ag1805x

#Extract gene ids of particular biotype from GFF3 files
#Assuming: GFF3 file is Homo_sapiens.GRCh38.84.gff3 (ftp://ftp.ensembl.org/pub/release-84/gff3/homo_sapiens/Homo_sapiens.GRCh38.84.gff3.gz)
#Assuming: biotype=protein_coding

grep "biotype=protein_coding" Homo_sapiens.GRCh38.84.gff3 | cut -f9 | cut -d';' -f1 |cut -d'=' -f2 | grep "gene" | cut -d':' -f2 | sort | uniq > proten_coding_ids