snakemake-RNAseq

#  snakemake.py
SAMPLE = ['BLO_S','KID_S']
TIME = [1,2,3,4]
REP = ['1','2','3']
gtffile = "/public1/home/stu_zhangyixing/workspace/snakemake/RNASeq-ref/2.Quantification/script/run_Quantification.sh"
rule all:
    input:
        expand("2.Quantification/{sample}{time}_LD{rep}", sample = SAMPLE, time=TIME, rep=REP)
rule hisat2_build:
# hisat2-build ../ref/genome.fasta ../ref/genome 1>hisat2-build.log 2>&1
    input:
        "ref/genome.fasta"
    output:
        "ref/genome"
    shell:
        "hisat2-build {input} {output} "

rule hisat2:
# hisat2 --new-summary -p 10 -x ../ref/genome -U ../data/BLO_S1_LD1.fq.gz -S BLO_S1_LD1.sam --rna-strandness R 1>BLO_S1_LD1.log 2>&1
# BLO_S1_LD1.fq.gz  BLO_S2_LD3.fq.gz
    input:
        "ref/genome",
        "data/{sample}{time}_LD{rep}.fq.gz"
    output:
        "1.Mapping/{sample}{time}_LD{rep}.sam"

    shell:
        "hisat2 --new-summary -p 10 -x {input[0]} -U {input[1]} -S {output} --rna-strandness R "


rule samtobam:
# samtools sort -o BLO_S1_LD1.bam BLO_S1_LD1.sam
    input:
        "1.Mapping/{sample}{time}_LD{rep}.sam"
    output:
        "1.Mapping/{sample}{time}_LD{rep}.bam"
    shell:
         "samtools sort -o {output} {input}"
         
rule bam_build:
#  samtools index BLO_S1_LD1.bam
    input:
        "1.Mapping/{sample}{time}_LD{rep}.bam"
    output:
        "1.Mapping/{sample}{time}_LD{rep}.bam.bai"
    shell:
        "samtools index {input}"
rule quantification:
# /public1/home/stu_zhangyixing/workspace/snakemake/RNASeq-ref/2.Quantification/script/run_Quantification.sh 
    input:
        "1.Mapping/{sample}{time}_LD{rep}.bam",
        "ref/genes.gtf",
        "1.Mapping/{sample}{time}_LD{rep}.bam.bai" 
    output:
        "2.Quantification/{sample}{time}_LD{rep}"
    script:
        "Rscript {gtffile} -b {input[0]} -g {input[1]} -o {output}"

rulegraph.png

# snakemake -np 不执行，只是打印出来要执行的命令， -s  指定要打开的文件， 不加-s 默认是Snakefile
snakemake -np -s snakemake.py  

下面的job list 是以26字母的顺序排列的，我以为是按任务顺序呢。一直在找错误原因

image.png