第二次RNA-seq实战总结(2)-数据下载并进行数据处理

~/.aspera/connect/bin/ascp -T -i /home/qiujunhui/.aspera/connect/etc/asperaweb_id_dsa.openssh -k 1 -l 200m 
anonftp@ftp-private.ncbi.nlm.nih.gov:/sra/sra-instant/reads/ByRun/sra/SRR/SRR957/SRR957677/SRR957677.sra ./
~/.aspera/connect/bin/ascp -T -i /home/qiujunhui/.aspera/connect/etc/asperaweb_id_dsa.openssh -k 1 -l 200m 
anonftp@ftp-private.ncbi.nlm.nih.gov:/sra/sra-instant/reads/ByRun/sra/SRR/SRR957/SRR957678/SRR957678.sra ./
~/.aspera/connect/bin/ascp -T -i /home/qiujunhui/.aspera/connect/etc/asperaweb_id_dsa.openssh -k 1 -l 200m 
anonftp@ftp-private.ncbi.nlm.nih.gov:/sra/sra-instant/reads/ByRun/sra/SRR/SRR957/SRR957679/SRR957679.sra ./
~/.aspera/connect/bin/ascp -T -i /home/qiujunhui/.aspera/connect/etc/asperaweb_id_dsa.openssh -k 1 -l 200m 
anonftp@ftp-private.ncbi.nlm.nih.gov:/sra/sra-instant/reads/ByRun/sra/SRR/SRR957/SRR957680/SRR957680.sra ./

iptables -I INPUT -p udp --dport 33001 -j ACCEPT
iptables -I OUTPUT -p udp --dport 33001 -j ACCEPT

wget ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2/data/hg19.tar.gz
mkdir hg19
mv hg19.tar.gz hg19
tar -zvxf hg19.tar.gz #将索引文件解压存放在hg19文件夹里面

wget ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_29/GRCh37_mapping/gencode.v29lift37.annotation.gtf.gz
mv GRCh37_mapping/gencode.v29lift37.annotation.gtf.gz hg19
tar -zvxf GRCh37_mapping/gencode.v29lift37.annotation.gtf.gz #将基因组注释文件保存至hg19文件夹并解压

#!/bin/bash
#把sra文件都存放在Sra文件夹里面
#参考基因组和注释文件都在hg19文件夹里面
#qiujunhui 1801963472@qq.com
mkdir Fastq_out #创建一个存放SRA-toolkit解压sra文件的输出文件夹
mkdir Sam_out #创建一个存放用hisat2比对的输出文件夹
mkdir Sorted.bam #创建一个存放用samtools将sam文件排序的生成的bam文件的文件夹
mkdir Counts  #创建一个存放用HTseq-count计算基因表达量的输出文件夹
#批量解压文件
for i in ~/Sra/*sra
do
        echo $i
        #判断sra文件时单端测序还是双末端测序
        num=$(fastq-dump -X 1 --split-spot -Z $i | wc -l | grep [0-9])
        if [ $num -eq 4 ];then
                echo "$i是单端测序"
                fastq-dump $i
                mv ~/Sra/*fastq ~/Fastq_out
                #用hisat2进行比对
                for x in ~/Fastq_out/*fastq
                do
                        echo $x
                        a=$(echo $x | cut -d "." -f1)

                       hisat2 -p 5 -x ~/hg19/genome -U $x -S $a.sam
                        mv ~/Fastq_out/*sam ~/Sam_out
                done
        else
                echo "$i是双端测序！"
                fastq-dump --split-files $i
                mkdir 1Fastq_out
                mkdir 2Fastq_out
                mv ~/Sra/*_1.fastq ~/1Fastq_out
                mv ~/Sra/*_2.fastq ~/2Fastq.out
                #用hisat2进行比对
                for j in ~/1Fastq_out/*_1.fastq
                do
                        for h in ~/2Fastq_out/*_2.fastq
                        do
                                b=$(echo $j | cut -d "_" -f1)
                                c=$(echo $h | cut -d "_" -f1)
                                if [ $b = $c ];then
                                        hisat2 -p 5 -x ~/hg19/genome -U -1 $j -2 $h -S $b.sam
                                mv ~/2Fastq_out/*.sam ~/Sam_out
                                fi
                        done
                done
        fi
done
#用samtools进行排序
for y in ~/Sam_out/*sam
do
        echo $y
        d=$(echo $y | cut -d "." -f1)
        samtools sort -n -@ 5 -o $d.bam $y
        mv ~/Sam_out/*bam ~/Sorted.bam
done
#用HTseq-count进行基因表达量计算
for z in ~/Sorted.bam/*bam
do
        echo $z
        e=$(echo $z | cut -d "." -f1)
        htseq-count -f bam -r name -s no -a 10 -t exon -i gene_id -m intersection-nonempty $z ~/hg19/gencode.v29lift37.annotation.gtf>$ecounts.txt
        mv ~/Sorted_bam/*.txt ~/Counts
done
#把不要的文件夹删除只留下counts文件夹
rm -rf ~/Sra
rm -rf ~/Fastq_out
rm -rf ~/1Fastq_out
rm -rf ~/2Fastq_out
rm -rf ~/Sam_out
rm -rf ~/Sorted.bam