install the rsem_perl_utils.pm to /usr/bin even though this is wrong

[rsem.git] / rsem-run-ebseq

diff --git a/rsem-run-ebseq b/rsem-run-ebseq
index cd4750f4a6107dccbdb27efbaf6e56e025d0a2ae..47f767859a51f97c070f6c134c216159e5da2b79 100755 (executable)
--- a/rsem-run-ebseq
+++ b/rsem-run-ebseq
@@ -1,13 +1,17 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
 
 use Getopt::Long;
 use Pod::Usage;
-use FindBin;
-use lib $FindBin::Bin;
-use strict;
 
+use FindBin;
+use lib $FindBin::RealBin;
 use rsem_perl_utils;
 
+use Env qw(@PATH);
+@PATH = ("$FindBin::RealBin/EBSeq", @PATH);
+
+use strict;
+
 my $ngvF = "";
 my $help = 0;
 
@@ -18,7 +22,6 @@ pod2usage(-verbose => 2) if ($help == 1);
 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (scalar(@ARGV) != 3);
 pod2usage(-msg => "ngvector file cannot be named as #! # is reserved for other purpose!", -exitval => 2, -verbose => 2) if ($ngvF eq "#");
 
-my $dir = "$FindBin::Bin/";
 my $command = "";
 
 my @conditions = split(/,/, $ARGV[1]);
@@ -28,7 +31,7 @@ pod2usage(-msg => "At least 2 conditions are required for differential expressio
 if ($ngvF eq "") { $ngvF = "#"; }
 
 $" = " ";
-$command = $dir."EBSeq/rsem-for-ebseq-find-DE ".$dir."EBSeq $ngvF $ARGV[0] $ARGV[2] @conditions";
+$command = "rsem-for-ebseq-find-DE $FindBin::RealBin/EBSeq $ngvF $ARGV[0] $ARGV[2] @conditions";
 &runCommand($command)
 
 __END__
@@ -85,8 +88,8 @@ This program is a wrapper over EBSeq. It performs differential expression analys
 
 This file reports the calculated statistics for all genes/transcripts. It is written as a matrix with row and column names. The row names are the genes'/transcripts' names. The column names are for the reported statistics.
 
-If there are only 2 different conditions among the samples, four statistics (columns) will be reported for each gene/transcript. They are "PPEE", "PPDE", "PostFC" and "RealFC". "PPEE" is the posterior probability (estimated by EBSeq) that a gene/transcript is equally expressed. "PPDE" is the posterior probability that a gene/transcript is differentially expressed. "PostFC" is the posterior fold change (condition 1 over condition2) for a gene/transcript. It is defined as the ratio between posterior mean expression estimates of the gene/transcript for each condition. "RealFC" is the real fold change (condition 1 over condition2) for a gene/transcript.  It is the ratio of the normalized within condition 1 mean count over normalized within condition 2 mean count for the gene/transcript. Fold changes are calculated using EBSeq's 'PostFC' function. The genes/transcripts are reported in descending order of their "PPDE" values. 
-  
+If there are only 2 different conditions among the samples, four statistics (columns) will be reported for each gene/transcript. They are "PPEE", "PPDE", "PostFC" and "RealFC". "PPEE" is the posterior probability (estimated by EBSeq) that a gene/transcript is equally expressed. "PPDE" is the posterior probability that a gene/transcript is differentially expressed. "PostFC" is the posterior fold change (condition 1 over condition2) for a gene/transcript. It is defined as the ratio between posterior mean expression estimates of the gene/transcript for each condition. "RealFC" is the real fold change (condition 1 over condition2) for a gene/transcript.  It is the ratio of the normalized within condition 1 mean count over normalized within condition 2 mean count for the gene/transcript. Fold changes are calculated using EBSeq's 'PostFC' function. The genes/transcripts are reported in descending order of their "PPDE" values.
+
 If there are more than 2 different conditions among the samples, the output format is different. For differential expression analysis with more than 2 conditions, EBSeq will enumerate all possible expression patterns (on which conditions are equally expressed and which conditions are not). Suppose there are k different patterns, the first k columns of the output file give the posterior probability of each expression pattern is true. Patterns are defined in a separate file, 'output_file.pattern'. The k+1 column gives the maximum a posteriori (MAP) expression pattern for each gene/transcript. The k+2 column gives the posterior probability that not all conditions are equally expressed (column name "PPDE"). The genes/transcripts are reported in descending order of their "PPDE" column values. For details on how EBSeq works for more than 2 conditions, please refer to EBSeq's manual.
 
 =item B<output_file.pattern>