美文网首页
RNA-seq实战

RNA-seq实战

作者: 晓颖_9b6f | 来源:发表于2021-01-20 12:30 被阅读0次

    代码如下

    #1、下载电脑里没有的的软件
    conda install Trim Galore cutadapt subread salmon
    #2、下载数据
    #只下载三个转录组数据 未经处理、地塞米松处理组、沙丁胺醇处理组。剩下的那些数据太多,后面太难处理了。
    prefetch SRR1039508
    prefetch SRR1039509
    prefetch SRR1039510 
    #下载参考基因组,hg38.fa。用迅雷下载的
    #下载注释,gencode.v36.annotation.gtf.gz
    wget ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_36/gencode.v36.annotation.gtf.gz
    #3、具体流程
    #SRR--fastq
    conda create -n rna python=2
    source activate rna
    fastq-dump --gzip --split-3 -O SRR1039508
    fastq-dump --gzip --split-3 -O SRR1039509
    fastq-dump --gzip --split-3 -O SRR1039510
    #质控
    fastqc -t 2 -o SRR1039508_1.fastq.gz \ SRR1039508_2.fastq.gz
    fastqc -t 2 -o SRR1039509_1.fastq.gz \ SRR1039509_2.fastq.gz
    fastqc -t 2 -o SRR10395010_1.fastq.gz \ SRR1039510_2.fastq.gz
    trim_galore -q 20 --phred33 --stringency 3 --length 20 -o  SRR1039508.fastq.gz
    trim_galore -q 20 --phred33 --stringency 3 --length 20 -o  SRR1039509.fastq.gz
    trim_galore -q 20 --phred33 --stringency 3 --length 20 -o  SRR1039510.fastq.gz
    #比对
    id="SRR1039508"
    hisat2 -p 2 -x /home/xiaoying/hg38/genome \ -1 ${id}_1_val_1.fq.gz \ -2 ${id}_2_val_2.fq.gz \ -S ${id}.hisat.sam
    id="SRR1039509"
    hisat2 -p 2 -x /home/xiaoying/hg38/genome \ -1 ${id}_1_val_1.fq.gz \ -2 ${id}_2_val_2.fq.gz \ -S ${id}.hisat.sam
    id="SRR1039510"
    hisat2 -p 2 -x /home/xiaoying/hg38/genome \ -1 ${id}_1_val_1.fq.gz \ -2 ${id}_2_val_2.fq.gz \ -S ${id}.hisat.sam
    #sam转bam
    samtools view -bS -h SRR103908.sam \ -o SRR1039508.bam
    samtools view -bS -h SRR103909.sam \ -o SRR1039509.bam
    samtools view -bS -h SRR103910.sam \ -o SRR1039510.bam
    #bam排序
    samtools sort -@ 5 SRR1039508.bam \ -o SRR1039508.sort.bam
    samtools sort -@ 5 SRR1039509.bam \ -o SRR1039509.sort.bam
    samtools sort -@ 5 SRR1039510.bam \ -o SRR1039510.sort.bam
    #计数
    for fn in {508..510}
    do
    featureCounts -T 5 -p -t exon -g gene_id \ -a /home/xiaoying/gencode.v25.annotation.gtf.gz \ -o SRR1039$fn.counts.txt SRR1039$fn.hisat.sort.bam
    done
    #salmon输出结果
    salmon index -t /home/xiaoying/Homo_sapiens.GRCh38.cdna.all.fa -i hg381_index
    salmon quant -i hg381_index  -l A -1 SRR1039508_1.fastq -2 SRR1039508_2.fastq -o SRR1039510_quant
    salmon quant -i hg381_index  -l A -1 SRR1039509_1.fastq -2 SRR1039509_2.fastq -o SRR1039509_quant
    salmon quant -i hg381_index  -l A -1 SRR1039510_1.fastq -2 SRR1039510_2.fastq -o SRR1039510_quant
    #salmon结果倒入R
    
    image.png
    image.png

    相关文章

      网友评论

          本文标题:RNA-seq实战

          本文链接:https://www.haomeiwen.com/subject/rmchzktx.html