根据位置从gff中提取gene

小程序-根据位置从gff中提取gene

Table of Contents

• 1 需要的文件格式
• 2 程序

1 需要的文件格式

1:  染色体 位置

2 程序

 1:  use strict;
 2:  use warnings;
 3:   
 4:  my (@information,$chr,%hash,$key1,$key2,);
 5:  
 6:  #构建gff的hash
 7:  
 8:  my  $in_in = "saccharomyces_cerevisiae_R64-1-1_20110208.gff";
 9:  open  my $in, '<', $in_in or die "cannot open\n";
10:  while(<$in>)
11:  {
12:      chomp;
13:      next if /^#/;
14:      @information=split/\s+/,$_;
15:      if ($information[2] eq "gene")
16:      {
17:          $information[0]=~/^chr(.+)/;
18:          $chr=$1;
19:          $information[8]=~/^ID=(.+?);/;
20:          $hash{$chr}{$information[3]}{$information[4]} = $1;
21:      }
22:  }
23:  close  $in;
24:   
25:   
26:  my  $out_out = "pos_with_gene.txt";
27:  open  my $out, '>', $out_out or die  "failed open$!\n";
28:  #根据染色体和位置信息，遍历寻找 
29:   
30:  my  $in1_in = "pos_to_find_gen.txt";
31:  open  my $in1, '<', $in1_in or die "cannot open\n";
32:  while(<$in1>)
33:  {
34:      chomp;
35:      next if /^\s+$/;
36:      @information=split/\s+/,$_;
37:      foreach $key1 (sort keys %{$hash{$information[0]}})
38:      {
39:          foreach $key2 (sort keys %{$hash{$information[0]}{$key1}})
40:          {
41:              if ($information[1]>=$key1 and $information[1]<=$key2)
42:              {
43:                  print $out "@information[0,1] $hash{$information[0]}{$key1}{$key2}\n";
44:                  last;
45:              }
46:              else
47:              {
48:                  next;
49:              }
50:          }
51:      }
52:  }
53:  close  $in1;
54:  close  $out;

Author: grc <grc@grc>

Date: 2013-06-29 22:50:30 CST

HTML generated by org-mode 6.33x in emacs 23