Mercurial > repos > mahtabm > ensembl
comparison variant_effect_predictor/Bio/Tools/RepeatMasker.pm @ 0:1f6dce3d34e0
Uploaded
| author | mahtabm |
|---|---|
| date | Thu, 11 Apr 2013 02:01:53 -0400 |
| parents | |
| children |
comparison
equal
deleted
inserted
replaced
| -1:000000000000 | 0:1f6dce3d34e0 |
|---|---|
| 1 # BioPerl module for Bio::Tools::RepeatMasker | |
| 2 # | |
| 3 # Cared for by Shawn Hoon <shawnh@fugu-sg.org> | |
| 4 # | |
| 5 # Copyright Shawn Hoon | |
| 6 # | |
| 7 # You may distribute this module under the same terms as perl itself | |
| 8 | |
| 9 # POD documentation - main docs before the code | |
| 10 | |
| 11 =head1 NAME | |
| 12 | |
| 13 Bio::Tools::RepeatMasker - DESCRIPTION of Object | |
| 14 | |
| 15 =head1 SYNOPSIS | |
| 16 | |
| 17 use Bio::Tools::RepeatMasker; | |
| 18 my $parser = new Bio::Tools::RepeatMasker(-file => 'seq.fa.out'); | |
| 19 while( my $result = $parser->next_result ) { | |
| 20 | |
| 21 } | |
| 22 | |
| 23 =head1 DESCRIPTION | |
| 24 | |
| 25 A parser for RepeatMasker output | |
| 26 | |
| 27 =head1 FEEDBACK | |
| 28 | |
| 29 =head2 Mailing Lists | |
| 30 | |
| 31 User feedback is an integral part of the evolution of this and other | |
| 32 Bioperl modules. Send your comments and suggestions preferably to | |
| 33 the Bioperl mailing list. Your participation is much appreciated. | |
| 34 | |
| 35 bioperl-l@bioperl.org - General discussion | |
| 36 http://bioperl.org/MailList.shtml - About the mailing lists | |
| 37 | |
| 38 =head2 Reporting Bugs | |
| 39 | |
| 40 Report bugs to the Bioperl bug tracking system to help us keep track | |
| 41 of the bugs and their resolution. Bug reports can be submitted via | |
| 42 email or the web: | |
| 43 | |
| 44 bioperl-bugs@bioperl.org | |
| 45 http://bugzilla.bioperl.org/ | |
| 46 | |
| 47 =head1 AUTHOR - Shawn Hoon | |
| 48 | |
| 49 Email shawnh@fugu-sg.org | |
| 50 | |
| 51 Describe contact details here | |
| 52 | |
| 53 =head1 CONTRIBUTORS | |
| 54 | |
| 55 Additional contributors names and emails here | |
| 56 | |
| 57 =head1 APPENDIX | |
| 58 | |
| 59 The rest of the documentation details each of the object methods. | |
| 60 Internal methods are usually preceded with a _ | |
| 61 | |
| 62 =cut | |
| 63 | |
| 64 | |
| 65 # Let the code begin... | |
| 66 | |
| 67 | |
| 68 package Bio::Tools::RepeatMasker; | |
| 69 use vars qw(@ISA); | |
| 70 use strict; | |
| 71 | |
| 72 use Bio::Root::Root; | |
| 73 use Bio::SeqFeature::FeaturePair; | |
| 74 use Bio::Root::IO; | |
| 75 | |
| 76 @ISA = qw(Bio::Root::Root Bio::Root::IO ); | |
| 77 | |
| 78 =head2 new | |
| 79 | |
| 80 Title : new | |
| 81 Usage : my $obj = new Bio::Tools::RepeatMasker(); | |
| 82 Function: Builds a new Bio::Tools::RepeatMasker object | |
| 83 Returns : Bio::Tools::RepeatMasker | |
| 84 Args : -fh/-file => $val, # for initing input, see Bio::Root::IO | |
| 85 | |
| 86 | |
| 87 =cut | |
| 88 | |
| 89 sub new { | |
| 90 my($class,@args) = @_; | |
| 91 | |
| 92 my $self = $class->SUPER::new(@args); | |
| 93 $self->_initialize_io(@args); | |
| 94 | |
| 95 return $self; | |
| 96 } | |
| 97 | |
| 98 =head2 next_result | |
| 99 | |
| 100 Title : next_result | |
| 101 Usage : my $r = $rpt_masker->next_result | |
| 102 Function: Get the next result set from parser data | |
| 103 Returns : L<Bio::SeqFeature::FeaturePair> | |
| 104 Args : none | |
| 105 | |
| 106 | |
| 107 =cut | |
| 108 | |
| 109 sub next_result{ | |
| 110 my ($self) = @_; | |
| 111 while ($_=$self->_readline()) { | |
| 112 if (/no repetitive sequences detected/) { | |
| 113 print STDERR "RepeatMasker didn't find any repetitive sequences\n"; | |
| 114 return ; | |
| 115 } | |
| 116 if (/\d+/) { #ignore introductory lines | |
| 117 my @element = split; | |
| 118 # ignore features with negatives | |
| 119 next if ($element[11-13] =~ /-/); | |
| 120 my (%feat1, %feat2); | |
| 121 my ($score, $query_name, $query_start, $query_end, $strand, | |
| 122 $repeat_name, $repeat_class ) = (split)[0, 4, 5, 6, 8, 9, 10]; | |
| 123 | |
| 124 my ($hit_start,$hit_end); | |
| 125 if ($strand eq '+') { | |
| 126 ($hit_start, $hit_end) = (split)[11, 12]; | |
| 127 $strand = 1; | |
| 128 } | |
| 129 elsif ($strand eq 'C') { | |
| 130 ($hit_start, $hit_end) = (split)[12, 13]; | |
| 131 $strand = -1; | |
| 132 } | |
| 133 my $rf = Bio::SeqFeature::Generic->new; | |
| 134 $rf->seq_id ($query_name); | |
| 135 $rf->score ($score); | |
| 136 $rf->start ($query_start); | |
| 137 $rf->end ($query_end); | |
| 138 $rf->strand ($strand); | |
| 139 $rf->source_tag ("RepeatMasker"); | |
| 140 $rf->primary_tag ($repeat_class); | |
| 141 my $rf2 = Bio::SeqFeature::Generic->new; | |
| 142 $rf2->seq_id ($repeat_name); | |
| 143 $rf2->score ($score); | |
| 144 $rf2->start ($hit_start); | |
| 145 $rf2->end ($hit_end); | |
| 146 $rf2->strand ($strand); | |
| 147 $rf2->source_tag ("RepeatMasker"); | |
| 148 $rf->primary_tag ($repeat_class); | |
| 149 my $fp = Bio::SeqFeature::FeaturePair->new(-feature1=>$rf, | |
| 150 -feature2=>$rf2); | |
| 151 | |
| 152 return $fp; | |
| 153 } | |
| 154 } | |
| 155 } | |
| 156 | |
| 157 1; |
