dec2_pipeline.txt

### cleaning
for sample in Wt-1 Wt-2 Wt-3 DecWt-1 DecWt-2 DecWt-3 P384R-1 P384R-2 P384R-3; do echo $sample; python trim_galore_pipeline.py $sample; done

### mapping
# build hisat2 index
cd ~/db/Dmel/dmel_r6.39
extract_splice_sites.py dmel-all-r6.39.gtf > dmel-all-r6.39.gtf.ss
extract_exons.py dmel-all-r6.39.gtf > dmel-all-r6.39.gtf.exon
hisat2-build -p 32 --ss dmel-all-r6.39.gtf.ss --exon dmel-all-r6.39.gtf.exon dmel-all-chromosome-r6.39.fasta dmel-all-chromosome-r6.39.fasta_hisat2_index

# build salmon index
cd ~/db/Dmel/dmel_r6.39
- create index for cdna only
#perl -lane 'print $1 if /gene:(\w+)/;' < Caenorhabditis_elegans.WBcel235.cdna.all.fa > Caenorhabditis_elegans.WBcel235.cdna.all.fa.WBGene.ids
~/software/salmon/salmon-1.6.0_linux_x86_64/bin/salmon index -p 32 \
    -t dmel-all-transcript-r6.39.fasta -i dmel-all-transcript-r6.39.fasta_hisat2_index

# hisat2 alignment
hisat2_fc_pipeline.py

# salmon alignment 
for sample in Wt-1 Wt-2 Wt-3 DecWt-1 DecWt-2 DecWt-3 P384R-1 P384R-2 P384R-3; do echo $sample; python salmon_aln.py $sample; done

### counts
# generate count files for cdna only - need to remove ncrna from salmon alignments
python salmon_counts.py

# hisat2 counts
python hisat2_counts.py

### dge
# create sample_info.txt to be used in DeSeq2
sample  Condition
WT_1    WT
WT_2    WT
WT_3    WT
DecWT_1 DecWT
DecWT_2 DecWT
DecWT_3 DecWT
P384R_1 P384R
P384R_2 P384R
P384R_3 P384R

python dge_pipeline.py # need to edit outdir in R script for this location