MTandrRNA_filter.txt

##for mitochondrial gene depletion 
awk -F"\t" -v OFS='\t' '{ if ($1=="MT") print $0}' Rattus_norvegicus.mRatBN7.2.108.gtf > mitochrondrial_genes.gtf

awk -F"\t" '{ if ($3 == "gene") print $9}' mitochrondrial_genes.gtf | awk -F"; " '{print $1}' | awk -F" " '{print $2}' | sed 's/\"//g' > mitochrondrial_genes_ids.txt ##just gene_ids
awk -F"\t" '{ if ($3 == "gene") print $9}' mitochrondrial_genes.gtf | awk -F";" '{print $1 $3}' | awk -F"\"" '{print $2 "\t" $4}' >  mitochrondrial_genes_ids.txt ##use this for both ID and name

##for rRNA looking for "Biotypes"

##first select "gene"; then select 5th part of feature attributes
awk -F"\t" '{ if ($3 == "gene") print $9}' Rattus_norvegicus.mRatBN7.2.108.gtf  | awk -F"\"" '{ if ($10 =="rRNA") print $0}' | head

awk -F"\t" '{ if ($3 == "gene") print $9}' Rattus_norvegicus.mRatBN7.2.108.gtf  | awk -F"\"" '{ if ($10 =="rRNA") print $0}' > ribosomal_RNA.gtf ##attributes col 9 only
awk -F"\t" '{ if ($3 == "gene") print $0}' Rattus_norvegicus.mRatBN7.2.108.gtf  | awk -F"\"" '{ if ($10 =="rRNA") print $0}' > ribosomal_RNA.gtf

awk -F"\t" '{ print $9}' ribosomal_RNA.gtf | awk -F"; " '{print $1}' | awk -F" " '{print $2}' | sed 's/\"//g' > ribosomal_genes_ids.txt ##initial test
awk -F"\t" '{ print $9}' ribosomal_RNA.gtf | awk -F";" '{print $1 $3}' | awk -F"\"" '{print $2 "\t" $4}' > ribosomal_genes_ids.txt  ##works better gives ensembl ID and name
##and for 7SK SRP although may not use to filter
grep snRNA Rattus_norvegicus.mRatBN7.2.108.gtf | awk -F"\t" '{ if ($3 == "gene") print $9}' | awk -F"; " '{print $3}' | awk -F" " '{print $2}' | head

[eak37@htc-1024-n1 Rnor_7.0]$ grep misc Rattus_norvegicus.mRatBN7.2.108.gtf | awk -F"\t" '{ if ($3 == "gene") print $9}' | awk -F"; " '{print $3}' | awk -F" " '{print $2}' | sort | uniq
"Metazoa_SRP"
"Rn7sl1"

grep -E "Metazoa_SRP|Rn7sl1" Rattus_norvegicus.mRatBN7.2.108.gtf | awk -F"\t" '{ if ($3 == "gene") print $9}' | awk -F"; " '{print $3}' | awk -F" " '{print $2}' >

##next use the mt and rRNA gene lists to filter reads for each RNA seq sample and set counts = 0.