use strict;
use warnings;

my $sentence = 'The Doc4 protein , stress-induced flibbled the woozle in the presence of gonadotrophin alpha 2 subunit';

my %proteinLU;

while (<DATA>) {
    chomp;

    my $protein = $_;
    my @parts = split;
    my $parent = \%proteinLU;

    while (@parts) {
        my $part = shift @parts;

        $parent = $parent->{$part} ||= {};
        next if @parts;
        $parent->{_name_} = $protein;
    }
}

my @words = split ' ', $sentence;

while (@words) {
    my $word = shift @words;

    next if ! exists $proteinLU{$word};

    my $parent = $proteinLU{$word};
    my $wIndex = 0;

    while ($wIndex < @words && exists $parent->{$words[$wIndex]}) {
        $parent = $parent->{$words[$wIndex++]}
    }

    print "$parent->{_name_}\n" if exists $parent->{_name_};
}


__DATA__
7-phospho-2-dehydro-3-deoxy-D-arabino-heptonate D-erythrose-4-phosphate lyase (pyruvate-phosphorylating)
gamma-glutamyl-gamma-aminobutyraldehyde dehydrogenase (Gamma-Glu-gamma-aminobutyraldehyde dehydrogenase)
3-phosphoshikimate 1-carboxyvinyltransferase (5-enolpyruvylshikimate-3-phosphate synthase)(EPSP synthase
Hypothetical protein CBG17340
gonadotrophin alpha 2 subunit
Doc4 protein , stress-induced
optomotor-blind
Dfrizzled-3
Tramtrack69
gutfeeling
betaFTZ-F1
Sex-lethal
Strabismus
PAR3alpha
Armadillo
AP-2alpha
GLUT1CBP
eIF3-p44
Flamingo
PP2Czeta
PLCgamma
TFIIIC90
Wingless
Frizzled
Profilin
TXBP151