Original

ls *.vcf|xargs -I% sed -i 's/$/\t%/' %

for file in *.vcf; do                                                                                                                                                                                                                                                                      grep -v -h '^#' $file > "$(basename "$file" .vcf).tempQ"; 
done


for file in *.vcf
do
awk -F'\t' '{print $10}' "$(basename "$file" .vcf).tempQ" | awk -F':' '{print $4}'  > "$(basename "$file" .vcf).tempQ1";
done



for file in *.vcf
do
paste "$(basename "$file" .vcf).tempQ" "$(basename "$file" .vcf).tempQ1" > "$(basename "$file" .vcf).tempQ2";
done

for file in *.vcf
do
awk -F"\t" '$12 >= '$GQ' { print $0 }' "$(basename "$file" .vcf).tempQ2" | awk '{$12=""; print}' > "$(basename "$file" .vcf).tempQ3";
done


rm -f, yes | rm *.vcf

for file in *.tempQ3; do                                                                                                                                                                                                                                                                      cp -rf $file "$(basename "$file" .tempQ3).GQ.vcf"; 
done
sed -i "s/ /\t/g" *.vcf
sed -i "s/ /\t/g" *.tempQ3

cat *tempQ3 > MULTIPLE


awk -F"\t" '!_[$1,$2,$4,$5]++' MULTIPLE > ALLVARIANT


for file in *.tempQ2
do
awk -F"\t" '$12 < '$GQ' { print $1"\t"$2"\t"$2 }' $file > "$(basename "$file" .tempQ2).GQ.bed";
done



for file in *.GQ.bed
do
cat  $file "$(basename "$file" .GQ.bed).RECOVER.bed" > "$(basename "$file" .GQ.bed).RECOVER_ALL.bed";
done







rm *.txt

rm MULTIPLE.vcf
) |
zenity --progress --auto-close "press Ok and go on" 
--text "upload data" --percentage=0


zenity progress bar dialog
(
echo "40" ; sleep 1
echo "# PED creation" ; sleep 1

for file in *.vcf
do
awk -F'\t' '{print $1"-"$2"-"$4"-"$5}' $file > "$(basename "$file" .vcf).temp0" ;
done

for file in *.vcf
do
paste "$(basename "$file" .vcf).temp0" $file > "$(basename "$file" .vcf).temp";
done

for file in *.vcf
do
awk '!seen[$1]++ >= 1' "$(basename "$file" .vcf).temp" > "$(basename "$file" .vcf).TEMPO1";
done


FILE2=$DIR/ALLVARIANT

awk -F'\t' '{print $1"-"$2"-"$4"-"$5}' $FILE2 > temp1
paste temp1 $FILE2 > temp2

sort -k1 temp2 > temp5


for file in *.vcf
do
sort -k1 "$(basename "$file" .vcf).TEMPO1" > "$(basename "$file" .vcf).temp6";
done


for file in *.vcf
do
awk -F'\t' '{print $1"\t"$11}' "$(basename "$file" .vcf).temp6" > "$(basename "$file" .vcf).temp6bis";
done

for file in *.vcf
do

awk -F':' '{print $1}' "$(basename "$file" .vcf).temp6bis" > "$(basename "$file" .vcf).temp6tris";
done


for file in *.vcf
do
sort -k1 "$(basename "$file" .vcf).temp6tris" > "$(basename "$file" .vcf).temp6tris2";
done


for file in *.vcf
do
join -a 1 -a 2 -e "NA" temp5 "$(basename "$file" .vcf).temp6tris2" -o 1.1,2.2 > "$(basename "$file" .vcf).ID";
done


for file in *.vcf
do
sed 's/-/\t/g' "$(basename "$file" .vcf).ID"  > "$(basename "$file" .vcf).ID.bed";
done



for file in *.vcf
do

awk -F'\t' '{print $1"\t"$2"\t"$2"\t"$3"\t"$4"\t"$5}' "$(basename "$file" .vcf).ID.bed" > "$(basename "$file" .vcf).ID2.bed";
done

