Added --append-names

EM.cpp

@@ -552,9 +552,9 @@ int main(int argc, char* argv[]) {
 		printf("  -b: produce bam format output file. (default: off)\n");
 		printf("  -q: set it quiet\n");
 		printf("  --gibbs-out: generate output file used by Gibbs sampler. (default: off)\n");
-		printf("  --sampling: sample each read from its posterior distribution when bam file is generated. (default: off)\n");
+		printf("  --sampling: sample each read from its posterior distribution when BAM file is generated. (default: off)\n");
 		printf("  --seed uint32: the seed used for the BAM sampling. (default: off)\n");
-		printf("  --append-names: append transcript_name/gene_names when available. (default: off)\n");
+		printf("  --append-names: append transcript_name/gene_name when available. (default: off)\n");
 		printf("// model parameters should be in imdName.mparams.\n");
 		exit(-1);
 	}

WriteResults.h

@@ -131,8 +131,6 @@ void writeResultsEM(int M, const char* refName, const char* imdName, Transcripts
 	std::vector<int> tlens;
 	std::vector<double> fpkm, tpm, isopct;
 	std::vector<double> glens, gene_eels, gene_counts, gene_tpm, gene_fpkm;
-
-	std::string transcript_name, gene_name;
 
 	// Load group info
 	sprintf(groupF, "%s.grp", refName);
@@ -228,9 +226,9 @@ void writeResultsEM(int M, const char* refName, const char* imdName, Transcripts
 	    const Transcript& transcript = transcripts.getTranscriptAt(i);
 
 	    fprintf(fo, "%s", transcript.getTranscriptID().c_str());
-	    transcript_name = transcript.getTranscriptName();
-	    if (transcript_name != "") fprintf(fo, "_%s", transcript_name.c_str());
-	    fprintf(fo, "%c", , (i < M ? '\t' : '\n'));
+	    if (appendNames && transcript.getTranscriptName() != "") 
+	      fprintf(fo, "_%s", transcript.getTranscriptName().c_str());
+	    fprintf(fo, "%c", (i < M ? '\t' : '\n'));
 	  }
 	  for (int i = 1; i <= M; i++) {
 	    const Transcript& transcript = transcripts.getTranscriptAt(i);
@@ -315,18 +313,20 @@ void writeResultsEM(int M, const char* refName, const char* imdName, Transcripts
 		const Transcript& transcript = transcripts.getTranscriptAt(gi.spAt(i));
 
 		fprintf(fo, "%s", transcript.getGeneID().c_str());
-		gene_name = transcript.getGeneName();
-		if (appendNames && gene_name != "") fprintf(fo, "_%s", gene_name.c_str());
+		if (appendNames && transcript.getGeneName() != "") fprintf(fo, "_%s", transcript.getGeneName().c_str());
 		fprintf(fo, "%c", (i < m - 1 ? '\t' : '\n'));
 	}
 	for (int i = 0; i < m; i++) {
 		int b = gi.spAt(i), e = gi.spAt(i + 1);
 		std::string curtid = "", tid;
 		for (int j = b; j < e; j++) {
-			tid = transcripts.getTranscriptAt(j).getTranscriptID();
+			const Transcript& transcript = transcripts.getTranscriptAt(j);
+			tid = transcript.getTranscriptID();
 			if (curtid != tid) {
 			  if (curtid != "") fprintf(fo, ",");
 			  fprintf(fo, "%s", tid.c_str());
+			  if (appendNames && transcript.getTranscriptName() != "")
+			    fprintf(fo, "_%s", transcript.getTranscriptName().c_str());
 			  curtid = tid;
 			}
 		}

rsem-calculate-expression

@@ -75,6 +75,8 @@ my $bowtie2_sensitivity_level = "sensitive"; # must be one of "very_fast", "fast
 
 my $seed = "NULL";
 
+my $appendNames = 0;
+
 my $version = 0;
 
 my $mTime = 0;
@@ -128,6 +130,7 @@ GetOptions("keep-intermediate-files" => \$keep_intermediate_files,
 	   "estimate-rspd" => \$estRSPD,
 	   "num-rspd-bins=i" => \$B,
 	   "p|num-threads=i" => \$nThreads,
+	   "append-names" => \$appendNames,
 	   "no-bam-output" => sub { $genBamF = 0; },
 	   "output-genome-bam" => \$genGenomeBamF,
 	   "sampling-for-bam" => \$sampling,
@@ -466,6 +469,7 @@ if ($genBamF) {
     if ($seed ne "NULL") { $command .= " --seed $seeds[0]"; }
 }
 if ($calcPME || $calcCI) { $command .= " --gibbs-out"; }
+if ($appendNames) { $command .= " --append-names"; }
 if ($quiet) { $command .= " -q"; }
 
 &runCommand($command);
@@ -648,6 +652,10 @@ Input file is in BAM format. (Default: off)
 
 Number of threads to use. Both Bowtie/Bowtie2, expression estimation and 'samtools sort' will use this many threads. (Default: 1)
 
+=item B<--append-names>
+
+If gene_name/transcript_name is available, append it to the end of gene_id/transcript_id (separated by '_') in files 'sample_name.isoforms.results' and 'sample_name.genes.results'. (Default: off)
+
 =item B<--no-bam-output>
 
 Do not output any BAM file. (Default: off)