diff --git a/misc-scripts/xref_mapping/XrefParser/RefSeqGPFFParser.pm b/misc-scripts/xref_mapping/XrefParser/RefSeqGPFFParser.pm index b550cfbc442b7087821db97d601d69dc0c946749..37da140c579c3bbe5cc547882466acfc5b1af2d1 100644 --- a/misc-scripts/xref_mapping/XrefParser/RefSeqGPFFParser.pm +++ b/misc-scripts/xref_mapping/XrefParser/RefSeqGPFFParser.pm @@ -202,6 +202,7 @@ sub create_xrefs { { my ($acc) = $entry =~ /ACCESSION\s+(\S+)/; my ($ver) = $entry =~ /VERSION\s+(\S+)/; + my ($refseq_pair) = $entry =~ /DBSOURCE\s+REFSEQ: accession (\S+)/; # get the right source ID based on $type and whether this is predicted (X*) or not my $source_id; @@ -272,6 +273,9 @@ sub create_xrefs { foreach my $cb (@coded_by){ $xref->{PAIR} = $cb; } + if (!defined $xref->{PAIR}) { + $xref->{PAIR} = $refseq_pair; + } foreach my $pi (@protein_id){ $xref->{PROTEIN} = $pi;