cgi-bin/search/unigene-estscan-detail.pl

   1 #!/usr/bin/perl -w
   2 use strict;
   3 use CXGN::Page;
   4 use CXGN::Page::FormattingHelpers qw/  page_title_html
   5                                        blue_section_html
   6                                        html_break_string
   7                                     /;
   8 use CXGN::DB::Connection;
   9 use CXGN::Transcript::Unigene;
  10 use CXGN::Transcript::CDS;
  11 use Bio::Seq;
  12
  13 my $page = CXGN::Page->new( "ESTScan Details", "Chenwei Lin");
  14 my ($unigene_id) = $page->get_encoded_arguments("unigene_id");
  15
  16
  17 my $dbh = CXGN::DB::Connection->new();
  18
  19
  20 my $unigene = CXGN::Transcript::Unigene->new($dbh, $unigene_id);
  21 my $unigene_seq = uc($unigene->get_sequence());
  22 my @cds = $unigene->get_cds_list(); ##gets list of cds ids associated with the given unigene_id
  23
  24 my $estscan_pep_content = "";
  25 my $estscan_clean_cds_content = "";
  26 my $estscan_edit_cds_content = "";
  27 my $direction_content = "";
  28 my $score_content = "";
  29
  30
  31 foreach my $c (@cds) {
  32     if ($c->get_method() eq "estscan") {
  33         my $seq_text = $c->get_seq_text();
  34         my $seq_edits = $c->get_seq_edits();
  35         my $protein_seq = $c->get_protein_seq();
  36         my $begin = $c->get_begin();
  37         my $end = $c->get_end();
  38         my $direction = $c->get_direction();
  39         my $score = $c->get_score();
  40
  41         $estscan_pep_content = html_break_string($protein_seq,90);
  42         $estscan_clean_cds_content = html_break_string($seq_edits,90);
  43         $estscan_pep_content = qq{<tr><td class="sequence">$estscan_pep_content</td></tr>};
  44         $estscan_clean_cds_content = qq{<tr><td class="sequence">$estscan_clean_cds_content</td></tr>};
  45         $direction_content = ($direction eq 'F')
  46             ? '<tr><td>Forward</td></tr>'
  47             : '<tr><td>Reverse</td></tr>';
  48
  49         $score_content = "<tr><td>$score</td></tr>";
  50
  51         $estscan_edit_cds_content = reformat_unigene_sequence_with_edits($c,$unigene_seq, $direction, $begin, $end, $seq_text);
  52
  53     }
  54 }
  55
  56 my $note_content = <<EOH;
  57 <br /><span style="color: blue">ACTGX</span><span style="color: gray"> -- Inserted by ESTScan</span>
  58 <br /><span style="color: red">actgn</span><span style="color: gray"> -- Deleted by ESTScan</span>
  59 <br /><span style="color: gray">ACTGN</span><span style="color: gray"> -- UTR Deleted by ESTScan</span>
  60 <br />
  61 EOH
  62
  63 $page->header();
  64 print page_title_html("ESTScan Details for Unigene SGN-U$unigene_id");
  65 print blue_section_html('Score','<table width="100%" cellpadding="0" cellspacing="0" border="0">'.$score_content.'</table>');
  66 print blue_section_html('Direction', '<table width="100%" cellpadding="0" cellspacing="0" border="0">'.$direction_content.'</table>');
  67 print blue_section_html('Predicted Peptide Sequence','<table width="100%" cellpadding="0" cellspacing="0" border="0">'.$estscan_pep_content.'</table>');
  68 print blue_section_html('Predicted Coding Sequence','<table width="100%" cellpadding="0" cellspacing="0" border="0">'.$estscan_clean_cds_content.'</table>');
  69 print blue_section_html('Edits in Original Sequence','<table width="100%" cellpadding="0" cellspacing="0" border="0">'.$estscan_edit_cds_content.'<tr><td>'. $note_content.'</td></tr>'.'</table>');
  70
  71
  72 $page->footer();
  73
  74 sub empty_search {
  75
  76   $page->header();
  77
  78   print <<EOF;
  79   <br />
  80   <b>No unigene search criteria specified</b>
  81
  82 EOF
  83
  84   $page->footer();
  85
  86   exit 0;
  87 }
  88
  89 sub invalid_search {
  90   my ($unigene_id) = @_;
  91
  92   $page->header();
  93
  94   print <<EOF;
  95   <br />
  96   <b>The specified unigene identifer ($unigene_id) does not result in a valid search.</b>
  97
  98 EOF
  99
 100   $page->footer();
 101   exit 0;
 102
 103 }
 104
 105 sub reformat_unigene_sequence_with_edits {
 106
 107     my $self = shift;
 108     my $unigene_seq = shift;
 109     my $direction = shift;
 110     my $begin = shift;
 111     my $end = shift;
 112     my $seq_text = shift;
 113     my $estscan_edit_cds_content = "";
 114
 115     #correctly gets reverse compliment of a unigene sequence
 116     if ($direction eq 'R'){
 117         my $u = Bio::Seq->new();
 118         $u->seq($unigene_seq);
 119         my $rc = $u->revcom();
 120         $unigene_seq = $rc->seq();
 121     }
 122     my $up_seq = substr($unigene_seq, 0, ($begin-1));
 123     my $down_seq = substr($unigene_seq,$end);
 124
 125     $down_seq =~ s/\s//g;
 126     $up_seq =~ s/\s//g;
 127     $seq_text =~ s/\s//g;
 128
 129     $seq_text = "${up_seq}(5')${seq_text}(3')${down_seq}";
 130     $estscan_edit_cds_content = html_break_string($seq_text,90);
 131
 132     #my @text_components = split /\(5'\)|\(3'\)/,$estscan_edit_cds_content; ##doesn't split if the (5') or (3') markers are split on two lines
 133     my @text_components = split /5|3/,$estscan_edit_cds_content;
 134
 135
 136         ##Color the edited nucleotides
 137     foreach my $comp (@text_components) {
 138         $comp =~ s/[\(\)\']//g;
 139         $comp =~ s!([actgn])!<span style="color: red">$1</span>!g;
 140         $comp =~ s!X!<span style="color: blue">X</span>!g;
 141         $comp ||= '';
 142     }
 143
 144     $estscan_edit_cds_content = qq{<span style="color: gray">$text_components[0]</span>(5')$text_components[1](3')<span style="color: gray">$text_components[2]</span>};
 145
 146     $estscan_edit_cds_content = qq{<tr><td class="sequence">$estscan_edit_cds_content</td></tr>};
 147
 148     return $estscan_edit_cds_content;
 149
 150 }
 151