) |
zenity --progress --auto-close "press OK and go on" 
--text "upload data" --percentage=0

zenity progress bar dialog
(
echo "60" ; sleep 1
echo "# genotypes removal" ; sleep 1
for file in *.GQ.vcf
do
subtractBed -a "$(basename "$file" .vcf).ID2.bed" -b "$(basename "$file" .GQ.vcf).RECOVER_ALL.bed" | sed 's/NA/AA/g' > "$(basename "$file" .vcf).ID3.bed";
done

) |
zenity --progress --auto-close "press ok and go on" 
--text "upload data" --percentage=0

zenity progress bar dialog
(
echo "80" ; sleep 1
echo "# matrix transposition" ; sleep 1

for file in *.vcf
do
awk -F'\t' '{print $1"-"$2"-"$4"-"$5"\t"$6}' "$(basename "$file" .vcf).ID3.bed" > "$(basename "$file" .vcf).ID4.bed";
done



for file in *.vcf
do
join -a 1 -a 2 -e "NA" temp5 "$(basename "$file" .vcf).ID4.bed" -o 2.2 > "$(basename "$file" .vcf).ID5";
done


for file in *.vcf
do
find "$(basename "$file" .vcf).ID5" -type f -print -exec cat {} \; > "$(basename "$file" .vcf).tempOUT";
done

paste *.tempOUT > PEDIGREE 




awk '
{
    for (i = 1; i <= NF; i++) {
        if(NR == 1) {
            s[i] = $i;
        } else {
            s[i] = s[i] " " $i;
        }
    }
}
END {
    for (i = 1; s[i] != ""; i++) {
        print s[i];
    }
}' PEDIGREE > tempPED

) |
zenity --progress --auto-close "press ok and go on" 
--text "upload data" --percentage=0


awk -F'\t' '{print $1}' temp5 > tempMAP

awk -F'-' '{print $1}' tempMAP | sed "s/chr//g" > tempMAP2
awk -F'-' '{print $2}' tempMAP > tempMAP3
paste tempMAP2 tempMAP tempMAP3 | sed "s/ /\t/g"  > tempMAP4
awk -F'\t' '{print $1"\t"$2"\t""0""\t"$3}' tempMAP4 > MAP.map


sed "s/\//@/g" tempPED | sed "s/0@1/A B/g" | sed "s/1@1/B B/g" |  sed "s/NA/0 0/g" | sed "s/1@2/A B/g" | sed "s/AA/A A/g" | sed "s/ 1 / A B /g" | sed "s/BA/A B/g" | sed "s/BA/A B/g" | sed "s/ /\t/g"  > temPED2


awk -F'\t' '{print $1"\t"$1"\t""0""\t""0""\t""0""\t""0""\t"$0}' temPED2 | cut -f1-6,8- | sed "s/.GQ.ID5//g" | sed "s/  / /g"> PED.ped

awk -F'\t' '{print $1"\t"$1"\t""0""\t""0""\t""0""\t""0""\t"$0}' temPED2 > tempPEDX

cut -f1-6,8- tempPEDX > tempPEDY


awk -F'\t' '{print $1"\t"$1"\t""0""\t""0""\t""0""\t""0""\t"$0}' temPED2 | awk '{$7=""; print}' > prova

awk -F'\t' '{print $1"\t"$1"\t""0""\t""0""\t""0""\t""0""\t"$0}' temPED2  > prova


zenity progress bar dialog
(
echo "100" ; sleep 1
echo "# analisi terminata" ; sleep 3


rm -f, yes | rm *temp*
rm -f, yes | rm *.ID*
rm -f, yes | rm *.TEMPO*

) |
zenity --progress --auto-close "press OK and go on" 
--text "upload data" --percentage=0


rm -f, yes | rm *temp*
rm -f, yes | rm *temPED2*
rm -f, yes | rm *.ID*
rm -f, yes | rm *.TEMPO*
rm -f, yes | rm *.bed
rm -f, yes | rm *.vcf
rm -f, yes | rm PEDIGREE
rm -f, yes | rm BASES
rm -f, yes | rm MULTIPLE
rm -f, yes | rm ALLVARIANT
rm -f, yes | rm MATRIX
rm -f, yes | rm COVERAGE
mv -f, yes | mv $DIR/VCF_Original/*.vcf $DIR/




zenity --info --title="analysis consensus" --window-icon=/dati/server/Software/appGEN.png --text=" are you happy? 
have a nice day 
         gentilini.davide@gmail.com" --ok-label="close me"