# HG changeset patch # User Jim Johnson # Date 1386262468 21600 # Node ID 1ff2fc8da32813e05adff157300bba37ca3ed9b2 # Parent 64d45f9593038d400c26fff91e46d38f03be07bb Updates to rsem_calculate_expression.xml diff -r 64d45f959303 -r 1ff2fc8da328 extract_transcript_to_gene_map_from_trinity.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/extract_transcript_to_gene_map_from_trinity.xml Thu Dec 05 10:54:28 2013 -0600 @@ -0,0 +1,35 @@ + + extract transcript to gene map from trinity + + rsem + + + extract-transcript-to-gene-map-from-trinity $trinity_fasta_file $map_file + + + + + + + + + + + + + + +RSEM HOME PAGE - http://deweylab.biostat.wisc.edu/rsem/ + +NAME + extract-transcript-to-gene-map-from-trinity + +SYNOPSIS + extract-transcript-to-gene-map-from-trinity trinity_fasta_file map_file + +DESCRIPTION + generates a gene_mp_file from a trinity fasta file + + + + diff -r 64d45f959303 -r 1ff2fc8da328 rsem.py --- a/rsem.py Mon Nov 11 13:54:43 2013 -0500 +++ b/rsem.py Thu Dec 05 10:54:28 2013 -0600 @@ -1,5 +1,5 @@ """ -SnpEff datatypes +RSEM datatypes """ import os,os.path,re,sys import galaxy.datatypes.data @@ -8,7 +8,7 @@ class RsemReference( Html ): """Class describing an RSEM reference""" - MetadataElement( name='reference_name', default='galaxy_generated_bowtie_index', desc='RSEM Reference Name', readonly=True, visible=True, no_value=None ) + MetadataElement( name='reference_name', default=None, desc='RSEM Reference Name', readonly=True, visible=True, no_value=None ) file_ext = 'rsem_ref' is_binary = True @@ -69,7 +69,6 @@ extra_files_path/.rev.2.ebwt extra_files_path/.rev.1.ebwt """ - log.info( "RSEM reference set_meta %s %s" % (dataset,dataset.extra_files_path)) pat = '^(.*)\.grp$' efp = dataset.extra_files_path flist = os.listdir(efp) diff -r 64d45f959303 -r 1ff2fc8da328 rsem_calculate_expression.xml --- a/rsem_calculate_expression.xml Mon Nov 11 13:54:43 2013 -0500 +++ b/rsem_calculate_expression.xml Thu Dec 05 10:54:28 2013 -0600 @@ -5,179 +5,289 @@ samtools bowtie - + rsem-calculate-expression - --calc-ci $useci.ci - --fragment-length-mean $fraglenmean - --fragment-length-min $fraglenmin - --fragment-length-sd $fraglensd - --fragment-length-max $fraglenmax - --bowtie-e $bowtie_e - --bowtie-m $bowtie_m - - #if $input.format=="fastq" - ## IF FASTQ AND SINGLE END READS (DEFAULTS) - #if $input.fastqmatepair.matepair=="single" #rsem-wrapper-1.1.17.pl --bam_genome $bam_genome --bamtype $bamtype - --seed-length $seedlength $input.fastq_select --estimate-rspd $rspd --forward-prob - $fprob -p $cpus --bowtie-n $bowtie_mis --output-genome-bam --single_fastq $singlefastq - --output $output --isoformfile $isoforms --bamfile $bam_res --log $log - --sampling-for-bam $sampling_for_bam --reference ${index.fields.path} - #end if - ## IF FASTQ AND PAIRED END READS (DEFAULTS) - #if $input.fastqmatepair.matepair=="paired" #rsem-wrapper-1.1.17.pl --bam_genome $bam_genome --bamtype $bamtype - --paired-end --seed-length $seedlength --estimate-rspd $rspd $input.fastq_select --forward-prob $fprob -p $cpus - --bowtie-n $bowtie_mis --output-genome-bam --fastq1 $fastq1 --fastq2 $fastq2 --output - $output --isoformfile $isoforms --bamfile $bam_res --log $log --sampling-for-bam - $sampling_for_bam --reference ${index.fields.path} - #end if - #end if - #if $input.format=="fasta" - ## IF FASTA AND SINGLE END READS (DEFAULTS) - #if $input.fastamatepair.matepair=="single" #rsem-wrapper-1.1.17.pl --bam_genome $bam_genome --bamtype $bamtype - --no-qualities --seed-length $seedlength --estimate-rspd $rspd --forward-prob $fprob -p $cpus --bowtie-n $bowtie_mis - --output-genome-bam --single_fasta $single_fasta --output $output --isoformfile - $isoforms --bamfile $bam_res --log $log --sampling-for-bam $sampling_for_bam --reference - ${index.fields.path} + ## --tag string + #if $seedlength: + --seed-length $seedlength + #end if + --forward-prob $forward_prob + #if $rsem_options.fullparams == 'fullset': + ## Fragment info + #if $rsem_options.fragment_length_mean: + --fragment-length-mean $rsem_options.fragment_length_mean + #end if + #if $rsem_options.fragment_length_min: + --fragment-length-min $rsem_options.fragment_length_min + #end if + #if $rsem_options.fragment_length_sd: + --fragment-length-sd $rsem_options.fragment_length_sd + #end if + #if $rsem_options.fragment_length_max: + --fragment-length-max $rsem_options.fragment_length_max + #end if + ## RSPD + #if $rsem_options.rspd.estimate == 'yes': + --estimate-rspd + #if $rsem_options.rspd.num_rspd_bins: + --num-rspd-bins $rsem_options.rspd.num_rspd_bins + #end if + #end if + ## Calculate 95% credibility intervals and posterior mean estimates. + #if $rsem_options.useci.ci == 'yes': + --calc-ci + #if $rsem_options.useci.cimem: + --ci-memory $rsem_options.useci.cimem #end if - ## IF FASTA AND PAIRED END READS (DEFAULTS) - #if $input.fastamatepair.matepair=="paired" #rsem-wrapper-1.1.17.pl --bam_genome $bam_genome --bamtype $bamtype - --no-qualities --paired-end --seed-length $seedlength --estimate-rspd $rspd --forward-prob $fprob -p $cpus - --bowtie-n $bowtie_mis --output-genome-bam --fasta1 $fasta1 --fasta2 $fasta2 --output - $output --isoformfile $isoforms --bamfile $bam_res --log $log --sampling-for-bam - $sampling_for_bam --reference ${index.fields.path} - #end if + #end if + #end if + ## --num-threads $GALAXY_SLOTS + #if $input.format != 'bam' and $input.bowtie_options.fullparams == 'fullset': + ## Bowtie params + #if $bowtie_options.bowtie_e: + --bowtie-e $bowtie_options.bowtie_e + #end if + #if $bowtie_options.bowtie_m: + --bowtie-m $bowtie_options.bowtie_m + #end if + #if $bowtie_options.bowtie_n: + --bowtie-n $bowtie_options.bowtie_n + #end if + #end if + ## Outputs + #if $rsem_outputs.result_bams == 'none': + --no-bam-output + #else + #if $rsem_outputs.result_bams == 'both': + --output-genome-bam + #end if + $rsem_outputs.sampling_for_bam + #end if + ## Input data + #if $input.format=="fastq" + $input.fastq_select + #if $input.fastq.matepair=="single": + $input.fastq.singlefastq + #elif $input.fastq.matepair=="paired": + --paired-end + $input.fastq.fastq1 + $input.fastq.fastq2 + #end if + #elif $input.format=="fasta" + --no-qualities + #if $input.fasta.matepair=="single": + $input.fasta.singlefasta + #elif $input.fasta.matepair=="paired": + --paired-end + $input.fasta.fasta1 + $input.fasta.fasta2 + #end if + #elif $input.format=="sam" + #if $input.matepair=="paired": + --paired-end + #end if + #if $input.rsem_sam._extension == 'sam': + --sam + #elif $input.rsem_sam._extension == 'bam': + --bam + #end if + $input.rsem_sam + #end if + ## RSEM reference + #if $reference.refSrc == 'history': + ${reference.rsem_ref.extra_files_path}/${reference.rsem_ref.metadata.reference_name} + #elif $reference.refSrc == 'cached': + ${reference.index.fields.path} #end if - - - - - - - - - - - - - - - - + ## sample_name: use a hard coded name so we can pull out galaxy outputs + rsem_output + ## direct output into logfile + > $log + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + When RSEM generates a BAM file, instead of outputing all alignments a read has with their posterior probabilities, one alignment is sampled according to the posterior probabilities. The sampling procedure includes the alignment to the "noise" transcript, which does not appear in the BAM file. Only the sampled alignment has a weight of 1. All other alignments have weight 0. If the "noise" transcript is sampled, all alignments appeared in the BAM file should have weight 0. (Default: off) + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - - - bamtype == "yes" + + + + rsem_outputs['result_bams'] != "none" - + + rsem_outputs['result_bams'] != "none" + + + rsem_outputs['result_bams'] == "both" + + + rsem_outputs['result_bams'] == "both" + diff -r 64d45f959303 -r 1ff2fc8da328 rsem_prepare_reference.xml --- a/rsem_prepare_reference.xml Mon Nov 11 13:54:43 2013 -0500 +++ b/rsem_prepare_reference.xml Thu Dec 05 10:54:28 2013 -0600 @@ -5,6 +5,8 @@ bowtie + mkdir $reference_file.extra_files_path && + cd $reference_file.extra_files_path && rsem-prepare-reference #if $polya.polya_use == 'add': #if $polya.polya_length: diff -r 64d45f959303 -r 1ff2fc8da328 tool_dependencies.xml --- a/tool_dependencies.xml Mon Nov 11 13:54:43 2013 -0500 +++ b/tool_dependencies.xml Thu Dec 05 10:54:28 2013 -0600 @@ -1,7 +1,7 @@ - +