本期的教程代码(部分)
#!/bin/bash
#
# 使用fastq-dump解压sra数据
# 本数据集为双端数据
# 解压格式为fq.gz
for i in SRR6929571 SRR6929572 SRR6929573 SRR6929574 SRR6929577 SRR6929578;
do
pfastq-dump --split-files --threads 20 --gzip -s 00_RawData/${i}.sra --outdir 00_RawData/
## 质控
fastp -i 00_RawData/${i}_1.fastq.gz -o 01_CleanReads/${i}_1.clean.fq.gz -I 00_RawData/${i}_2.fastq.gz -O 01_CleanReads/${i}_2.clean.fq.gz -q 20 -z 4 -w 20 -h 01_CleanReads/html/${i}.html
## fastqc评估
fastqc -q -t 30 -o 01_CleanReads/fastqc/ 01_CleanReads/${i}_*.fq.gz
## 根据的信息,修改下面脚本
#mkdir 03_MappedFile/Hisat2_Mapped
#mkdir 03_MappedFile/Hisat2_Mapped/summary/
#mkdir 03_MappedFile/Hisat2_Mapped/Unmapped_reads
....
....
....
....
done
以下为获得.sort.bam
文件后进行运行。
# 合并gtf文件
ls 04_Result/Stringtie/*.gtf > 04_Result/Stringtie/mergelist.txt
stringtie --merge -F 0 -T 0 -G 02_Geneome_index/ITAG4.1_gene_models.gtf -o 04_Result/Stringtie/gffcompare/stringtie_merged.gtf 04_Result/Stringtie/mergelist.txt
## gffcomapre注释
gffcompare -r 02_Geneome_index/ITAG4.1_gene_models.gtf -G -o 04_Result/Stringtie/gffcompare/merged 04_Result/Stringtie/gffcompare/stringtie_merged.gtf
##
## 计算FPKM
mkdir 04_Result/Stringtie/featureCounts
featureCounts -T 20 -p -t exon -g transcript_id -a 04_Result/Stringtie/gffcompare/stringtie_merged.gtf -o 04_Result/Stringtie/featureCounts/All.transcript.count.txt 03_MappedFile/Hisat2_Mapped/*.sort.bam
###
## Count to FPKM
cat 04_Result/Stringtie/featureCounts/All.transcript.count.txt | cut -f 1,6-13 > 04_Result/Stringtie/featureCounts/01.all.count.txt
perl CountToFPKM.pl 04_Result/Stringtie/featureCounts/01.all.count.txt > 04_Result/Stringtie/featureCounts/02.all.FPKM.txt
一、写在前面
今天分享一个转录组上游分析的流程(Hisat2-Stringtie-Count)
,此流程的操作依旧是非常简单的。我们的流程主要使用软件的安装
、数据下载
、过滤
、比对
、Count
、Count To FPKM
等流程。
二、软件的安装
1. Conda软件安装
conda是常用的软件安装和管理