X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=rsem-prepare-reference;h=de4f061612d4b3a976147afe48e5a22594ae3f42;hb=4f7502168c3816ba3283385f093e599527e2b144;hp=81fd13ea74edab4b31dd147db9be502e62321167;hpb=66a1547e5d549a915cefb729222be915b87fb34d;p=rsem.git

diff --git a/rsem-prepare-reference b/rsem-prepare-reference
index 81fd13e..de4f061 100755
--- a/rsem-prepare-reference
+++ b/rsem-prepare-reference
@@ -24,8 +24,11 @@ my $bowtie2_path = "";
 my $quiet = 0;
 my $help = 0;
 
+my $alleleMappingF = "";
+
 GetOptions("gtf=s" => \$gtfF,
 	   "transcript-to-gene-map=s" => \$mappingF,
+	   "allele-to-gene-map=s" => \$alleleMappingF,
 	   "no-polyA" => \$no_polyA, 
 	   "no-polyA-subset=s" => \$subsetFile,
 	   "polyA-length=i" => \$polyALen,
@@ -39,6 +42,8 @@ GetOptions("gtf=s" => \$gtfF,
 
 pod2usage(-verbose => 2) if ($help == 1);
 pod2usage(-msg => "Set --no-polyA & --no-polyA-subset at the same time!", -exitval => 2, -verbose => 2) if ($no_polyA == 1 && $subsetFile ne '');
+pod2usage(-msg => "--transcript-to-gene-map and --allele-to-gene-map are mutually exclusive!", -exitval => 2, -verbose => 2) if (($mappingF ne "") && ($alleleMappingF ne ""));
+pod2usage(-msg => "--gtf and --allele-to-gene-map are mutually exclusive!", -exitval => 2, -verbose => 2) if (($gtfF ne "") && ($alleleMappingF ne ""));
 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (scalar(@ARGV) != 2);
 
 if ($bowtie2) { $no_bowtie = 1; $no_ntog = 1; }
@@ -85,6 +90,7 @@ else {
     $"=" ";
     $command = $dir."rsem-synthesis-reference-transcripts $ARGV[1] $quiet";
     if ($mappingF ne "") { $command .= " 1 $mappingF"; }
+    elsif ($alleleMappingF ne "") { $command .= " 2 $alleleMappingF"; }
     else { $command .= " 0"; } 
     $command .= " @list";
     &runCommand($command);
@@ -164,6 +170,19 @@ If this option is off, then the mapping of isoforms to genes depends on whether
 
 (Default: off)
 
+=item B<--allele-to-gene-map> <file>
+
+Use information from <file> to provide gene_id and transcript_id information for each allele-specific transcript.
+Each line of <file> should be of the form:
+
+gene_id transcript_id allele_id
+
+with the fields separated by a tab character.
+
+This option is designed for quantifying allele-specific expression. It is only valid if '--gtf' option is not specified. allele_id should be the sequence names presented in the FASTA-formatted files.  
+
+(Default: off) 
+
 =item B<--no-polyA>
 
 Do not add poly(A) tails to the end of reference isoforms. (Default: adding poly(A) tails to all transcripts)