The script below produces the same output as in your example output. Run it as follows (assuming the script is stored as
z):
perl z tmp01 tmp02
It's formatted widespreadly for better readability.
#!/usr/bin/env perl
use strict;
use warnings;
my $seen;
while ( <> ) {
next unless /^\d/;
s/\s*$//;
next unless m/ # [file1] [file2]
^
(\S+) # PeptideID PeptideID
\s+
(\S+) # ProteinID SpectrumID
(?:
\s+
(\S+) # ----- Sequence
)?
$
/x;
if ( $3 ) {
$seen->{$1}->{SpectrumID} = $2;
$seen->{$1}->{Sequence} = $3;
} else {
push @{ $seen->{$1}->{ProteinID} }, $2;
}
}
sub frmt {
print join("\t", @_) . "\n";
}
frmt qw( PeptideID ProteinID SpectrumID Sequence );
foreach my $k ( sort { $a <=> $b } keys %{ $seen } ) {
foreach my $p ( @{ $seen->{$k}->{ProteinID} } ) {
frmt $k, $p, $seen->{$k}->{SpectrumID}, $seen->{$k}->{Sequence
+};
}
}