suppa做RNA_Splicing

suppa做RNA_Splicing

环境配置

#创建虚拟环境，并安装好salmon，gffread，suppa三个工具

conda create -n suppa
source activate suppa
conda install bioconda::salmon
conda install bioconda::gffread
conda install bioconda::suppa

step1

#gtf剪切

suppa.py generateEvents -i /share/pub/liangjc/genome/bmy/Danio_rerio.GRCz11.110.gtf -o Danio_splicing_events -f ioe -e SE SS MX RI FL

#提取gtf转录本

gffread -w Danio_rerio.GRCz11.110.transcripts.fasta -g /share/pub/liangjc/genome/bmy/Danio_rerio.GRCz11.dna.primary_assembly.fa /share/pub/liangjc/genome/bmy/Danio_rerio.GRCz11.110.gtf

#合并所有ioe文件

awk ’
FNR==1 && NR!=1 { while (/^

/) getline; }
1 {print}
’ *.ioe > Danio.events.ioe

#为gtf转录本构建索引

salmon index -t Danio_rerio.GRCz11.110.transcripts.fasta -i Danio_rerio.GRCz11.110.transcripts.index

step2

#估计转录组表达量（TPM值）

salmon quant -i /share/pub/liangjc/RNA_splicing/Danio_rerio.GRCz11.110.transcripts.index/ -l ISF --gcBias -1 /share/pub/liangjc/bmy/RNA-seqW/CN-1-0.25.R1.fq.gz -2 /share/pub/liangjc/bmy/RNA-seqW/CN-1-0.25.R2.fq.gz -p 10 -o test_output

step3

#得到符合要求的tpm文件

multipleFieldSelection.py -i /share/pub/liangjc/RNA_splicing/test_output/quant.sf -k 1 -f 4 -o iso_tpm.txt
perl -alne ‘{/(|.*|)\t/; ;s/$1//g;s/|//g;print}’ iso_tpm.txt > iso_tpm_formatted.txt

#计算psi

suppa.py psiPerEvent -i /share/pub/liangjc/RNA_splicing/ Danio.events.ioe -e /share/pub/liangjc/RNA_splicing/iso_tpm_formatted.txt -o test

step4

#做差异分析

suppa.py diffSplice --method empirical --input /share/pub/liangjc/RNA_splicing/ Danio.events.ioe --psi <Cond1.psi> <Cond2.psi> --tpm <Cond1_expression-file> <Cond2_expression-file> --area 1000 --lower-bound 0.05 -gc -o