update to v2.8.7

oushujun · May 20, 2020 · 053d9b4 · 053d9b4
1 parent bc211b9
commit 053d9b4
Show file tree

Hide file tree

Showing 2 changed files with 14 additions and 10 deletions.
diff --git a/LTR_retriever b/LTR_retriever
@@ -5,7 +5,7 @@ use File::Basename;
 
 ##Supported dependent program versions (or up): GenomeTools/1.5.1, BLAST+/2.2.25, BLAST/2.2.25, HMMER/3.1b1, RepeatMasker/3.3.0, CDHIT/4.5.6, Tandem Repeats Finder 4.07b, and Perl 5.0.0
 
-my $version="v2.8.6";
+my $version="v2.8.7";
 my $help="
 ##########################
 ### LTR_retriever $version ###
@@ -125,7 +125,6 @@ my $TEhmm="$script_path/database/TEfam.hmm";
 my $miu="1.3e-8"; #neutral mutation rate of the target species (per bp per ya), e.g., rice: 1.3e-8 (Ma and Bennetzen 2004); mammal: 2.2e−9 (S. Kumar 2002); Drosophila: 1.6e-8 (Bowen and McDonald 2001);
 my $step = "Init"; #start the program from a particular step. Default: Init (from the beginning).
 my $threads=4;
-#my $scn=''; #store screen output information
 
 my $k=0;
 my $argv='';
@@ -798,7 +797,6 @@ print "$date\tModule 5: Start to remove DNA TE and LINE transposases, and remove
 `cat $index.ltrTE.stg3.cln.clean.exclude.child >> $genome.LTRlib.exclude.tgt`;
 
 `mv $index.ltrTE.stg3.cln.clean.clean.clean $index.ltrTE`;
-#`mv $index.ltrTE.stg3.cln.clean.clean $index.ltrTE`;
 
 #generate clean pass.list without plant protein contamination
 `perl $script_path/bin/output_by_list.pl 1 $index.ltrTE.pass.list 1 $index.ltrTE.stg3.cln.clean.exclude.father -ex > $index.ltrTE.pass.list.cln`;

diff --git a/bin/output_by_list.pl b/bin/output_by_list.pl
@@ -1,10 +1,10 @@
 #!/usr/bin/env perl
+use warnings;
+use strict;
 
 ##Shujun Ou
 ##usage: $ perl output_by_list.pl target_file list_file > outfile
 
-use warnings;
-use strict;
 
 my $usage="\n#usage: \$ perl output_by_list.pl DB_index_pos database LS_index_pos LIST [Exclusive]* [MSU_format] [FASTA_format] [version]> outfile
 	* [] parameters are optional. 
@@ -16,6 +16,7 @@
 output_by_list: program for extracting information in database by provided list
 Author: Shujun Ou, Department of Horticulture, Michigan State University, East Lansing, MI, 48823, USA
 Version: 1.5 2014/05/12
+update: 1.6 2019/07/25
 \n";
 
 my $msuL=0;
@@ -45,11 +46,13 @@
 	s/^\s+//;
 	chomp;
 	my $loc=(split)[$list_pos];
+	next unless defined $loc;
 	$loc=~s/\|.*$//;
 	$loc=~s/\[.*\]//g;
 	if ($msuL){ #for MSU LOC position recognision 
-		$loc=(split /:/, $loc)[1];
-		$loc=~s/\.\..*$//;
+		$loc=~s/#.*//;
+		$loc=~s/\.+$//;
+		$loc=~s/^.*[_:\-.]+([0-9]+)[_:\-.]+([0-9]+)$/$1..$2/;
 		}
 	$data{$loc}=undef;
 }
@@ -60,13 +63,16 @@
 	s/>//g;
 	s/^\s+//;
 	my $pos=(split)[$data_pos];
+	next unless defined $pos;
 	if ($pos=~/pos/i){ print $_ }
 	$pos=~s/\[.*\]//g;
 	if ($pos=~/^([0-9]+),.*$/){$pos=$1}
-	my ($p1, $p2)=($1, $2) if $pos=~/(.*)\|(.*)$/;
+	my ($p1, $p2)=(0, 0);
+	($p1, $p2)=($1, $2) if $pos=~/(.*)\|(.*)$/;
 	if ($msuD){
-		$pos=(split /:/, $pos)[1];
-		$pos=~s/\.\..*$//;
+		$pos=~s/#.*//;
+		$pos=~s/\.+$//;
+		$pos=~s/^.*[_:\-.]+([0-9]+)[_:\-.]+([0-9]+)$/$1..$2/;
 		}
         if (exists $data{$pos} or exists $data{$p1} or exists $data{$p2}){
 		if ($exclude==0){