X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=rsem-prepare-reference;h=5d954a1fc7b7f411fa8fe46d43b5cda1cb181fa6;hb=52f1bd6f44f9b2630b839f192fb9ece18581983b;hp=78743e946f2b2f1b6b02ecdb6cbeeaaebdf3c70e;hpb=fc69cf6af24c0550e55447fc82f01cb6f90c1c42;p=rsem.git diff --git a/rsem-prepare-reference b/rsem-prepare-reference index 78743e9..5d954a1 100755 --- a/rsem-prepare-reference +++ b/rsem-prepare-reference @@ -5,6 +5,8 @@ use Pod::Usage; use File::Basename; use strict; +use rsem_perl_utils; + my $status; my $gtfF = ""; @@ -93,20 +95,6 @@ if (!$no_bowtie) { &runCommand($command); } -# command, {err_msg} -sub runCommand { - print $_[0]."\n"; - my $status = system($_[0]); - if ($status != 0) { - my $errmsg; - if (scalar(@_) > 1) { $errmsg = $_[1]; } - else { $errmsg = "\"$command\" failed! Plase check if you provide correct parameters/options for the pipeline!"; } - print $errmsg."\n"; - exit(-1); - } - print "\n"; -} - __END__ =head1 NAME @@ -155,7 +143,7 @@ Each line of should be of the form: gene_id transcript_id with the two fields separated by a tab character. - + If you are using a GTF file for the "UCSC Genes" gene set from the UCSC Genome Browser, then the "knownIsoforms.txt" file (obtained from the "Downloads" section of the UCSC Genome Browser site) is of this format. If this option is off, then the mapping of isoforms to genes depends on whether the --gtf option is specified. If --gtf is specified, then RSEM uses the "gene_id" and "transcript_id" attributes in the GTF file. Otherwise, RSEM assumes that each sequence in the reference sequence files is a separate gene. @@ -164,7 +152,7 @@ If this option is off, then the mapping of isoforms to genes depends on whether =item B<--no-polyA> -Do not add poly(A) tails to the end of reference isoforms. (Default: add poly(A) tails to all transcripts) +Do not add poly(A) tails to the end of reference isoforms. (Default: adding poly(A) tails to all transcripts) =item B<--no-polyA-subset> @@ -207,7 +195,7 @@ This program will generate 'reference_name.grp', 'reference_name.ti', 'reference 'reference_name.grp', 'reference_name.ti', 'reference_name.seq', 'reference_name.idx.fa', and 'reference_name.chrlist' are used by RSEM internally. -B<'reference_name.transcripts.fa'> contains the extracted reference transcripts in FASTA format. Poly(A) tails are not added. +B<'reference_name.transcripts.fa'> contains the extracted reference transcripts in FASTA format. Poly(A) tails are added unless '--no-polyA' is set. =head1 EXAMPLES