Peptide::Pubmed 1.02

Peptide::Pubmed is a Perl module that can extract peptide sequences from MEDLINE article abstracts.

SYNOPSIS

use Peptide::Pubmed;
$parser = Peptide::Pubmed->new;
$in = {
PMID => q[15527327],
Author => q[Doe JJ, Smith Q],
Journal => q[J Biological Foo. 2004;8(2):123-30.],
Title => q[Foo, bar and its significance in phage display.],
Abstract =>
q[Peptide sequences EYHHYNK and Arg-Gly-Asp, but not ACCCGTNA or VEGFRI.],
Mesh => q[Genes, p53/genetics; Humans; Bar],
Chemical => q[Multienzyme Complexes; Peptide Library; Foo],
};
$parser->parse_abstract($in);

# get the peptide sequences in 1 letter symbols (select all words where the
# combined word/abstract score is above threshold:
# WordAbstScore >= WordAbstScoreMin):
@seqs = $parser->get_seqs;
print "@seqsn"; # prints: EYHHYNK RGD

EXAMPLES

# same as above, set threshold explicitly:
$parser->WordAbstScoreMin(0.4);
@seqs = $parser->get_seqs;

# set low threshold to get more peptide sequences (but at a cost of getting
# more false positives)
$parser->WordAbstScoreMin(-1);
@seqs = $parser->get_seqs;
print "@seqsn"; # prints: EYHHYNK RGD ACCCGTNA VEGFRI

# reset threshold back:
$parser->WordAbstScoreMin(0.4);

# get more data for the abstract:
$abst = $parser->get_abst;
print "$abst->{AbstScore}n"; # abstract score, in the [0,1] interval
print "$abst->{AbstMtext}n"; # abstract with sequences marked up:
# Peptide sequences EYHHYNK and Arg-Gly-Asp,
# but not ACCCGTNA or VEGFRI.

# get more data for the words, in addition to peptide sequences:
@words = $parser->get_words;
for my $word (@words) {
# combined word/abstract score, in the [0,1] interval
print "$word->{WordAbstScore}n";
# word as found in the abstract, eg Arg-Gly-Asp,
print "$word->{WordOrig}n";
# peptide sequence in 1 letter symbols, eg RGD
print "$word->{WordSequence}n";
}

# There are no mandatory input fields. This will work too, but may give lower score.
$in = {
Abstract =>
q[Peptide sequences EYHHYNK and Arg-Gly-Asp, but not ACCCGTNA or VEGFRI.],
};
$parser->parse_abstract($in);
@words = $parser->get_words;

# No peptide sequences are found in empty input:
$in = undef;
$parser->parse_abstract($in);
@words = $parser->get_words;