1 软件安装
https://www.jianshu.com/p/eb89ab4af035
linux平台下需要安装的软件:fastqc,fastp,hisat2,samtools,htseq
2下载基因组序列和基因组注释文件
猪基因组:
wget -c http://ftp.ensembl.org/pub/release-104/fasta/sus_scrofa/dna/Sus_scrofa.Sscrofa11.1.dna.toplevel.fa.gz
基因组注释文件
wget -c http://ftp.ensembl.org/pub/release-104/gtf/sus_scrofa/Sus_scrofa.Sscrofa11.1.104.gtf.gz
3构建索引文件
hisat2-build -p 2 Sus_scrofa.Sscrofa11.1.dna.toplevel.fa Sus_scrofa
4过滤raw reads
mkdir -p fastp
ls *1.fastq.gz|while read id;
do
fastp -5 20 -i ${id%_*}_1.fastq.gz -I ${id%_*}_2.fastq.gz \
-o ${id%_*}_1.clean.fq.gz -O ${id%_*}_2.clean.fq.gz \
-j ./fastp/${id%_*}.json -h ./fastp/${id%_*}.html;
done
5比对
ls *1.clean.fq.gz|while read id;
do
hisat2 -t -p 2 -x /media/lzx/0000678400004823/Indexs/Hisat2/Chicken/Sus_scrofa \
-1 $id -2 ${id%_*}_2.clean.fq.gz \
2>${id%%_*}.hisat2.log \
|samtools sort -@ 2 -o ${id%_*}_ht2p.bam
done
网友评论