use warnings; $sentence='kinase inhibitor SET6 activates p16(INK4A) in cell-wall.'; my @phrases = ('kinase i', 'inhibitor', 'tor SET6', 'SET6', 'p16(INK4A)', 'cell'); my $phrases_re = join '|', map { quotemeta } @phrases; $sentence =~ s/(^| )($phrases_re)(?= |$)/$1#$2#/g; print $sentence, "\n"; #### kinase #inhibitor# #SET6# activates #p16(INK4A)# in cell-wall. #### $sentence =~ s/(^| )($phrases_re)( |$)/$1#$2#$3/g for 0, 1; #### use 5.010; given ($sentence) { s/ / /g; s/(^| )($phrases_re)( |$)/$1#$2#$3/g; s/ / /g; } #### my %phrase; $phrase{$_}++ for @phrases; my @sentence = split /( +)/, $sentence; for (@sentence) { $phrase{$_} and $_ = "#" . $_ . "#"; }; $sentence = join "", @sentence; #### $sentence =~ s/(?