做piRNA gff文件

#从miRBase下载miRNA的注释信息

#从piRNAbank下载mouse_pir.txt

#将mouse_pir.txt转换成gtf注释文件

#用python脚本转换成bed

for file in /media/pc/6a524d78-97d1-481c-b068-8116a4d007f8/jjc/piRNA/mm9_pi/*.txt

do

grep ">" $file | awk -F: '{print $2,"\t",$3,"\t",$4,"\t",$1,"\t",$5}'

done

sed -n '1397836,1399813p' mm9pi.bed> last.bed

#bed文件转换成gtf

cat sorted.mm9pi.bed| tr "\>\|" "\t" | awk '{printf("%s\tpiRNAbank\tpiRNA\t%s\t%s\t.\t%s\t.\tID=%s;transcript_id=%s;\n", $1, $2, $3, $9, $4, $6)}' > mm9pi.gtf

cat last.bed| tr "\>\|" "\t" | awk '{printf("%s\tpiRNAbank\tpiRNA\t%s\t%s\t.\t%s\t.\tID=%s;\n", $1, $2, $3, $7, $4)}' > last.gtf

cat last.gtf>> mm9pi.gtf

#排序和链的替换

sort -k1,1 -k2,2n mm9pi.gtf> sorted.mm9pi.gtf

sed -i 's/Minus/-/g' sorted.mm9pi.gtf

sed -i 's/Plus/+/g' sorted.mm9pi.gtf

ls *R1.clean.trim.fastq | while read id ; do bowtie2 -x /media/pc/6a524d78-97d1-481c-b068-8116a4d007f8/jjc/piRNA/piPipes.1/piPipes/common/mm9/mm9 -U $id -S ${id%%.*}.mm9.sam -p 10 -N 1 ; done

ls *mm10.sam | while read id ; do htseq-count -s no -t miRNA -i ID $id ../mmu.gff3 > ${id%%.*}.counts_out.txt ; done