use strict; use warnings; while (<>) { if (/^DE|^GN|^ID/) { my $lines = $_; if ($lines =~ /^DE|^GN/ && $lines !~ /Putative uncharacterized protein/) { my @pairs = $lines =~ /(.+?=.+?;)/g; for my $pair (@pairs) { if ($pair =~ /=(.+);/) { print lc($1), "\n"; } } } elsif ($lines =~ /^ID/) { print " \n"; } } } __END__ adp-ribosylation factor 1 arf1 arf, plarf