transcription_pipeline

###########
01.qc
###########

fastqc 0.rawdata/$1_1.fq.gz \
    -o 1.QC/ --noextract
fastqc 0.rawdata/$1_2.fq.gz \
    -o 1.QC/ --noextract
trim_galore \
    --cores 4
    --paired \
    --quality 20 \
    --fastqc \
    --length 25 -j 10 \
    --output_dir 2.cleandata \
    0.rawdata/$1_1.fq.gz 0.rawdata/$1_2.fq.gz

##########
02. quality control
##########

sortmerna --ref /expt/cfliu/database/RNAseq_db/sortmerna_db/smr_v4.3_default_db.fasta \
    --reads 1.cleandata/$1_1_val_1.fq.gz \
    --reads 1.cleandata/$1_2_val_2.fq.gz \
    --aligned 2.rm_rRNA/$1_aligned \
    --other 2.rm_rRNA/$1_filtered \
    --fastx --threads 60 -v \
    --workdir temp_$1/
gzip 2.rm_rRNA/$1_aligned.fq
gzip 2.rm_rRNA/$1_filtered.fq
rm -rf temp_$1/

########
03.mapping
########

mkdir -p 3.bam

hisat2 -p 30 \
    -5 15\
    -3 15\
    -x /expt/cfliu/database/RNAseq_db/mouse/grcm38_tran \
    -U 2.rm_rRNA/$1_filtered.fq.gz \
    | tee >(samtools flagstat - > 3.bam/$1.hisat2.flagstat.txt) \
    | samtools sort -O BAM \
    | tee 3.bam/$1.bam \
    | samtools index - 3.bam/$1.bam.bai

########
04.gene count
########

mkdir -p 5.result
featureCounts \
    -T 10 \
    -g 'gene_name'\
    -a /expt/cfliu/database/RNAseq_db/mouse/grcm38_tran/genome_tran.gtf \
    -o 5.result/final_featureCounts_gene_name.txt \
    3.bam/*.bam