A script to import RepeatMasker output

#!/usr/bin/perl -w

# 

# A perl script to enrich the GFF3 annotation. After rmsk2bed | bed2gff3 conversion 

# the repeat class remains in the *.out file. This script adds it to the Name variable

# and changes it to lowercase name.

# 

# Usage: perl enrich_rmsk_gff3_annotation.pl RM_output/Athaliana_167_TAIR10.fa.out.gff3 RM_output/Athaliana_167_TAIR10.fa.out

# 

open(GFF,"$ARGV[0]") || die "Can't open GFF. Exiting\n";

open(OUT,"$ARGV[1]") || die "Can't open OUT. Exiting\n";

# Read headers

$line_gff = <GFF>;

$line_out = <OUT>;

$line_out = <OUT>;

$line_out = <OUT>;

# Read the lines from the two files

while($line_gff = <GFF>) {

  chop($line_gff);

  $line_out = <OUT>;

  chop($line_out);

  # extract the repeat class from *.out (column 11)

  $line_out =~ m/^ +[^ ]+ +[^ ]+ +[^ ]+ +[^ ]+ +[^ ]+ +[^ ]+ +[^ ]+ +[^ ]+ +[^ ]+ +[^ ]+ +([^ ]+) /;

  $repclass = $1;

  if(defined($repclass)) {

  # add repeat class to the GFF file and print it out

  #print STDERR "GFF: $line_gff\n";

  #print STDERR "REP: $repclass\n";

  $line_gff =~ s/Name=[^ \t]+/annot=$repclass/;

  #print STDERR "OUT: $line_out\n";

  print "$line_gff\n";

  }

}

close(OUT);

close(GFF);

exit 1;