# Author: Rehannah Borup Helweg-Larsen
# script for sc-RNA seq mapping and FPKM estimation based on hisat2 mapping script published in: 

# Pertea, M., Kim, D., Pertea, G.M., Leek, J.T. & Salzberg, S.L. 
# Transcript-level expression analysis of RNA-seq experiments with HISAT, StringTie and Ballgown. 
# Nat Protoc 11, 1650-67 (2016).



# running AfterQC python script for trimming of fastq files using defalut settings
cd WORKDIR
python after.py 

# Generate Index for hisat2 based on gencode v27 (GRCh38)
hisat2-build -p 22 GRCh38.primary_assembly.genome.fa.gz gencode.v27

# ### Run Hisat and Stringtie script (Pertea et al. 2016): 
nohup ./rnaseq_pipeline.sh &      # calls rnaseq_pipeline_config.sh 

# remove/filter Mitochondrial reads from aligned bam files
samtools view -h $bam | awk '{if($3 != "chrM" && $3 != "chrUn"){print $0}}' | samtools view -Sb  > $bamfile    # output MT filtered bamfile 

# run stringtie on bam files to get abundance output (FPKM)

#!/bin/bash  
while read bamfile
 do
   base=`echo $bamfile | cut -d "." -f1 |cat`
   echo $base
   GTFFILE="gencode.v27.annotation.gtf" 
   stringtie -p 20 -G $GTFFILE -e -A $tsv $bamfile
 done < bam.files