perl 多fasta文件匹配，并提取匹配文件第一条序列

Posted 2020-11-24 mmtinfo

目标如题，有多个fasta文件和一个文件名列表，将文件名列表中包含的文件匹配出来并提取第一条序列合并成一个fa文件。

这个采用perl实现，用法和代码如下：

  1 #!/usr/bin/perl -w
  2 use strict;
  3 
  4 sub usage{
  5 	die "usage:perl $0 <fa.list> <Fasta_Dir> <merged.fa>
",unless(@ARGV==3);
  6 }
  7 usage();
  8 
  9 open LIST,"$ARGV[0]";
 10 open F,"$ARGV[1]";
 11 open OU,">$ARGV[2]";
 12 
 13 my @listName=<LIST>;
 14 
 15 my @files=glob("$ARGV[1]/*.faa");
 16 my $matchNum=0;
 17 
 18 foreach my $k(@files){
 19 	my $fileName=(split ///,$k)[-1];
 20 	if(grep /^$fileName$/,@listName){
 21 		$matchNum+=1;
 22 		open EACH,"$ARGV[1]/$fileName";
 23 		$/=">";
 24 		<EACH>;
 25 		while(<EACH>){
 26 			chomp;
 27 			my @info=split /
/,$_;
 28 			my $seqID=shift @info;
 29 			my $seq=join "",@info;
 30 			print OU ">$seqID
$seq
";
 31 			last;
 32 		}
 33 		$/="
";
 34 	}
 35 }
 36 
 37 print "match: $matchNum files,and merge completed!
";
 38 
 39 close LIST;
 40 close F;